Physical AI Brief
Daily cross-source signals for the Physical AI supply chain — silicon photonics, CPO, VLA models, humanoid hardware, embodied AI. Three streams, one page, zero filler.
492 items today · 438 arxiv · 0 SEC 8-K · 54 humanoid · 0 CN photonics
01 ARXIV · PHYSICAL AI PAPERS
438 items- arxiv:2610.08791 · cs.CVWorld Models' Last Exam in PhysicsMingju Gao, Qingle Liu, Yuzhao Peng, Xinjie Lin +7
Video world models can produce visually convincing yet physically inconsistent sequences, raising concerns about their reliability for prediction and planning in embodied AI systems. Existing evaluations often rely on model-based judgments or reference videos, while direct physical tests largely focus on mechanics. We introduce World Models' Last Exam in Physics, a measurement-based benchmark for evaluating physical consistency in video world models. The benchmark comprises 40 controlled tasks spanning mechanics, optics, fluids, thermal and phase-change phenomena, electromagnetism, and surface tension. Each task pairs an initial image and a generation prompt with predefined physical criteria, enabling interpretable tests of observable physical relationships without requiring reference videos. Its evaluator combines task-observability screening with task-specific quantitative physical measurements. Experiments on eight video generation models across 1,280 videos reveal persistent physical inconsistencies and substantial variation across tasks, with the best model achieving an overall score of 57.76 out of 100. Evaluation on synthetic videos with known physical relationships provides evidence for the validity of the measurement module under controlled conditions. The evaluator also achieves higher agreement with human judgments than a direct vision-language model baseline in both within-task rankings and pairwise comparisons. By combining coverage across physical domains with scores grounded in measurable evidence and explicit measurement limitations, the benchmark provides an interpretable basis for diagnosing physical inconsistencies and tracking progress toward physically consistent video world models.
embodiedworld modelbenchmarkevaluator - arxiv:2610.08789 · cs.ROQF3: Fast Flow RL with Filtered Q-GradientsChung Min Kim, Brent Yi, David McAllister, Hongsuk Choi +6
Flow policies have become a standard policy class for learning robot behaviors from demonstrations, but reinforcement learning is still critical for improving pre-trained flow policies or learning them from scratch through interaction. We introduce QF3 (Fast Flow RL with Filtered Q-Gradients), an online off-policy RL algorithm that trains a flow policy with flow matching plus the critic's action gradient, backpropagated through a one-step prediction of the flow's output. To keep updates where the critic and this prediction are reliable, QF3 applies the critic gradient only to action dimensions that stay near the replay action. To our knowledge, QF3 is the first off-policy flow RL method to train humanoid locomotion policies from scratch and transfer them zero-shot to hardware. Paired with a high-throughput off-policy training recipe, it trains humanoid locomotion and motion-tracking policies with a 10x wall-clock speedup over FPO++, a recent on-policy flow RL method. We further apply QF3 to fine-tune pretrained flow-based manipulation policies on both ABC-Sim and Robomimic tasks. These results suggest that QF3 can both learn robot policies from scratch and refine those acquired from demonstrations. Website: https://qf3-rl.github.io/
manipulationhumanoid - arxiv:2610.08786 · physics.opticsEnergy-constrained two-way capacity bounds for noisy Gaussian channelsStefano Pirandola
A gap between achievable rates and converse bounds persists for energy-constrained bosonic communication in the presence of excess noise. We derive a unified adaptive weak-converse bound for thermal attenuation, noisy amplification, and additive Gaussian noise under an unconditional mean transmitted-photon-number constraint. The bound applies to arbitrary adaptive protocols with quantum memories and constrains the two-way quantum, entanglement-distribution, private, and secret-key capacities. It vanishes throughout the entanglement-breaking region and approaches the corresponding PLOB bound at infinite energy. At finite energy, it improves the evaluated Gaussian squashed-entanglement and PLOB bounds in relevant parameter regimes, while comparison with hashing rates quantifies the remaining gap to achievability. The result provides a common energy-dependent benchmark for noisy bosonic Gaussian channels and extends finite-energy converse methods beyond the quantum-limited setting.
benchmark - arxiv:2610.08784 · cs.ROPEARS: Physical-Prior-Guided Efficient Adaptation via Failure Reasoning and Diffusion Steering for Tactile ManipulationKun Song, Yiming Wang, Yilin Chen, Tianyi Ding +4
Pretrained robotic policies can suffer substantial performance degradation under out-of-distribution (OOD) conditions encountered during deployment, motivating post-training through real-world interaction. However, reinforcement-learning (RL)-based post-training typically requires substantial environment interactions, a burden that is especially significant in manipulation, where each trial can be slow, costly, or destructive. Therefore, we present PEARS, a physics-prior-guided hybrid RL framework for sample-efficient online adaptation of pretrained policies with tactile feedback. After each episode, its physics-guided force reasoning (PFR) module uses physical priors encoded in a vision-language model (VLM) to diagnose failures from the visual outcome and tactile interaction history and update task-appropriate contact-force bounds. A high-frequency hybrid force-position controller then enforces these bounds during contact. Complementarily, tactile-conditioned diffusion steering reinforcement learning adjusts the latent noise of the frozen flow-matching policy to correct errors in free-space motion and contact timing without updating the base model. In simulation, PEARS improves success rates by 12.4-37.4 percentage points over the strongest per-task baselines. PEARS also reduces the number of interaction episodes required for a certain success threshold by up to 53.2% relative to the fastest baseline. In real-world experiments, PEARS achieves success rates of 95% on Whiteboard Erasing and 90% on Pipette Liquid Aspiration. These results show that combining the PFR module with policy steering can accelerate adaptation while reducing costly interactions. The project website is available at https://song-kun.github.io/pears.
manipulationtactilepost-training - arxiv:2610.08782 · cs.CV4D-HOF: Hand-Object Flow Matching for Feed-Forward 4D Interaction ReconstructionShiqi Li, Sean Cho, Yijie Li, Fengzhi Guo +2
Existing methods for 4D hand-object reconstruction often rely on costly per-sequence optimization, while generative approaches typically synthesize interactions from random noise, which can lead to unstable interaction prediction. We introduce 4D-HOF, a feed-forward framework that reconstructs 4D hand-object interactions from coarse but informative estimates produced by vision foundation models. Concretely, we learn a conditional flow matching model that transports foundation-model-derived hand-object states toward an interaction manifold, allowing the model to correct errors in translation, rotation, and alignment in a feed-forward manner. A key advantage of our generative formulation is that it naturally enables test-time guidance within the transport process. Rather than applying a separate post-hoc optimization after reconstruction, we directly steer the evolving generative states using physical interaction constraints and observed 2D evidence, allowing the reconstruction to be refined as part of the generative process itself. By training the generative model on diverse datasets, 4D-HOF generalizes robustly to challenging in-the-wild scenarios. Experiments on out-of-domain benchmarks show that 4D-HOF achieves state-of-the-art performance, producing more stable and accurate 4D hand-object reconstructions.
benchmark - arxiv:2610.08780 · cs.RODepthWorld: 3D World Model for Robot ManipulationJai Bardhan, Josef Sivic, Vladimir Petrik
World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning policy evaluation, improvement, and planning. All of these uses depend on faithful 3D geometry, yet current video-based world models are trained on RGB alone and produce rollouts that look correct frame-by-frame but do not compose into a consistent 3D world. Closing this gap requires progress on two fronts: large-scale 3D supervision for manipulation, and an architecture that can absorb it without disturbing strong pretrained video priors. We introduce a calibration pipeline that combines learned stereo depth with a joint factor graph, pooling all episodes collected from the same physical robot to recover its shared kinematic parameters alongside per-scene extrinsics. Applied to the DROID dataset, this yields DROID-3D, a calibrated 3D dataset providing dense metric depth and recalibrated multi-view extrinsics (achieving <0.7 px reprojection error on 90% of episodes for external cameras). We then train DepthWorld, a Stable Video Diffusion-based world model that jointly predicts multi-view RGB and depth via spatial latent tiling, leaving the pretrained Variational Autoencoder (VAE) unchanged. Depth supervision improves RGB prediction itself by +1.48 dB PSNR over an identical RGB-only baseline at equal training budget, while simultaneously yielding accurate metric depth for downstream geometric reasoning.
manipulationworld modelpolicy evaluation - arxiv:2610.08779 · cs.CVALIVE: Interaction-Aligned Object Insertion for First-Frame-Guided Video EditingZhenghong Zhou, Zhe Lin, Jiebo Luo, Yuqian Zhou
Current video editors can insert objects but often struggle to make them participate in interactions such as being picked up or manipulated. We introduce ALIVE, a framework that makes inserted objects "alive" through coherent interactions with the source video's contents, using an edited first frame and an instruction naming only the added object. We curate 35,800 editing pairs combining 3D-rendered, model-generated, and real-world videos with general editing pairs from ROSE. Each pair differs in the target object's presence while preserving the surrounding action, teaching editors coordinated object behavior and source preservation. We further train a vision-language model (VLM) to predict interaction guidance from the same inputs. We introduce the ALIVE-interaction benchmark to assess interaction fidelity, source preservation, and visual coherence using a unified VLM-based protocol, and evaluate on the general video object insertion benchmark. Without VLM guidance, ALIVE improves Overall over the strongest evaluated baseline by 43.9% and 4.4% on the two benchmarks, respectively. VLM-predicted guidance further improves the ALIVE-interaction score by 0.95 points without additional user inputs.
benchmark - arxiv:2610.08777 · cs.CVCtrlCache: Accelerating Interactive Video World Models with Control-Aware CachingShangye Song, Dong Gong, Hong Jia, Yun Sing Koh +1
Interactive video world models need to generate each video chunk efficiently while responding faithfully to user controls. Many systems use chunk-wise autoregressive generation with few-step denoising, but each chunk still requires several costly denoising iterations. Training-free caching can reduce this cost, yet existing policies make reuse decisions primarily from model-internal denoising dynamics and do not explicitly account for control transitions. Actually, interactive generation explicitly exposes a signal they do not use: the controls for a chunk arrive before it is denoised, so a schedule derived from them costs no forward pass. To this end, we analyze adjacent chunks under different control regimes and find that structural similarity drops around action changes, while low-frequency structure remains more persistent than high-frequency detail. Motivated by these observations, we propose CtrlCache, a training-free control-aware caching framework that adapts computation to the current control sequence. Specifically, the action-aware scheduling and refresh policy detects action changes across and within chunks, and labels each chunk as initial, transition, turning, or steady state. At one selected interior denoising step, initial and transition chunks retain full computation, while turning and steady chunks reuse the transformer residual from the most recent fully computed step in the same chunk. To exploit the persistence of low-frequency structure during steady interaction, we further introduce a frequency-mixed history prior guidance that incorporates complementary information from the preceding clean latent without an additional DiT forward pass. Evaluated on Matrix-Game 2.0 and LingBot-World v1/v2, CtrlCache achieves 1.21x to 1.41x DiT-backbone speedups without model retraining while improving WBench Overall scores over original inference across all three models.
world model - arxiv:2610.08775 · cs.AIAgent in a Bottle: Can LLM Agents Turn Their Capabilities Into Cheap, Scalable Artifacts?Ankit Sonthalia, Haritz Puerto, Alexander Rubinstein, Martin Gubri +1
Large language models (LLMs) can solve many narrow tasks, but querying them separately for millions of related instances can be prohibitively expensive. Can LLM agents autonomously create cheaper solutions for such workloads? We call this ability "bottling": the ability to turn general capabilities into task-specific solutions that balance answer quality and amortised cost. We introduce BOTTLED, a benchmark in which agents receive an entire unlabelled workload and must complete it under fixed time, compute and LLM API budgets. Agents choose their own approach, such as training a small model or writing a reusable program. Across ten models and three tasks, we find that strong zero-shot task performance does not reliably translate into strong bottling capabilities. Models with similar zero-shot scores can differ substantially after bottling, and 48 of 60 bottling runs score below the lower bound of the 95% confidence interval of their model's zero-shot performance. Moreover, 31 of 60 runs underperform the stronger of two small-model distillation baselines with the same token budget. Nevertheless, bottling can yield substantial savings: on query-product relevance classification, Opus 5 retains about 82% of its zero-shot macro-F1 at roughly 657 times lower reported cost. Bottling is also competitive with Jev, a "system one" model built especially for cheap, repetitive inference: Opus 5 on the same task recovers about 94% of Jev's macro-F1 at a quarter of Jev's projected full-workload cost. BOTTLED provides a basis for evaluating and improving agents' ability to invest limited resources in reusable solutions for large, repetitive workloads.
llm agentbenchmark - arxiv:2610.08773 · cs.LGAdvSim2Real : Training Web Agents Against Adaptive Prompt Injection in a Web World ModelSarim Hashmi, Mukul Ranjan, Kshitij Mishra, Mikhail Kuznetsov +2
Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's goal. The agent cannot simply ignore the page, because the page also holds the values and controls the task requires. Current defenses fine-tune the agent on injections fixed before training, and attackers that adapt to the trained model bypass them. Adversarial training lets the attacker adapt but keeps the tasks fixed, so a task stops teaching once the agent solves it. We introduce AdvSim2Real, which co-evolves a task curriculum, an injection adversary, and the agent inside a frozen web world model. The curriculum is rewarded for tasks the agent solves about half of the time, and the adversary only for a success flip, an injection that turns a judged success into a failure. Training in the simulator makes a 4B agent both more capable and more robust: its completion rises with and without attacks, holds against a frontier-model adversary it never trained against, and its capability gain carries over to a real browser. On 150 web tasks, AdvSim2Real raises completion under this unseen adversary by 33.6\% relative to the base agent.
sim2realworld modelagent - arxiv:2610.08761 · cs.ROVeriFine: Scaling Verification for Self-Improvement in Embodied ReasoningZewei Zhou, Rachel Luo, Yulong Cao, Chaowei Xiao +9
Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. However, current fixed judges constrain both optimization feedback and the discovery of useful training examples, limiting further self-improvement. This challenge is even more acute in embodied reasoning, where reliable evaluation must account for spatial grounding, causal reasoning, and safety-aware decision-making. We introduce VeriFine, an agent harness framework that scales verification through the co-evolution of the policy, training curriculum, and judge. The Policy Improvement Loop uses a rubric judge to diagnose recurring failures, construct an adaptive curriculum, and optimize the policy. When progress plateaus and verification becomes a bottleneck, the Judge Improvement Loop selectively queries human guidance on informative failure cases and refines the judge through coactive calibration, in which humans and agents resolve disagreements and converge toward the objective rubric of physical reasoning. The revised judge then guides the next stage of data selection and policy optimization. Experiments on driving and robot navigation tasks demonstrate continuous self-improvement in both policy and judge capability across reinforcement and supervised fine-tuning. These results show how scaling verification supports continuous self-improvement as policy failure patterns evolve.
embodiedagentself-improvingself-improvement - arxiv:2610.08760 · cs.CVWorldSonus: Bringing Sound to WorldsPengjun Fang, Jingyi Fa, Kam Man Wu, Jiaming Wang +8
Recent advances in world models have enabled increasingly realistic visual synthesis. However, these generated environments remain largely silent. Bringing sound to world models poses three core challenges: real-time generation to keep pace with interactive video streams, interactive control to respond to mid-stream sound instructions, and spatially aligned stereo to reflect scene geometry and camera motion. To address these demands, we introduce WorldSonus, an interactive video-to-audio framework designed for real-time spatial sound synthesis in world models. For real-time generation, WorldSonus employs a streaming causal autoregressive diffusion architecture that synthesizes audio chunks at a low real-time factor (RTF) of 0.41. For interactive control, we incorporate an audio-centric captioning pipeline with chunk-indexed prompt scheduling, enabling dynamic manipulation of sound events during generation. For spatial alignment, we leverage high-quality stereo supervision curated from diverse stereo and ambisonic data. Extensive experiments demonstrate that while tailored for world models, WorldSonus generalizes effectively to open-domain video-to-audio benchmarks, matching or outperforming state-of-the-art bidirectional models in both acoustic quality and spatial alignment. Project page: https://noizai.github.io/WorldSonus/
manipulationworld modelbenchmark - arxiv:2610.08756 · cs.CVPost-Training Semantic Lifting for 3D Gaussian Splatting: Separating Detector, Lifting and Representation ErrorIván Verdugo Guerra, Ezequiel López Rubio, Jorge García González
The same Gaussian of a 3D Gaussian Splatting model is seen from many views, and these views do not always agree on the class it belongs to. The Gaussian may be occluded in some of them, and the confidence of the detector is not the same from one view to another. The ground truth, on the other hand, is given as an annotated mesh, because two training runs do not produce the same Gaussians. In this work, we propose a post-training lifting method that works with one target class at a time and combines the information coming from all the views. Target and non-target evidence are accumulated simultaneously, weighted by the visibility of each Gaussian in each view. After that, the Gaussians are filtered with two thresholds: a main threshold $β$ selects the high-confidence seeds, and a lower one $γβ$ adds the connected components around them. For the evaluation, the labels are transferred from the Gaussians to the mesh vertices that are both visible and annotated. With this design, we can separate three sources of error: the 2D detector, the lifting and the transfer between representations. The thresholds and the transfer operator are chosen on seven Replica validation scenes, and the method is evaluated on ten held-out ScanNet++ scenes with the same values for every scene and class. The mean mIoU on the validation scenes was 0.93 with masks from the dataset annotations and 0.65 with YOLO masks, and on the ScanNet++ test scenes it was 0.80 and 0.54. Compared with thresholding the evidence per view, as a previous version of the method did, the fraction improves the test mIoU by 0.24 and makes it possible to use a single threshold for all the classes and scenes of both datasets. Finally, the error analysis shows that most of the remaining error comes from the detector.
post-training - arxiv:2610.08745 · cs.LGLinear Bandits under Exact Sliding-Window ConstraintsSeyed Mohammad Hadi Hosseini, Yasin Abbasi-Yadkori, Sattar Vakili
We study linear bandits under exact sliding-window constraints, where every consecutive block of actions must belong to a prescribed feasible set. In the offline setting, where the reward function is known, we show that convexity and cyclic-shift invariance make a stationary solution optimal when $w\mid T$ and within an additive $O(w)$ gap otherwise. In the online setting, we show that geometric structure alone is insufficient for learning, and sublinear regret can be impossible. We introduce a transition diameter $τ$ that quantifies feasible reachability and develop a rare-switching OFUL algorithm with regret $\widetilde{O}(d\sqrt{T}+τd+w)$ against the offline-optimal feasible trajectory. Finally, we remove cyclic invariance and consider general sliding-window constraints, where optimal behavior may be non-stationary. We represent recent action history as the state of a finite-memory control problem and introduce a history-state diameter $D$ that measures feasible communication between viable histories. Combining optimistic remaining-horizon planning with rare policy updates, we obtain a regret bound of $\widetilde{O}(d\sqrt{T}+dD+w)$. We evaluate our approach on real-world and synthetic benchmarks, showing that it maintains exact feasibility while achieving reward and regret comparable to baselines with substantially fewer policy updates.
benchmark - arxiv:2610.08737 · cs.ROPhoneBot: A Low-Cost Open Humanoid Robot Platform Reusing SmartphonesRuochen Hou, Quanyou Wang, Daniel Koh, Dennis W. Hong
The adoption of humanoid robots in education and research remains limited by high hardware costs, complex sensing systems, and substantial computational requirements. This paper presents PhoneBot, a low-cost, open-source humanoid robot platform that repurposes commodity smartphones as its primary sensing and computing unit. By using a smartphone's integrated inertial measurement unit (IMU), camera, wireless connectivity, and onboard processing capabilities, PhoneBot reduces hardware costs and simplifies the system architecture. The robot combines a modular lower-body structure driven by 13 low-cost actuators with a torso-mounted smartphone that supports perception, control computation, and user interaction. We describe the mechanical design, software architecture, and real-time communication framework that support stable locomotion and capabilities including vision-based human following, conversational interaction, filming, and mobile telepresence. Experimental evaluations demonstrate reliable walking, perception-driven interaction, and straightforward deployment using off-the-shelf consumer smartphones. With fully open-source hardware and software designs, PhoneBot provides an affordable, reproducible platform for education, research, and rapid prototyping. More details are available at https://phonebot.dev.
humanoid - arxiv:2610.08738 · cs.LGDenoising Hierarchical Representations: Joint Continuous Diffusion for Language ModelingMathias Ollu, Nikos Komodakis
Diffusion Language Models (DLMs) hold the promise of order-agnostic, parallel text generation. Recently, continuous diffusion and flow matching models have seen substantial gains, driven by carefully crafted token representations and diffusion/flow spaces. In this work, we introduce Hierarchical Continuous Diffusion Language Models (H-CDLMs), a simple framework that further improves continuous DLMs with minimal compute and parameter overhead. Drawing on the discrete DLM and continuous image diffusion literature on joint diffusion, we diffuse multiple modalities in parallel. These modalities represent tokens at different semantic granularities: in our instantiation, the tokens themselves and coarser clusters obtained by clustering pretrained token embeddings. We propose a general setup that allows per-modality samplers and schedules to enhance the interplay between modalities. Applied to CoBit, this yields H-CoBit, which delivers large empirical gains across benchmarks. At dataset entropy, H-CoBit improves MAUVE and reaches a generative perplexity (GenPPL) of 49.4 on LM1B and 50.4 on OWT, improving on the baseline by 24.2 and 20.7 points and surpassing even discrete DLMs of comparable size. On GSM8K, it reaches 27.4% accuracy, outperforming prior continuous diffusion and flow-based models. We further apply H-CDLM to the flow matching model FLM, obtaining consistent gains with H-FLM and demonstrating that the framework generalizes across continuous generative paradigms. Our code will be made publicly available at https://github.com/matol-16/HCDLM.git .
benchmark - arxiv:2610.08733 · cs.ROTowards an Extensible Benchmark for Spoken Dialogue with Social RobotsCasey Kennington, Ross Mead, Saad Elbeleidy, Jesse Thomason
Language models provide a plug-and-play interface between humans and robots, but important challenges remain when speech, dialogue, fast interaction, and collaboration are required. We propose a benchmark for the community to use as a way to explore common spoken dialogue artifacts between robots and humans, including requests for clarification, interruptions, embodied signals (e.g., head nods or facial cues), and time constraints. We also explain our vision to extend the benchmark for other aspects of human-robot interaction that are important to the larger research community. To facilitate the benchmark, we further propose using \textit{Retico}, a real-time communication framework that fulfills important technical requirements to enable robots to have spoken dialogue capabilities.
embodiedbenchmark - arxiv:2610.08726 · cs.ROEgoLAP: Learning from Egocentric Human Data through Language-Action ReasoningLihan Zha, Shresth Grover, Tenny Yin, Samuel M. Bateman +6
Egocentric human data offer a path to scaling robot learning beyond costly robot demonstrations, yet the embodiment gap makes raw human trajectories a poor supervisory target for control. Our key insight is that, although low-level actions are embodiment-specific, their underlying motion intent can capture task-relevant structure that transfers across humans and robots. We introduce EgoLAP, a VLA pre-training framework that jointly learns from human and robot trajectories through a shared language-based action chain-of-thought. EgoLAP expresses motion intent as structured, temporally abstracted language actions and pairs them with motion-level reasoning grounded in scene geometry, physics, and object affordances. Across extensive real-world and simulated experiments, EgoLAP transfers human experience to robot control more effectively than alternative action representations and reaches 80.1% mean real-world task progress, a 2.3x performance gain over alternative action representations. Motion-level reasoning also outperforms a composite reasoning format that combines subtask, object-box, and visual-trace reasoning.
vla - arxiv:2610.08722 · cs.LGDoes an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay CorpusEgor Pakhomov, Erik Nijkamp
Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was doing. We ask whether the agent's recent behaviour predicts when a compaction will hurt. TRACE's public corpus of 590 harness-triggered AppWorld compaction boundaries replays each boundary from a re-executed prefix state under the pre-compaction context and under the summary, and records the burden of the next actions: calls that error or repeat a call already made. We find that pre-boundary history predicts post-compaction harm only weakly. An internally prespecified contrast by prefix placement is a wide null, and the naive "has-written" label behind it turns out to measure trajectory phase. The best extension-protocol trigger reaches held-out AUROC 0.66 (0.64 on the replicate's own label) against a same-boundary replicate of 0.72; the best frozen, interpretable trigger avoids 21% of harmful (positive-burden) boundaries while keeping 84% of compaction opportunities, and exceeds the random-rule expectation on count but not on burden mass (a post hoc comparison). Whether the best trigger beats a token-budget rule at matched retention cannot be evaluated on the release. We state what corpora should ship to answer it.
agent - arxiv:2610.08720 · cs.AIWorldSolver: Can LLM Agents Simulate the Physical Dynamics via Solver Generation?Siru Jiang, Yongzhe Lyu, Shuo Lu, Yubin Wang +5
LLM-based agents are increasingly advancing scientific and engineering problem solving, with physics simulation emerging as a challenging yet practical testbed for reproducing complex physical phenomena with application in embodied AI, games and films. As the workhorse of such simulation, a solver computes how the state of a dynamic system evolves over time. Building such solvers requires physical understanding to identify appropriate models, mathematical reasoning to formulate the underlying dynamics, and software engineering to implement them as executable code, yet this capability of LLM agents remains underexplored. To this end, we introduce WorldSolver, a benchmark of 168 simulation tasks derived from physical phenomena in 61 classic computer graphics papers, spanning 7 physical domains. Each task contains a code scaffold that provides a fixed simulation environment for the scene, with the solver implementation left for the agent to complete. Specifically, we evaluate them along three dimensions: Execution Checks for successful execution, Visual Fidelity for reproducing the intended dynamic behavior in the rendered simulation, and Physical Plausibility for physics-grounded verification of the generated dynamics. Experiments on frontier agents reveal that producing executable solvers is difficult itself, and satisfying visual and physical correctness is even harder. GPT-5.6-Sol and Claude-Opus-5 perform comparatively better than the other evaluated agents, yet achieve overall scores of only 48.7% and 46.7%, respectively. WorldSolver is an early step toward agentic solver generation, and we hope it helps drive progress toward agents that can faithfully simulate the dynamic physical world. Code is available at https://github.com/sirujiang/WorldSolver.
embodiedagentllm agentagenticbenchmark - arxiv:2610.08718 · cs.LGWhen Forgetting is not Catastrophic: On the Mechanics of Spurious ForgettingVedant Palit, Florent Draye, Nicolas Zucchet, Zhijing Jin +1
Knowledge that a language model appears to forget during finetuning often remains stored and can be recovered, a phenomenon called spurious forgetting. Finetuning on new facts can even produce forgetting that undoes itself: recall of the old facts collapses, recovers as training continues on new facts alone, and only then erodes for good. We seek to understand when such forgetting is not catastrophic. A minimal associative memory reproduces these dynamics with three ingredients: keys with shared structure, concentrated new values, and normalization in the network. Finetuning moves all old representations along a common direction, hiding the old facts while preserving their relative geometry; normalization withdraws this shift once the new facts are learned, whereas fact-specific changes accumulate and cause the erosion. Moreover, subtracting the common shift eliminates the collapse in a Transformer trained on synthetic data, and removing a single direction from each weight update restores old facts in a pretrained language model. Forgetting thus combines a shared, reversible loss of access with a slow erosion of individual facts, and only the second is catastrophic. Which one dominates depends on whether the new data move old memories together or apart.
memory - arxiv:2610.08713 · cs.CVSpaTime: Streaming Vision-Language Models for Spatio-temporal ReasoningHairong Yin, Huangying Zhan, Shin-Fang Chng, Yi Xu +1
Embodied agents must reason about 3D space while the video is still arriving, answering questions as soon as they have observed enough of the scene. VLMs that incorporate 3D geometric priors achieve strong spatial reasoning, but they operate offline, i.e., the full video must be available before they produce an answer. Streaming VLMs process frames causally and decide for themselves when to respond, yet they lack explicit 3D representations. We present SpaTime, a streaming VLM that fuses causal geometry tokens into the language model at every frame, using only the frames observed so far. To supervise when the model answers, we propose a response-time loss that maps per-frame response probabilities to a differentiable expected response time and penalizes the distance from the ground-truth frame. For evaluation, we construct StreamVSTI-Bench and StreamVSI-Bench, streaming adaptations of VSTI-Bench and VSI-Bench. On StreamVSTI-Bench, SpaTime reaches 49.2% overall accuracy and reduces the mean response-time error by 66% relative to the strongest streaming baseline.
embodiedembodied agent - arxiv:2610.08699 · cs.AInanoMuse: An Open-Source Personal Agent for Every Device You OwnGuangyi Liu, Yong Liu, Jiangning Zhang
Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped. In September 2026 Meta's Muse showed an agent for one person, with accounts, devices, memory and a conversation that lasts, closed, in a vendor's cloud, in one country. Such an agent is expected to act on a person's accounts and devices, remember them across weeks, speak first when it is worth it, and answer for what it did. It is a kind of software, not a model, and until now had no open counterpart. This report defines the personal agent in five questions and three horizons. It reads how Muse is built from Meta's public record and a copy of its production prompt, each statement marked by its source. It then presents nanoMuse, the open-source counterpart under the GPL-3.0, one agent on every device a person owns, with hands on the phone's screen and the computer's. They share one conversation over a relay anyone can run; every action goes through a Sentinel, memory is files the person can read, and the model is their choice. Its size and cost are given as estimates. What is open, memory with provenance, an evaluation suite for the hands and an open model for them, is set out as a roadmap.
memoryagent - arxiv:2610.08691 · cs.AIScienceClaw: Benchmarking Continual Self-Evolution of AI-for-Science Agents Across the Natural and Social SciencesMingda Zhang, Wenjin Liu, Tiesunlong Shen, Zikai Xiao +5
Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent program-level improvements, and existing evaluations do not examine this process across sequential tasks in both the natural and social sciences. We formalize ScienceClaw as fixed-parameter program self-evolution that unifies task solving, scientific verification, and program updates. ScienceClaw-Eval spans 23 disciplines and measures scientific correctness, evolutionary gain, retention, cross-dataset transfer, and evolution cost through sequential streams and independent reset evaluation. Our framework repairs executable workflows through multi-turn interaction, converts re-execution-verified failure--success trajectories into linked Skill and Operator candidates, and retains an update only when source-task replay reproduces the repair and independent scientific tasks improve. Code is available at https://github.com/beita6969/ScienceClaw.
benchmark - arxiv:2610.08684 · cs.CVRenderBench: Benchmarking Render-to-Real Video Transfer with Reconstructed Digital TwinsDicong Qiu, Zhiyuan Xu, Yaosheng Liu, Feng Han +1
Modern video models can generate realistic videos from real appearance references and proxy renders that specify scene structure, viewpoint changes, and motion. Evaluating this render-to-real capability requires a real target video depicting the same scene evolution, paired with an editable, geometrically registered 3D replica. Such data has traditionally required substantial manual modeling, calibration, and animation effort. We introduce RenderBench, a benchmark of 12 reconstructed real-world scenes spanning large-scale indoor environments and egocentric viewpoints, with both static and dynamic settings. Our construction pipeline combines visual geometry, neural reconstruction, and assisted 3D authoring. Each scene is decomposed into static objects and dynamic actors, registered to the capture cameras, and accepted only after multi-view geometric and temporal validation. Each evaluation unit contains appearance reference images, a held-out real target video, an editable digital twin, a matched proxy render, and renderer-native scene annotations. We evaluate transfer models against paired real target videos, retain PAI-Bench-C-compatible structural projections, and use scene annotations to localize failures by object, visibility, articulation, and motion. The first release retains 12 of 14 registered samples (85.7%), comprising 1,496 paired real-proxy frames. All released scenes pass file-integrity and environment-edit audits, while proxy diagnostics yield a depth si-RMSE of 0.2170 and instance mIoU of 0.3673. RenderBench provides paired real observations and editable scene state for assessing both appearance fidelity and preservation of geometry and dynamics.
benchmark - arxiv:2610.08683 · cs.AICoupled but Late: Turn-Taking Between Full-Duplex Speech Models in Unscripted DialogueLichen Zhu, Yueqian Lin, Yiheng Wang, Hai "Helen" Li +1
Full-duplex speech models are trained to converse with a person, but they are increasingly made to converse with each other, in self-play data generation, agent societies, and model-based evaluation. In that loop no human absorbs a timing error: each model's turn-taking is the other's input. We ask what timing the loop settles into. Two PersonaPlex-7B instances exchange audio tokens on a shared clock in unscripted conversation, and one floor-transfer rule is applied to them and to Switchboard. Their timing is coupled: re-pairing speakers across conversations destroys it. But the floor changes hands late, at a median of 400-560 ms against 137 ms for humans, and the last 120 ms of the partner's turn, where human projection places a tenth of its transfers, holds 1% of theirs. Delaying one direction of the channel shifts the response one-for-one and leaves the run-up to it empty, consistent with a reactive wait after the perceived end rather than the turn-end projection human timing requires.
agentself-play - arxiv:2610.08680 · cs.LGA Systematic Study of Small Language Models on Abstract Reasoning TasksNur A Zarin Nishat, Jens Lehmann, Andrei Aioanei, Sahar Vahdati
Endpoint accuracy on abstract-reasoning benchmarks does not reveal whether a language model has acquired a transferable rule or fit distribution-specific regularities. We study this distinction in small language models on the ARC-TGI benchmark, which organizes abstract grid transformations into controllable task families and supports resampling, spatial shifts, and cross-benchmark transfer. Across more than 1,000 runs, we profile decoder-only, encoder--decoder, and mixture-of-experts model families under supervised fine-tuning. We examine the efficiency and stability of skill acquisition, robustness beyond the training distribution, interactions with model family and task formulation, and layer-wise attention signatures that accompany behavioral differences. Substantial in-distribution accuracy is attainable, but acquisition is sensitive to optimization and unevenly distributed across task families. Performance deteriorates sharply outside the training distribution, including when the rule is retained but grid scale changes. Greater training-set depth and breadth yield uneven gains, while the effect of additional in-context examples depends on model family. Executable-rule induction also yields correct solutions not observed under direct grid generation. On selected tasks, attention diagnostics show distinct concentration and context-dependence profiles, but do not establish general causal mechanisms. Overall, abstract-reasoning scores are conditional on the model, adaptation regime, evaluation distribution, and response format.
benchmark - arxiv:2610.08678 · cs.LGSecure Speculative Decoding for Large Language ModelsYichi Zhang, Zhiqi Wang, Neil Gong, Yuchen Yang
Speculative decoding accelerates inference for a large language model (LLM), referred to as the \emph{target model}, by first using a smaller model, referred to as the \emph{draft model}, to generate candidate tokens and then verifying them with the target model for acceptance or rejection. Prior studies primarily focused on the efficiency-utility trade-off of speculative decoding, e.g., lossy speculative decoding, leaving its security implications largely unexplored. In this work, we bridge this gap by providing the \emph{first} systematic study of the security implications of speculative decoding. Through a large-scale measurement study, we reveal a pronounced security-utility asymmetry: across a wide range of lossy speculative decoding methods, improvements in inference efficiency come at a disproportionately high cost to security, with attack success rates for jailbreak and prompt injection attacks increasing much faster than utility degrades. We then propose SecureSD, a new theory-guided speculative decoding method that enhances security while maintaining efficiency and utility. Specifically, our theoretical analysis reveals that security degradation primarily originates from the early tokens generated by the draft model. Motivated by this insight, SecureSD applies a stricter verification criterion to draft-model tokens at early decoding positions. Extensive experiments on both security and utility benchmarks demonstrate that SecureSD significantly improves security while preserving efficiency and utility compared to existing speculative decoding methods.
benchmark - arxiv:2610.08677 · cs.LGVariance-Optimal Off-Policy Evaluation with Conjunct Effect ModelingNicolò Felicioni, Michael Benigni, Maurizio Ferrari Dacrema, Paolo Cremonesi
Off-policy evaluation (OPE) for contextual bandit policies becomes challenging when action-level importance weighting incurs excessive variance. Doubly robust (DR) estimation remains unbiased under common support but retains these high-variance action-level weights. A prior estimator, Off-policy evaluation with Conjunct Effect Model (OffCEM), replaces them with more stable cluster-level weights, at the cost of relying on local correctness of the reward model. In this paper, we show that, under the assumptions required by DR and OffCEM, there exists an unbiased family of estimators that interpolates between OffCEM and DR. Building on this result, we propose the Variance Optimal-CEM (VOCEM) estimator, which selects the interpolation coefficient to minimize variance. We derive the population-optimal coefficient in closed form and show that the resulting estimator has variance no larger than either endpoint, OffCEM or DR. Experiments in controlled synthetic settings and on two large-action benchmarks show that VOCEM improves upon both endpoints in all 23 evaluated conditions, exhibiting greater stability and empirical robustness.
benchmarkpolicy evaluation - arxiv:2610.08674 · cs.CVEC-RAG: Event Chain Retrieval-Augmented Generation for Long Video UnderstandingYuhao Qin, Junbo Wang, Yuke Li, Yining Zhu
Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independently, making it difficult to capture temporal dependencies across events. Although retrieval-augmented approaches have been introduced to provide additional context, most of them operate at the frame or snippet level, which limits their ability to model how events evolve over time and relate to each other. In this paper, we propose Event Chain Retrieval-Augmented Generation (EC-RAG), a training-free framework that organizes video content into an explicit event chain before question answering. Instead of retrieving isolated frames or text segments, EC-RAG first partitions the video into semantically coherent segments, represents each segment using multi-modal signals, and then links them into a structured chain that preserves temporal order and captures inter-event relationships. Given a query, the system identifies relevant events within this chain and gathers supporting evidence from the associated modalities. Our approach offers several practical advantages: (i) event-level abstraction that better reflects how video content is naturally structured, enabling more reliable localization compared to frame-level retrieval; (ii) structured multi-modal fusion that aggregates speech, text, and visual cues at the event level, allowing complementary information to be more effectively utilized during reasoning; and (iii) plug-and-play compatibility with existing LVLM backbones, requiring no additional training or reliance on proprietary models. Experiments on Video-MME, MLVU, and LongVideoBench show that this event-centric design consistently outperforms frame-level retrieval baselines, highlighting the importance of modeling temporal structure for long-video understanding.
retrieval-augmented - arxiv:2610.08670 · cs.LGPrincipled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral JudgmentOrion Reblitz-Richardson
Language models increasingly act as agents. An agent that says an action is wrong and then takes it anyway is a different failure from one that does not know better, and evaluations of stated values cannot see it. We build a pre-registered panel of 248 scenarios across five kinds of pressure. Each scenario is posed twice to the same model, once as the agent choosing what to do and once in the third person asking which option is right, so the model's own judgment is the reference. Every scenario has a twin with the pressure removed, and every model gets a positive control in which its operator orders the violating action, so that a missing gap can be told apart from a blind instrument. On OLMo-3-7B-Instruct, the model takes the action it judged wrong on about one in five pressuring scenarios, more often than on the same scenarios with the pressure removed. Across four instruct models the gap depends on the post-training recipe: OLMo-3 and Meta's Llama-3.1-8B-Instruct carry it; Tulu 3 shows none on the whole panel (above about 0.01 in probability) or on its own most-pressuring scenarios; Qwen2.5-7B-Instruct shows none on the whole panel (above about 0.02) and is unresolved on its own (0.083, -0.028 to 0.195). Meta's recipe and Ai2's Tulu 3 start from the same Llama-3.1 weights, and only Meta's carries the gap. Reading a chat model outside its chat template reverses the sign of its gap with nothing at stake (-0.038 against +0.055 under the template on OLMo-3), a distortion present on two of three recipes. On both models that carry it, reasoning about the stakes before acting moves the choice back toward the model's own judgment, against a same-length non-moral task, with or without the pressure; on OLMo-3, naming the norm at stake does about a third of that. The gap is a measurable target for post-training recipes, not a fixed property of pretrained weights.
agentpost-training - arxiv:2610.08669 · cs.LGMemFLoRA: Memory-Floor LoRA for CNN Adaptation at the EdgeMehmet Emre Akbulut, Johannes Geier, Ulf Schlichtmann
On-device learning is necessary when the model encounters user-,sensor-, or environment-specific shifts after deployment. Although parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA) variants, enable efficient adaptation at the edge, the limiting resource for Convolutional Neural Network (CNN) adaptation is often not the number of trainable parameters but the activation state that must be retained until the backward pass. This paper introduces Memory-Floor LoRA (MemFLoRA), a low-rank CNN adapter built around a memory-first design principle rather than a direct application of transformer-oriented LoRA. Instead of merely reducing trainable weights, we define an activation-memory-floor criterion: trainable backward computations must not depend on full-width layer inputs. The resulting adapter freezes the down-projection, trains a scale-matched up-projection, and combines eval-mode backbone normalization with activation-minimal backward rules, reducing saved state to the low-rank branch. Evaluated on three Human Activity Recognition (HAR) datasets and two CNN backbones under subject, body-location, and sensor-placement shifts, MemFLoRA reduces saved-activation memory by 98.5-98.7% and peak training-state memory by 94.9-97.3% relative to full fine-tuning, while matching or exceeding CNN PEFT baselines.
memory - arxiv:2610.08668 · cs.AISemantic Behavioral Watermarking: Paraphrase-Robust and Forgery-Resistant Provenance for LLM AgentsSuxin Ji, Hungtao Wan, Shaoxuan Chen, An Zhang
Behavioral watermarking embeds an owner identifier in an LLM agent's high-level action choices, giving provenance without touching output tokens. Prior agent watermarks break in two ways. First, all three prior schemes bind the watermark to the exact action symbol, so renaming a tool desynchronizes decoding even when the observation is untouched; in AgentMark's own robustness test, paraphrasing the observation alone drops bit-recovery to 16.8%. Second, every prior agent watermark studies only removal: none asks whether an adversary can forge a trajectory that verifies as someone else's, a question answered affirmatively for text watermarks (Jovanović et al., 2024). We present Semantic Behavioral Watermarking (SBW): watermarking over semantic action clusters under history conditioning, with the public-cluster bin replaced by keyed collision-resistant binning whose fresh-bucket assignment is provably unpredictable in the random-oracle model. Across five agent models (3B-14B, four vendors) and three encoders the ordering holds on both benchmarks: on ToolBench (600 trajectories per model) detection under rewriting is 0.49-0.66 for cluster-level versus 0.05-0.17 for exact-symbol at a permutation-calibrated 1% FPR, at 72-83% choice agreement against 22-27% for logit biasing; on ALFWorld (100 episodes per model) it is 0.92-0.97 versus 0.00-0.01. Keyed binning takes adaptive forgery from 100% to the false-positive floor at the primary operating point (bge, r=64). We also mark the boundary that guarantee does not cover: when the adversary copies the victim's own steps, shuffled splicing is neutralized (0.000 on Qwen2.5-3B) but chained replay remains at 0.76-0.98 across the five models, reported as open. Paraphrase robustness costs about half of the per-step watermark capacity. Code is available at https://anonymous.4open.science/r/SBW-Agent-Watermark.
agentllm agentbenchmark - arxiv:2610.08662 · cs.AIParanoiaEval: Benchmarking Unnecessary Defensive Work in Agentic CodingHanjun Luo, Xiucheng Zhang, Zhuoning Xu, Zhimu Huang +3
As coding agents increasingly undertake real-world work autonomously, judging whether their risk treatments are warranted has become important. Existing work evaluates related agent behaviors from separate perspectives, but lacks a systematic framework for unifying these behaviors. To bridge this gap, we introduce ParanoiaEval, the first benchmark for unified evaluation of risk-treatment capabilities in coding agents. Grounded in the well-established Avoidance-Transfer-Mitigation-Acceptance framework in software engineering risk management, ParanoiaEval operationalizes its 4 fundamental treatments for coding-agent settings and contains 200 evidence-controlled repository-level task pairs, each differing only in treatment-defining evidence. We further introduce dedicated metrics for risk-treatment violations and evidence responsiveness, using a human-calibrated agentic judge for reliable evaluation. Large-scale experiments on 8 representative models and a post-hoc human study reveal that (I) unnecessary risk treatment occurs in 11.2%-58.7% of runs despite explicit evidence, with substantial variation across agent configurations; (II) stronger task capability does not ensure more appropriate risk treatment, while treatment violations substantially harm developers' experience, establishing risk treatment as an independent capability dimension; and (III) agents exhibit systematic patterns consistent with established risk-management findings, suggesting that knowledge from human practice can guide the diagnosis and improvement of this capability.
agentagenticbenchmark - arxiv:2610.08660 · cs.CLEvidence-Bound Reasoning: Neuro-Semantic Verification of Biomedical AI in Glioblastoma RadiogenomicsMariya Miteva, Maria Nisheva-Pavlova
Background: Biomedical AI can generate plausible explanations without reliably verifying whether each statement is supported by patient-specific evidence. We developed a neuro-semantic verification framework that converts radiomic measurements into addressable evidence records and machine-checkable claims. Methods: UPenn-GBM radiomics were aligned with de novo CaPTk extraction from standardized MRI and expert-validated segmentations in an independent multicenter cohort. The shared space comprised 1,728 features from T1, T1GD, T2, and FLAIR MRI across three tumor regions. Reference-defined semantic states were derived from 611 UPenn cases. We evaluated cross-cohort transportability, model-linked provenance, deterministic verification, controlled predictive degradation, and an LLM claim-extraction pilot; MGMT prediction served only as a transport stress test. Results: Median semantic-state agreement was 0.786 (weighted kappa 0.709), ranging from 0.918 for morphologic to 0.252 for intensity features. The external evidence ledger contained 1,655 model-linked records for 331 patients. The verifier achieved 100% exact-set accuracy in a 6,620-claim corruption benchmark. In a 24-case pilot, GPT-5.6 Sol reproduced 72/72 prespecified atomic claims, and the frozen verifier recovered 24/24 expected conditions. During controlled degradation, ROC AUC declined from 0.899 to 0.500 while verification accuracy remained 1.000. External MGMT discrimination was weak (ROC AUC 0.543). Conclusions: Verifiability can be engineered and evaluated independently of predictive performance. LLMs may structure explanations, while final evidence-consistency checking remains deterministic.
benchmark - arxiv:2610.08659 · cs.CVSelective Transfer of RL Updates for Visual ReasoningSuxin Ji, Hungtao Wan, Mingjun Liu, An Zhang
Model merging provides a training-free way to transfer reasoning capabilities from language models to vision-language models (VLMs), but endpoint-based transfer can conflate pre-existing model differences with changes acquired during reasoning post-training. We instead formulate capability transfer around the training-stage update, isolating the parameter changes induced by reinforcement learning (RL). Yet transferring this update in full remains suboptimal: we find that its components differ substantially in cross-model transferability, with dominant directions transferring more effectively than the complete update. Based on this finding, we introduce Selective-RL, which isolates the RL-stage update, retains its dominant matrix-wise directions with magnitude preservation, and transfers them to the language modules of a VLM. Across three model families and five visual-reasoning benchmarks, Selective-RL improves full-update interpolation in 12 of 15 comparisons, including an 8.55 percentage-point MathVision gain on the Qwen recipient. Matched controls show that update magnitude or arbitrary low rank alone does not reproduce these gains. These results highlight a distinction between what is acquired during post-training and what remains transferable across models, providing a training-stage perspective on cross-model capability transfer. Code is available at https://anonymous.4open.science/r/selective-rl.
post-trainingbenchmark - arxiv:2610.08653 · cs.ROMagnet-Aware Control of Legged RobotsJ. Playan Garai, S. B. Djuve, C. McGreavy, M. Khadiv
Autonomous robots can increase uptime and reduce human exposure in Big Science facilities, but strong magnetic fields needed for their operation corrupt sensors and induce pose-dependent mechanical wrenches that destabilize robots and challenge conventional reactive controllers. This paper presents a control framework for modeling, estimating, and dynamically compensating for spatially varying magnetic wrenches acting on legged robots to improve robustness in these fields. We introduce a custom physics plugin for the MuJoCo simulator to model magnetic forces on rigid-body elements, alongside an inverse field-estimation framework to infer the latent magnetic field directly from quadruped dynamic responses and any number of sensor readings. Furthermore, we develop a Magnet-Aware Model Predictive Control (MPC) and Whole-Body Control (WBC) architecture that predicts and counteracts magnetic perturbations during locomotion to increase the range of magnetic fields in which the robot can operate. The effectiveness of the framework is validated through both simulation and physical hardware experiments. We show our method increases the the maximum rejectable disturbances from magnetic field in the force space by a factor of 2.5 and and between 1.6-2 times in torque space compared to a non-compensated system. Within the proposed magnetic field, this constitutes an increase in the area in which the robot can operate by 29,34% of which 10,84% would have previously caused an immediate collapse to non-compensated controllers.
quadrupedwhole-body control - arxiv:2610.08651 · cs.AIA Case Study in Assuring AI-Written SoftwareLindsey Ferris, Sierra Bonilla
Software-engineering agents can enable people without formal software training to build systems they could not otherwise implement and simultaneously can produce more code than even experts can meaningfully inspect. In both cases, exhaustive code review is not reliable as the sole basis for human control. We report a case study of a production healthcare platform built through coding agents and governed by an operator without formal software-engineering training. Over time, its workflow grew into a human-led meta-agent system where one agent wrote code, other agents supervised and reviewed it, and project rules carried lessons forward. The operator found that tests, monitors and reviewing agents used to supervise the system were fallible. Some monitors measured proxies rather than outcomes, some audits failed silently, missing checks disappeared from reported results and one automated repair caused operational disruption. In this case, human control depended on keeping the intended outcome, the evidence used to judge it, the agents' permissions and the final human decision were all tied to the same underlying objective.
agentagent system - arxiv:2610.08650 · cs.ROFast Non-Parametric Heteroscedastic Imitation Learning With Geometric PriorsMaximilian Mühlbauer, Arne Sachtler, Markus Knauer, Cem Küçükgenç +3
When learning probabilistic policies from human demonstrations, data-efficient learning and fast adaptations to new scenarios are key requirements. One popular way to achieve intuitive and reliable adaptations is through non-parametric, typically kernel-based, methods. However, existing solutions either fail to account for the geometry of manifolds common in robotics, limiting data efficiency, or, when geometry-aware, provide unreliable uncertainty estimates or require retraining to adapt. We propose a non-parametric approach leveraging geometric priors in scenarios of data scarcity and heteroscedastic uncertainties for probabilistic modeling. We utilize the method to formulate policies based on time or robot state, where non-separable diagonal kernels allow capturing uncertainty relations between degrees of freedom for same-sized in- and outputs. Fast updates, requiring less than 3 ms for a trajectory involving both position and orientation are possible through an optimized formulation. Our approach supports both manifold-valued input and manifold-valued output with large orientation changes. Using task parameterization, adaptation to different object poses is easily possible. We evaluate the approach on a set of toy examples and on real robot manipulation tasks both in autonomous execution and in shared control scenarios.
manipulation - arxiv:2610.08649 · cs.CVStable Scores, Unstable Answers: Frame Phase and Option Order in Video Multiple-Choice EvaluationLichen Zhu, Yiheng Wang, Yueqian Lin, Hai "Helen" Li +1
Video-language models are ranked by multiple-choice accuracy on frames from a uniform grid. The grid has two parameters, a rate and a phase, and benchmarks report only the rate. The phase moves answers: two deployed samplers differing only by a half-step phase offset answer 23.6% of questions differently while scoring within a point, and across four releases from two families shifting only the phase changes roughly one answer in five after controlling option order. PHASEFUSION decodes three offset grids and averages the option posteriors. The grids are the polyphase components of the dense grid. Fusion matches a 32-frame single pass in accuracy within a prespecified margin (logit-scored) and cuts the answers a half-step shift of all three grids changes from 18.2% to 10.1%. Option order, which changes only the presentation, is flagged instead by a one-pass answer margin. Report the phase convention with the budget, or marginalize it.
benchmark - arxiv:2610.08647 · cs.LGSquidAgent: Parallelize Wisely, Coordinate EfficientlyYexiong Lin, Shanshan Ye, Yu Yao, Zhen Fang +2
LLM-based agents solve complex multi-step tasks, but sequential execution incurs substantial latency. In principle, parallelizing work across multiple agents should yield near-linear speedups. Yet existing parallel multi-agent systems often run slower than a single-agent baseline. We attribute this gap to two hidden costs that parallel execution incurs but a serial agent avoids. First, there is a re-exploration cost: redundant effort spent by parallel workers reconstructing context that the orchestrator already possesses, such as prior decisions, that would otherwise be inherited implicitly in a serial execution. Second, there is an alignment cost: the overhead required to reconcile inconsistencies across independently generated outputs. We thus derive a principled decision criterion: a layer should be parallelized only when its critical-path cost, plus re-exploration and alignment overheads, is lower than the corresponding serial cost. While this criterion is naturally expressed in wall-clock time, we observe that LLMs are poorly calibrated when asked to estimate task duration. To address this, we instead measure cost in predicted output tokens, which we empirically find LLMs can estimate substantially more reliably than wall-clock time. Building on this token-based criterion, we propose SquidAgent. It estimates all token budgets in a single planning step, forks each worker directly from the orchestrator's session to eliminate re-exploration cost, and replaces post-hoc reconciliation with a pre-generated shared convention block that converts alignment into a bounded upfront cost. A deterministic scheduler then applies the criterion layer by layer. Empirically, SquidAgent achieves a 2.2$\times$ mean throughput improvement and a 2.6$\times$ mean wall-time speedup over Claude Code, and a 2.0$\times$ throughput improvement over the strongest multi-agent baseline.
agentmulti-agentagent system - arxiv:2610.08642 · cs.ROHygieneRoboBench: Benchmarking Hygiene-Aware Planning for Household RobotsYurun Chen, Josh Qixuan Sun, Jason Qin, Chengtai Li +3
Contact with contaminated objects can spread hazards through a household robot's grippers, tools, and shared surfaces, while new contacts can make an existing plan unsafe. Existing benchmarks do not jointly assess how planners identify hygiene risks from contact history and plan safe continuations after new contact events. Planners must do so within time and resource limits while respecting user priorities. We introduce HygieneRoboBench, with 624 instances across 134 task families, to evaluate safe resolution of household tasks from a given execution history. Tasks capture contamination through two grippers and shared objects, treatment costs, and user priorities. We combine controlled history, profile, and event comparisons with independent plan evaluation. These assess safe resolution, cost efficiency under user priorities, and responses to contact events. Evaluation of LLM-based and symbolic planners shows that safely completing a task does not guarantee the lowest execution costs under the user's priorities. To address this problem, we introduce Hygiene-NSP. It combines LLM-based grounding, contact-history reconstruction, and CP-SAT to jointly plan hygiene treatment and task execution under user priorities. Hygiene-NSP achieves safe resolution and optimal safe resolution rates of 94.4% and 90.4%, respectively. Both rates are higher than those of the evaluated baseline planners on the full dataset. Project page: https://euron-zc.github.io/HygieneRoboBench/.
gripperbenchmark - arxiv:2610.08640 · cs.RORIWANav: Recursive World-Action Models with Self-Improvement for Urban NavigationJing Xie, Shouwei Ruan, Yubin Wang, Yuxiang Zhang +3
Long-horizon urban navigation requires sequential local decisions whose errors can compound over time. Imitation learning (IL) rarely learns from failures, while physical trial-and-error reinforcement learning (RL) is costly. Action-conditioned world models can provide imagined feedback by predicting visual consequences for candidate actions. However, a frozen world model may become less reliable as the policy evolves. In this paper, we introduce RIWANAV, a post-training framework that casts the coupled adaptation of a world model and an action model (policy) as task-specific recursive self-improvement (RSI). Each cycle alternates two updates. The world model evaluates policy actions through imagined outcomes, providing comparative feedback for group-relative policy optimization (GRPO). The improved policy then constructs a grounded self-curriculum, selecting expert-consistent action-video pairs by behavioral novelty and prediction error. The refined world model supplies feedback for the next policy update, closing the recursive self-improvement loop. Experiments show that RIWANAV outperforms training baselines and prior methods, validating the proposed recursive self-improvement loop between the policy and world model. Real-world trials further demonstrate its practical applicability.
world modelaction-conditionedself-improvementpost-training - arxiv:2610.08639 · cs.CVForensic Reserve: Eliciting Latent Knowledge for Image Forgery DetectionJiahua Li, Zixu John, Tom Zhong, Fuping Wu +4
As generated images become increasingly realistic, reliable forgery detection is essential for maintaining trust in visual information. However, existing methods primarily rely on task-specific supervision to adapt vision foundation model representations, without fully exploiting internal forensic knowledge to guide detection. To address this limitation, we propose Reserve-Guided Elicitation (RGE), a framework that treats sparse, origin-sensitive internal components in pretrained models as a forensic reserve and translates their localization into structural constraints for lightweight adaptation. Specifically, we first use the Forensic Lens (F-lens) to decompose activations across layers and token groups into independent components and globally screen them by their response differences between real and generated images, identifying reserve sites and directions. Next, we map the selected directions back to hidden-state space to construct fixed reserve subspaces and insert Forensic Reserve Adapters (FRA) only at the identified sites. Finally, with the backbone parameters, previously fitted reference classifier, and subspace bases fixed, we train only the FRA coefficient maps to generate input-dependent residual updates constrained to the corresponding subspaces, strengthening existing forensic responses. Using only 500 labeled training images and a trainable parameter budget below 0.2% of the backbone, RGE achieves competitive performance across three detection benchmarks without target-benchmark adaptation. Furthermore, RGE consistently improves over the corresponding frozen detectors across eight encoders spanning self-supervised and vision-language pretraining, eliciting a latent forensic capacity broadly shared across pretrained vision models.
benchmark - arxiv:2610.08637 · cs.ROFeeling Through the Load: Compliant Quadruped Locomotion under Payload InteractionsShaunak A. Mehta, Mayank Mishra, Prajit KrisshnaKumar, Sebastian Scherer +1
Quadruped robots are increasingly expected to carry objects while moving through human environments. But what happens when a person interacts directly with the payload rather than with the robot? If the payload is unrestrained, the robot must distinguish intentional external interactions from ordinary payload motion, while still keeping the load balanced and maintaining stable locomotion. How can a quadruped infer and compliantly respond to such interactions using only onboard measurements? In this work, we develop a force-aware locomotion framework that treats payload interactions as commands that shape the motion of the combined robot-payload system. Our approach separates the learning of force-aware locomotion and force estimation on an unrestrained payload. We combine a compliant load-carrying policy with a causal force estimator, trained through estimator-in-the-loop data aggregation and finetuning, to predict interactions from onboard robot measurements. Our simulations and real-world experiments show that the resulting controller can maintain stable payload-carrying locomotion, yield compliantly to external interactions, and use the inferred force to support human-guided changes in the robot's trajectory.
quadruped - arxiv:2610.08630 · cs.CLTowards In-Parameter Memory Augmentation for Large Language ModelsHaoyu Huang, Zhongwei Xie, Jiaxin Bai, Yisen Gao +5
Recently Large Language Models (LLMs) and LLM-based agents increasingly need to incorporate knowledge acquired after pretraining, e.g., domain facts, user preferences, documents, and interaction experience. In-context learning (ICL) and ICL-based agent harness remain flexible, but they consume context capacity and incur repeated discretized encoding cost that grows with context length. \textbf{In-parameter memory} offers a complementary substrate: reusable memory information is represented in model parameters, adapters, or other parameter-like objects that are composed into the forward pass at inference time. This survey focuses on methods that augment LLMs with such parametric memory at deployment: a memory-bearing parameter object is plugged into the forward pass during inference, whether it is acquired before or during deployment. We organize the landscape with two orthogonal axes: \textbf{Parameter Placement}, which includes Embedding, Attention, FFN layers, or Hybrid when two or more layers are used; and \textbf{Parameter Acquisition Time}, which distinguishes methods whose memory object is acquired during deployment (online) from those acquired before it (offline). We clarify boundaries, conduct comparisons, and discuss open directions in interference, safety, co-design with ICL, and recursive self-improvement.
memoryagentself-improvement - arxiv:2610.08627 · cs.AIParallel Predictive World Models for Accurate and Efficient Long-Horizon PlanningWanjin Feng, Baobin Zhang, Ao Yu, Shibo Feng +2
Long-horizon world-model planning typically relies on autoregressive rollouts, where predicted states are repeatedly fed back into the model. This preserves temporal structure but creates a horizon-length sequential path and exposes later predictions to recursive decoded-state feedback. We introduce Parallel Predictive World Models (PPWM), which predict a finite-horizon trajectory in parallel while retaining causal interaction among future representations. Each horizon is conditioned on its causal action prefix, and future representations interact before decoding, separating temporal causality from state-by-state output recursion. We formalize this distinction by viewing autoregressive rollout as a causal trajectory map and identifying the decoded-state feedback pathway removed by PPWM. Across four visual-control tasks, PPWM achieves the lowest long-horizon prediction error and the highest Cross-Entropy Method (CEM) simulator success among the evaluated predictive interfaces. Meanwhile, PPWM achieves more than a 3$\times$ average CEM planning speedup over the autoregressive LeWM baseline. These results suggest that accurate and efficient long-horizon world-model planning does not require state-by-state autoregression, but can instead be achieved through parallel causal trajectory prediction.
world model - arxiv:2610.08624 · cs.LGEarly Memory Selection for Balanced AdamAlberto Fernández-Hernández, Cristian Pérez-Corral, Jose I. Mestre, Manuel F. Dolz +1
We propose a method for choosing the shared memory parameter $β_1=β_2=β$ in Adam from a short pilot training. The selected $β$ remains fixed during the subsequent full training. A local model of Adam's normalized direction balances sampling variability against the delay introduced by averaging past gradients. This balance gives a cubic memory rule, whose two coefficients are estimated from gradient probes at a few pilot checkpoints. The estimator uses the numerator and denominator jointly, preserving their covariance. With a 200-update pilot and sixteen probe gradients at each of four checkpoints, a seed-matched retrospective evaluation on eleven vision and language workloads reduces mean relative validation gap by 40.7% and worst-quarter mean gap by 44.3% against the grid representative of shared $β=0.95$. The mean gap is also 32.3% lower than that of the best constant $β$ chosen across all eleven workloads.
memory - arxiv:2610.08622 · cs.AIAgentic RCA for Internet-Scale Services Using Constrained CreativitySayan Sinha, Vipul Harsh, B. Aditya Prakash, Vyas Sekar +1
System administrators of Internet-scale services need to resolve failure incidents to maintain reliability of such services. Ideally, we want a troubleshooting system to be: (1) expressive to known and unknown incidents with high accuracy; (2) cost efficient at scale; (3) explainable to provide actionable insights operators can act on; and (4) entail low effort from the operators. Unfortunately, most existing systems, including emerging LLM-assisted agentic workflows and structured frameworks for authoring diverse RCA algorithms fall short of achieving all four requirements. We present E4, a novel agentic system for troubleshooting for Internet-scale services. E4 embodies the paradigm of constrained creativity that combines the best of LLM-assisted automation and exploration with the explainability and efficiency of a structured approach. Instead of allowing an LLM agent to write arbitrary code or generate arbitrary responses, we provide the agent a restricted DSL to generate its response via simple loop-free data flow programs. This DSL, equipped with high level operators for troubleshooting, makes E4's output accurate, verifiable and explainable. On a mix of synthetic and real-world workloads, E4 achieves up to 62% better accuracy compared to state-of-the-art solutions, while providing more explainable responses at up to 12x reduced cost.
agentllm agentagentic - arxiv:2610.08621 · cs.AIRecursive Game Creator: An Agentic Product-Level Experience-Oriented Game HarnessJiajun Chen, Haoyu Wu, Mingda Jia, Xihui Liu
Recent game design agents have made substantial progress in generating playable games. However, program correctness does not ensure an enjoyable experience for players. We present Recursive Game Creator, an experience-oriented harness to advance agentic game development from rough game prototypes into entertaining games. Recursive Game Creator organizes recursive development around four components: Designer, Builder, Player, and Reviewer. The Designer translates user instructions and Reviewer's feedback into detailed plans. The Builder turns these plans into candidate games. The coding-native Player creates and executes reusable policies through programmatic interfaces to efficiently collect diverse gameplay trajectories, mitigating evaluation bias caused by slow GUI-based collection. The Reviewer uses carefully designed trajectory-based metrics to induce player preferences, integrating with visual evidence and explicit textual preferences to evaluate games against game-specific criteria. Finally, the Reviewer accepts the better version and provides improvement reviews for the next round, closing the recursive loop. Our method achieves state-of-the-art overall performance of 77.89 on GameCraft-Bench. On GameASG-Bench, it achieves a strict task success rate of 53.2%, a 34.1% improvement over the same-model baseline, and the highest mean runtime-check pass rate at 93.4% among compared methods. A user study shows longer playtime and higher ratings. Code is coming soon.
agentic - arxiv:2610.08595 · cs.ROOne for All, All for One: Coordinated Multi-Agent Diffusion Steering via Stochastic Optimal ControlRiccardo Barbano, Vincent Pauline, Runchang Li, George Webber +5
Deep generative models often produce structured outputs composed of interacting components. Modelling these outputs with a single model requires learning both the component distributions and their interactions. We pursue a modular alternative: reuse independently trained component generators and learn only how to coordinate them to produce coherent structured outputs. Our framework, Coordinated Multi-Agent Diffusion Steering (CMDS), treats frozen pretrained diffusion models as reusable generative primitives and coordinates their reverse processes through a learned control. We formulate coordination as a stochastic optimal control problem, balancing an assembly-level reward that specifies the desired properties of the combined output against deviations from the pretrained dynamics. The learned control amortises this optimisation, allowing reuse across new task instances. Experiments show that CMDS can recover a known target distribution, satisfy different spatial constraints with the same trained control, and recover individual sources from degraded mixtures. Across multi-agent maze navigation, articulated robot planning, and text-conditioned human motion, CMDS turns frozen models into coordinated multi-agent generators.
multi-agent - arxiv:2610.08593 · cs.LGMulti-Label Perceptual Bug Detection in Video Games using Deep Learning on Gameplay FootageNahian Rifaat, Felix Morosov, Loutfouz Zaman
Traditional approaches for automated bug detection in video games, such as manual testing, can be beneficial for the improvement of quality assurance, but they can be expensive and time-consuming. The scarce number of tools available to detect multiple perceptual bugs in the same video frame introduces detection challenges for automated bug detection tools in real-world scenarios. We propose a deep learning model for multi-label perceptual bug detection and compare it against video classification models such as Inflated 3D ConvNet and 3D ResNet. Our proposed model, ResNet-BiLSTM, achieved an F1 score of 85.78% on the benchmark dataset. Our results demonstrated that temporal dependency modelling is beneficial for accurate video-based bug detection. We believe this work with multi-label perceptual bug detection on gameplay videos will help save resources spent on manual testing workloads in video games. Furthermore, we introduce a new dataset with multi-label perceptual bugs in this work. The dataset contains 77,969 video clips across different genres of games with approximately 1.2 million frames, containing combinations from 5 classes of bugs in the same video frame.
benchmark - arxiv:2610.08586 · cs.AIMINDSET: Energy-based Schema Evolution for Long Conversational Agent MemorySujato Dutta, Sreekruthy Tummala, Shashank Vanga, Ayushmi Pavani
Long conversational agents have become essential in our daily lives. They must remember what was said long back in order to help us efficiently complete a task without needing the user to repeat instructions and context repeatedly. However, the main issue is that instructions and context change over time and so the agents must be able to adapt accordingly. A useful memory system should preserve both current and historical states, distinguish stale information from active knowledge, retrieve evidence appropriate to the query and avoid repeatedly invoking a large language model to rewrite prior interactions. We introduce MINDSET, a memory controller that stores a conversation as immutable episodes and organizes them into versioned schemas through minimum-energy state transitions. Each incoming episode may reinforce, supersede, split or create a schema. The transition decision balances representation distortion, contradiction, historical damage, fragmentation and internal inconsistency, while hysteresis prevents isolated contradictions from prematurely rewriting stable memory. We evaluate MINDSET against 5 memory systems on a reproducible sample of 850 questions (700 LoCoMo + 150 MemoryAgentBench). MINDSET obtains the highest observed LoCoMo answer F1 while significantly improving retrieval ranking (Recall@8, MRR and nDCG@8) over the second best method LightMem (p<0.01 after Holm correction). It obtains the highest observed scores on MemoryAgentBench although the relative difference is low. Ablations identify controlled fragmentation and schema-aware assignment as the largest contributors to answer quality. Additionally, a 700-question cross-model evaluation with GLM-4.7 and Gemma-4-31B supported model independence. These results show that long-term memory can be better handled as constrained state management rather than continual summarization.
memoryagent memoryagent - arxiv:2610.08571 · cs.LGRAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG SystemsNiveen O. Jaffal, Ahmet Yuksel, David Mohaisen
Retrieval-Augmented Generation (RAG) systems are vulnerable to prompt-injection attacks embedded in retrieved content. We introduce RAG-PIBench, a benchmark for RAG-style prompt-injection detection containing 4,876 contextual examples across frozen train, validation, and protected-test splits. Using a leakage-aware construction pipeline and strict evaluation protocol, we compare keyword-based, semantic-reference, TF-IDF, and transformer-based detectors. DistilBERT achieves the best protected-test performance (F1 = 0.896, PR-AUC = 0.968), while TF-IDF SVM and logistic regression remain competitive. Our results demonstrate the value of leakage-aware benchmark design and strong sparse baselines for reliable prompt-injection detection in RAG systems.
retrieval-augmentedragbenchmarkevaluation protocol - arxiv:2610.08570 · cs.LGLess Is More: A Leakage-Controlled Study of Dermoscopic Preprocessing for Joint Skin Lesion Classification and Segmentation with YOLO26Truong Viet Vu, Nguyen Chi Hai, Nguyen Phuc Nguyen, Ngo Hoang Tu +2
Handcrafted preprocessing is widely employed in automated dermoscopic analysis to suppress imaging artifacts and enhance lesion visibility. Nevertheless, its actual contribution to modern real-time models remains unclear, particularly when evaluation protocols do not adequately control correlations among images of the same lesion. This study presents a leakage-controlled, lesion-disjoint evaluation of dermoscopic preprocessing and augmentation for joint multi-class lesion classification and instance segmentation using a fixed nano-scale YOLO26 segmentation model (YOLO26n-seg). From HAM10000 (10,015 images), quality control yields 10,013 valid image-mask pairs from 7,468 unique lesions, partitioned into mutually exclusive sets by lesion identity. With the architecture, resolution, training budget, and evaluation protocol held fixed, we compare minimally processed images plus online augmentation against offline class balancing, DullRazor-CLAHE preprocessing, and raw-processed hybrid views, over three random seeds. On the lesion-disjoint test set, the raw baseline achieves a mask mAP$_{50:95}$ of $0.5636 \pm 0.0234$, a Dice score of $0.9356 \pm 0.0024$, and a macro-F1 score of $0.6917 \pm 0.0202$. Offline augmentation does not improve the mean performance, while the combined and hybrid strategies reduce both class-aware segmentation and classification accuracy. At only 2.69 million parameters, the model runs at approximately 50 frames per second. Under a leakage-controlled, lesion-disjoint protocol with all non-input factors held fixed, minimally processed dermoscopic images combined with standard online augmentation deliver a better accuracy-efficiency trade-off than increasingly complex deterministic preprocessing, which yields no consistent joint benefit across three seeds on HAM10000.
evaluation protocol - arxiv:2610.08561 · cs.LGReinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with TransformersNaoki Nishikawa, Taiji Suzuki
Reinforcement learning (RL) has become a standard tool for post-training language models on reasoning tasks, where the policy is updated by reward feedback while exploring the space of responses. Despite its empirical success, theoretical understanding of RL post-training remains limited, in particular of why on-policy exploration combined with a neural reward model is effective. In this paper, we address this question by modeling the reward as a hierarchical function on the response space: the reward consists of infinitely many local components, each of which becomes relevant only after the preceding ones have been resolved. We show that a natural Transformer-based actor--critic algorithm, which alternates between sampling from the current KL-regularized policy, fitting a Transformer critic to the observed rewards, and updating the policy, achieves the minimax optimal rates in the query budget and in the regularization strength up to logarithmic factors, and is minimax optimal for a fixed number of prompts. In contrast, we prove that sampling from the fixed reference distribution, as in offline reward modeling, can limit regret decay to a logarithmic rate. These results show that on-policy exploration progressively zooms in on the region where the reward is concentrated, and quantify its benefit for RL post-training.
post-training - arxiv:2610.08560 · cs.LGHave I Seen Enough? Frozen Video-Language Models Encode Evidence ReadinessDan Ben-Ami, Kobi Cohen, Chaim Baskin
Streaming video-language models must decide not only what to answer, but whether the evidence needed for the current question has arrived. Existing systems learn that decision as a separate trigger; we ask whether an unmodified model already computes it. We show that frozen VideoLLMs carry a linearly readable evidence-readiness signal, labelled from timestamped evidence rather than from model output. It decodes in all seven models of a shared byte-identical evaluation (AUROC 0.733-0.905 under the strictest not-ready sampling, where a fitted clock is near chance), and a probe fitted without any of a benchmark family's footage still reads that family. It is question-conditioned: on byte-identical windows, changing only the question reverses the readout on 66.1% of pairs, while every question-blind control is at chance by construction. The model can answer incorrectly and still encode readiness: AUROC remains 0.722 among wrong answers. Readiness also beats uncertainty estimators and their supervised combination on latency-matched answer selection, and tracks independent human judgments more closely than confidence. Released streaming triggers are also linear readouts, yet a trained trigger read on its own base model's activations is approximately orthogonal to readiness and decodes it far less accurately than a probe. We turn the readout into Readiness Gating, an answer-timing policy that improves accuracy by up to +9.75 pp at matched video duration with negligible computational overhead. How much it gains varies with the accuracy headroom the task makes available: across 26 configurations the gain tracks that headroom, and an intervention that moves it over identical pixels moves the gain with it.
benchmark - arxiv:2610.08559 · cs.LGLatent space bias directions in LLMs capture confidence, not fairnessStephanie Buttigieg, Maeve Madigan, Parameswaran Kamalaruban, Stuart Burrell
Activation steering has gained popularity as a lightweight inference-time debiasing technique for large language models. However, prior work reports that steering vectors generalise poorly, with unintended effects on model performance and limited transfer to new datasets. Our work analyses what the debiasing direction used for activation steering actually encodes, in order to shed light on its inconsistent performance. We study the linear debiasing direction obtained by contrasting the activations of anti-biased and biased prompts, and evaluate it as a steering intervention across bias and general knowledge benchmarks. We find that this direction is dominated by model confidence, pointing from regions of high to low-probability tokens in activation space rather than encoding a meaningful representation of model bias. Steering along it does reduce measured bias, but this is a consequence of reducing model confidence: on QA benchmarks we find that this steering drives the model to abstain from answering, with a side effect of improving fairness metrics. Our experiments show that model confidence is the dominant separating factor between biased and anti-biased prompts in hidden space, indicating that isolating a linear representation of bias which is disentangled from model confidence is difficult and steering-based debiasing results should be interpreted with care. In short, steering appears to reduce bias, not by correcting the model's underlying preferences, but by making it less confident, even on tasks unrelated to bias.
benchmark - arxiv:2610.08555 · cs.ROTowards Efficient Robotic Manipulation Models with Self-Recursive PruningZijia Chen, Yuenan Hou, Yu Li, Weijie Li +1
Network pruning can reduce parameter redundancy in robotic policies. However, generic pruning criteria are tailored for image recognition tasks and commonly designed to preserve weight magnitude, local reconstruction, or language-model likelihood rather than closed-loop action behavior. Directly applying these pruning algorithms to robotic tasks yields unsatisfactory performance. In this paper, we propose Loss-Conditioned Activation-Moment (LCAM) pruning, a training-free method for unstructured pruning of pre-trained robotic manipulation policies. Specifically, we first rank connections using row-normalized weight contribution, activation moments measured on calibration demonstrations, and the sensitivity of output directions to the action-prediction loss. We further design a self-recursive coarse-to-fine procedure: importance is recalibrated after each nested coarse pruning stage, while held-out offline action distortion guides fine-grained budget allocation after a sparsity knee. Our algorithm is free from costly recovery training and simulator rollouts after pruning. Experiments on three LIBERO suites with competitive robotic policies, together with evaluations on OpenVLA, show that LCAM attains competitive performance across a broad range of pruning ratios. Notably, on LIBERO-Object with OpenVLA, our LCAM achieves 84.0% success at 50% unstructured pruning, retaining over 90% of the dense policy's success rate. Promising results on real-world robotic ping pong further demonstrate the effectiveness of our pruning algorithm.
manipulationopenvlalibero - arxiv:2610.08553 · cs.LGDeltaTTT: Layerwise Optimization for Nonlinear Recurrent MemoryYining Li, Dongchen Han, Jie Fu, Gao Huang
Sequential test-time training adapts a memory network through successive updates, each computing an inner-loop gradient based on the network's previous state. Intuitively, this state dependence should allow each update to account for what the memory has already learned and better incorporate new information. However, we find that this expected advantage does not consistently materialize in nonlinear memories: a fixed-base parallel TTT baseline outperforms its serial counterpart. Our exploratory experiments point to a key underlying difficulty: nonlinear memories can be harder to optimize than linear ones within a single pass over the sequence. To alleviate this optimization difficulty, we introduce DeltaTTT, which replaces joint inner-loop optimization of a two-layer memory network with layerwise learning. Each layer is assigned a local prediction target and updated through a state-dependent delta rule. This formulation retains a nonlinear readout while enabling chunkwise parallel computation. Experiments on DeltaNet and LaCT backbones show improvements in language modeling and retrieval over their recurrent baselines.
memory - arxiv:2610.08541 · cs.ROMicro Neural Policies for Safe Real-Time Robotic ControlHongpeng Cao, Riccardo Curcio, Daniele Ottaviano, Marco Caccamo
In this paper, we investigate the synthesis of Micro Neural Policies (MNP) to enable safe and robust real-time robotic control on computationally constrained embedded devices. We demonstrate that integrating Evolution Strategy (ES) and Statistical Model Checking (SMC)-based verification for policy search can drastically reduce neural network size without compromising safety and robustness. We conduct a large-scale training and evaluation of MNP on Cartpole and Quadrotor control tasks, varying control frequencies and network architectures. After validating these policies in simulation, we evaluate their deployability through zero-shot transfer to physical systems. Our experiments show that MNP can successfully achieve safe sim-to-real transfer without sacrificing control performance. We then show that the policies' memory footprint, ranging from 0.5 to 7.5 kB, allows deployment on microcontrollers, where they achieve real-time inference latency with under 25 ns of jitter while leaving the chip idle for over 97% of the time for additional workloads. This makes them a highly practical solution for severely resource-constrained robotic systems.
sim-to-realmemory - arxiv:2610.08539 · cs.CVRSJEV: Discriminative Remote Sensing Scene Classification with Multimodal Large Language ModelsDongchen Si, Di Wang, Mingzhen Xu, Jing Zhang +2
Remote sensing scene classification is a fundamental task in Earth observation and geospatial analysis. Existing approaches mainly follow three paradigms: task-specific visual classification, vision-language similarity matching, and autoregressive multimodal generation. However, visual classifiers rely on predefined label spaces, CLIP-based methods perform recognition through static image-text alignment, and multimodal large language models (MLLMs) introduce unnecessary token-level generation for classification tasks with explicit candidate categories. To address these limitations, we propose RSJEV, a one-pass multimodal decision framework for remote sensing scene classification. Unlike conventional MLLMs that formulate classification as autoregressive text generation, RSJEV reformulates scene classification as a candidate-conditioned multimodal discriminative decision process, where visual representations, task instructions, and candidate category semantics are jointly modeled. Specifically, we introduce a OnePass Decider that extracts multimodal decision states and directly estimates category probabilities within the candidate category space, eliminating autoregressive decoding while preserving vision-language interactions. Extensive experiments on three widely used remote sensing scene classification benchmarks, including UC Merced, AID, and NWPU-RESISC45, demonstrate that RSJEV achieves superior classification performance compared with representative CNN-, Transformer-, Mamba-, CLIP-, and MLLM-based methods. Moreover, RSJEV significantly reduces inference costs and achieves a better accuracy-efficiency trade-off with only a compact 0.8B-parameter model. These results demonstrate the effectiveness of state-conditioned multimodal decision making for efficient remote sensing image understanding. The code will be available at https://github.com/Dongtcs/RSJEV.
benchmark - arxiv:2610.08537 · cs.LGFlowCF: Sparse Counterfactual Explanations for Mixed-Type Tabular Data using Flow MatchingEmmanouil Panagiotou, Eirini Ntoutsi
In the field of Explainable AI (XAI), counterfactual (CF) explanations interpret a model's decision by suggesting the changes to the input that would lead to a more favourable outcome. To be useful in practice, such an explanation should change few features and change them as little as possible, properties known as sparsity and proximity. We observe that existing methods remain limited in this respect, especially for numerical features, whether they are model-agnostic and amortised, or gradient-based with full access to the model. In this paper, we propose FlowCF, a model-agnostic generative method that frames CF generation as sparse transport from the factual to the target class. We solve this transport with flow matching, which we extend to mixed feature types with a novel mixed flow operator, and exploit the resulting geometry to optimise for sparsity through a gating network that minimises the number of features the transport changes. Extensive experiments on six benchmark datasets demonstrate that FlowCF produces the best numerical sparsity and proximity, changing 29% of the numerical features where the best baseline changes 89%, at 70% smaller displacement, while remaining comparable on the other desiderata.
benchmark - arxiv:2610.08535 · physics.app-phAn associated model of Coulomb friction based on the real area of contactManon Thbaut, Laura De Lorenzis
Coulomb friction is a non-associated law: it contains a threshold that depends on the contact pressure, i.e. a stress that is not conjugate to any internal variable, hence it admits no dissipation potential in the sense of generalized standard materials (GSM), and the incremental frictional contact problem is not a minimization problem. In this paper, we propose an alternative friction model that retains Coulomb-like behavior while being associated and fully GSM-compatible. Key to our formulation is the introduction of a new internal variable motivated by the microscopic contact state of rough surfaces, whose evolution is driven by the plastic deformation of the asperities. Under a non-decreasing contact pressure and below a threshold pressure, the model recovers Coulomb friction up to an asperity-scale penetration depth. This depth is physically meaningful and can be calibrated to reproduce known tribology results. Under decreasing contact pressures, the model exhibits a memory effect due to irreversible plastic deformation of the asperities, whereas above the pressure threshold it yields a saturation of the frictional traction. We present both penalty and Lagrange multiplier formulations of the model. A 2D finite element implementation of the penalty approach confirms excellent agreement with the classical Coulomb predictions across two benchmark tests.
memorybenchmark - arxiv:2610.08533 · cs.LGBeyond Perturbation Magnitude: Direction-Dependent Responses in Multimodal Geometric RepresentationsYongsheng Luo, Wengan He, Yu Li, Rouying Wu +1
Geometric alignment scores based on Gram determinants provide a compact way to model higher-order consistency among modalities, yet how such scores respond to modality degradation is poorly understood. This paper asks whether the response of a multimodal geometric score is determined primarily by the magnitude of the perturbation-induced displacement. Using frozen cohorts from MSR-VTT (N=878) and DiDeMo (N=980), we apply controlled video blur and audio noise and analyze the response in the relational geometry on which the score is defined. Displacement magnitude explains at most 15% of the out-of-sample variance in the absolute response, and magnitude-matched pairs respond systematically differently, so scalar magnitude does not organize the response. The closed-form first-order expansion of the Gramian volume yields the Directional Geometric Response (DGR): the projection of the displacement onto the local volume gradient, which jointly captures the clean operating point, displacement magnitude, and displacement direction. The absolute first-order DGR term explains the observed response with out-of-sample R^2 of 0.838-0.969, matched-magnitude ranking accuracies of 0.864-0.963, and response-sign accuracies of 0.909-0.989, whereas the tested direction-free alternatives remain weak or unstable under the corresponding evaluation protocols. A pre-specified gain-normalization candidate, V/(g_V+eps), fails its predictability and clean-order gates. DGR uses the observed degraded-state displacement and is therefore an explanatory quantity, not a deployment-time predictor: geometric response depends on where the representation operates, how far degradation moves the relational geometry, and in which direction it moves.
evaluation protocol - arxiv:2610.08527 · cs.LGPHBA: Prefix-State Hybrid Block AttentionRuijie Li, Jiaxi Hu, Shiyu Wang, Yuxuan Liang
Hybrid architectures combining linear sequence models with softmax attention provide an effective balance between efficient long-context modeling and precise token retrieval. Existing designs such as Native Hybrid Attention (NHA) combine compressed long-term states with sliding-window attention, but their exact attention is restricted to a fixed local window. In this work, we introduce Prefix-State Hybrid Block Attention (PHBA), which replaces local sliding-window attention with top-k block-sparse retrieval and couples each retrieved block with a compact prefix state summarizing its preceding context. The prefix states are constructed by a gated linear recurrence at block boundaries and retrieved together with the corresponding token blocks, allowing the model to combine precise long-range evidence with compressed historical context within a unified layer. We further develop a hardware-aware Triton implementation that streams routed token blocks and prefix states without materializing large intermediate tensors. Experiments show that PHBA improves long-context and retrieval performance over strong linear and hybrid baselines while retaining efficient training and inference.
long-context - arxiv:2610.08526 · cs.ROWareFly-VLA: A Vision-Language-Action Framework for UAV Navigation and Human Tracking in Smart WarehousesThinh D. Le, Son T. Nguyen, Duong Q. Nguyen, Dung D. Le +2
Vision-Language-Action (VLA) models have achieved impressive results in robotic manipulation and ground-mobile navigation, yet language-conditioned control of unmanned aerial vehicles (UAVs) in smart warehouses remains largely unexplored, hindered by the lack of benchmarks that jointly provide continuous low-level flight actions, fine-grained natural-language target descriptions, and realistic industrial environments. This paper introduces WareFly-VLA, a photorealistic UAV VLA framework and dataset for language-guided human search, localization, and tracking in warehouse environments. It contains 507 human-teleoperated flight episodes and 8,504 high-resolution RGB transitions collected in NVIDIA Isaac Sim, each paired with a human-written appearance description of the target worker and a synchronized four-degree-of-freedom control command. Two aerial tasks are covered: target approach and person following, under occlusion, long-range search, altitude variation, and clutter. A unified benchmark of four open-source VLA architectures (SmolVLA, GR00T N1.7, pi_0 and OpenVLA) is established under a leakage-free episode-level protocol at two control rates. The results show that language-conditioned aerial control in warehouses is far from solved: performance drops substantially under strict generalization settings, continuous action modeling consistently outperforms discrete action tokenization, only the forward channel is reliably learnable from a single frame, and current foundation-model interfaces transfer poorly from ground and humanoid embodiments to aerial platforms. The synchronized video, language, action, pose, and difficulty annotations further support world-model research. The dataset, baselines, and evaluation protocol are released to support language-grounded aerial autonomy in smart warehouses.
vision-language-actionvlamanipulationhumanoidopenvlagr00t - arxiv:2610.08518 · cs.CV2D Spatial Reasoning with Adaptive Neural Cellular AutomataMartin Spitznagel, Janis Keuper
Many modern learning approaches are still struggling with spatial reasoning tasks, i.e. they lack the ability to utilize geometric information of perceived entities and their spatial relation to each other to solve problems. We introduce a novel Adaptive Neural Cellular Automata (aNCA) architecture which uses deformable convolutions to dynamically adapt the perceptive field and iteratively reason over 2D spatial relations on grid-like data structures (e.g. images). Empirical results on public benchmarks show state of the art comprehensible results with high generalization abilities for solving image based puzzles like Sudoku or finding the shortest path in a maze.
benchmark - arxiv:2610.08514 · cs.AIHow Much Evidence Should a Coding Agent's Self-Correction Carry? Adaptive Dirichlet Evidence for Self-DistillationYunbo Long, Guangya Hao, Yuhan Liu, Yiting Duan +3
Execution feedback lets coding agents revise programs and learn from their own corrections. A correction's learning weight should reflect both the transitions supported by its executions and the amount of evidence behind that support. We introduce Effective-Evidence Self-Distillation (EESD), which represents these quantities separately. Normalized execution relevance determines relative transition support and an effective pseudo-count mass; a Dirichlet posterior then produces an uncertainty-penalized weight for KL-anchored correction learning. Under a symmetric prior, changing mass preserves category ordering, and effective mass yields a supervised coefficient bounded by its matched fixed-mass counterpart. Across four model-domain history sweeps, increasing visible observations from one to eight reduces future-outcome NLL by 55.0-59.3%. At eight observations, effective mass achieves lower NLL than fixed mass in all four comparisons. In the primary matched DeepSeek/RunBugRun study, argmax predictions agree on all 3,000 examples, with the largest NLL gain under concentrated relevance. After one correction-learning round, DeepSeek/CodeARC all-tests Pass@1 increases from 15.0% to 20.4%, with a paired 95% source-bootstrap interval of [+2.8, +8.0] percentage points. The twelve-setting downstream evaluation establishes the model-domain scope of this update. These results show how separating evidence support from evidence mass changes probability estimation and correction learning in coding agents.
self-correction - arxiv:2610.08513 · cs.AIWiki-Talkie: Multilingual Benchmarking of Persona-Based Agents on Real-World DiscussionsDennis Fucci, Andrea Bacciu, Dong Liu, Weronika Łajewska +1
LLMs are increasingly deployed as autonomous agents in social environments, making it critical to study their ability to faithfully simulate human interactions. Central to this is grounding agents in realistic user personas, yet existing datasets rely on fictional personas and are limited to a handful of languages, lacking the empirical grounding necessary to evaluate behavioral fidelity across diverse populations. We introduce Wiki-Talkie, a multilingual dataset of real-world conversations from Wikipedia Talk pages across five languages spanning two language families: Germanic (German, English) and Romance (Spanish, French, Italian), paired with personas derived from real user communities and encompassing sociodemographic attributes, self-descriptions, and behaviorally grounded interaction traits. Using Wiki-Talkie, we evaluate agent interactional behavior on a next-turn generation task across various persona conditioning strategies. Our evaluation assesses whether agents collectively reproduce the distributional behavioral patterns observed in human discussions. Results show that user's comment history exemplifying interaction behavior consistently outperforms explicit persona information. In addition, models systematically underproduce negative or extreme sentiments, while over producing references and suggestions, revealing biases toward agreeableness and positivity. Crucially, these patterns hold robustly across languages, with small cross-lingual differences.
agentautonomous agentbenchmark - arxiv:2610.08510 · cs.AICylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal TransformationOnur Selim Kilic, Afra Nawar, Cem Okan Yaldiz, Michael J. Cho +5
Paired translation between quasiperiodic physiological waveforms (i.e., recovering a target oscillatory signal from the source) is central to the interpretation of cardiovascular signals derived from wearables placed at different body locations. This source-to-target mapping in these problems carries inherent geometric structure: the phase wraps around the cycle and must be treated as a circular variable, the amplitude remains strictly positive, and the beat-to-beat alignment can drift unpredictably across cycles and subjects. While deep neural networks have been used for phase estimation and complex-valued signal modeling, prior work does not explicitly learn phase transport between paired signals. Consequently, neither endpoint-supervised regression nor the standard affine path used in flow matching accounts for this phase--amplitude structure. We introduce \emph{cylindrical geodesic flow matching} for paired cardiovascular waveform translation. We show that the standard affine path used in flow matching distorts intermediate amplitude and instantaneous frequency when interpolating between quasiperiodic signals; replacing it with a closed-form geodesic on the phase--amplitude cylinder eliminates these artifacts and converts each training pair into dense, geometry-consistent velocity supervision. On zero-shot photoplethysmography and limited-support seismocardiography adaptation benchmarks, our method consistently outperforms interpolation baselines and matches or exceeds direct supervised prediction, reducing Hilbert Transform, $L_2$, and Dynamic Time Warping distance by up to ${\sim}15\%$ over the strongest competing baseline. These results suggest that bridge geometry is a critical inductive bias for flow matching on oscillatory signal translation.
benchmark - arxiv:2610.08502 · cs.LGX-OPM: Explainable Automatic Digital On-Chip Power Modeling for Enhanced RobustnessJingbo Jiang, Xizi Chen, Jian Peng, Wei Zhang
Proactive power management systems reduce processor dynamic power through runtime power prediction and power-aware scheduling. Accurate, stable and low-overhead digital on-chip power meters (OPMs) are crucial for improving the prediction quality. Recent studies have explored various modeling methods, including using linear models, decision trees, and multi-layer perceptrons (MLPs) to construct OPMs. However, most current approaches train models end-to-end without analyzing the physical interpretability of features, affecting their ability to generalize to unseen workloads. Grounded in the design principles of synchronous digital VLSI circuits, X-OPM introduces a robust feature engineering framework that uses tree-based models to capture feature interactions and linear models for prediction. It also incorporates a human-in-the-loop workflow to balance model accuracy against modeling effort. Evaluated on a commercial C906 vector processor, X-OPM consistently achieves $R^2 > 0.93$ across all workloads with sampling window size set below $8$ cycles. In contrast, state-of-the-art methods including APOLLO, COBIT, and standard MLPs fail to generalize across all test cases. Layout with commercial EDA tools shows that X-OPM incurs an area overhead below $0.1\%$, which is on par with lightweight tree-based and linear models, and significantly smaller than MLP-based models.
human-in-the-loop - arxiv:2610.08486 · eess.SYFlatness-Based Geometric Path Following via Guiding Vector FieldsJ. P. van Gool, H. G. de Marina, B. Jayawardhana, S. Ahmed
Path following requires an agent to converge to and traverse a geometric path without a prescribed timing law. Guiding vector fields (GVFs) address this directly, but as guidance laws they offer no mechanism to compensate for the agent's own dynamics. Differential flatness-based control (DFBC), on the other hand, compensates for the agent's nonlinear dynamics but relies on a time-parameterized reference trajectory. This letter presents a unified algorithm, which we term flatness-based geometric control (FGC), that generates the DFBC reference hierarchy directly from a GVF and its higher-order time derivatives, eliminating the need for a pre-planned time-parameterized trajectory while retaining full dynamics-informed control. A cascade Lyapunov argument establishes exponential convergence of the tracking error and the physical trajectory to the desired path. The framework is further extended to singularity-free GVFs, which removes the topological obstruction and guarantees the condition for global exponential convergence on closed or self-intersecting paths. The proposed algorithm is validated in simulation.
agent - arxiv:2610.08479 · cs.LGMetaLearnNCA: Few-Shot Offline Meta-Learning via Interacting Neural Cellular AutomataEtienne Guichard, Stefano Nichele
Few-shot meta-learning traditionally formulates task adaptation either as analytical gradient descent through unrolled computational graphs or as metric-based distance comparisons over flattened 1D fea- ture vectors, which either incur costly test-time backpropagation or discard native 2D spatial geometry. In this work, we propose METALEARNNCA, a decentralized framework that achieves few-shot adapta- tion through the dynamical interaction of coupled Neural Cellular Automata (NCAs) without computing analytical gradients during inference. MetaLearnNCA decomposes task adaptation into an Active- NCA, which executes task inference conditioned on a continuous 2D spatial memory grid termed the spatial program, and a learned Meta-NCA, which acts as a decentralized cellular optimizer by diffusing spatial error residuals across local neighborhoods to dynamically update this program. METALEARN- NCA is competitive against canonical meta-learners in-distribution (96.12% on Omniglot) with Out-Of- Distribution transfer gains on MNIST, KMNIST, and Fashion-MNIST transfer across 10 independent testing seeds across 1-, 5-, and 10-shot regimes (e.g., surpassing Prototypical Networks by +10.54% on 10-shot MNIST and a +3.87% gain on 10-shot Fashion-MNIST over FOMAML). Our results establish that robust, gradient-free learning-to-learn can emerge from decentralized cellular dynamics on non-von Neumann substrates.
memory - arxiv:2610.08475 · cs.LGLearning PDE solution operators with variable initial conditions via Latent Dynamics NetworksStefano Maria Pizzamiglio, Stefano Pagani, Francesco Regazzoni
In many-query scenarios, data-driven surrogate models provide an efficient alternative to high-fidelity solvers for simulating physical systems governed by Partial Differential Equations (PDEs). In this context, the Latent Dynamics Network (LDNet) has recently demonstrated remarkable performance in predicting the response of spatio-temporal systems, combining Neural Ordinary Differential Equations with nonlinear dimensionality reduction. However, the original formulation assumes a fixed initial condition, limiting its applicability to many real-world applications where a system evolves from varying starting states. In this work, we overcome this limitation while keeping the end-to-end training procedure of the original LDNet and its encoder-free nature, which preserves its intrinsic independence from spatial resolution and grid topology. We infer the initial latent state directly from a small set of early-time observations, treating latent-state initialization as an adaptation problem, and investigate two strategies: an auto-decoding formulation and a meta-learning approach in which the initial latent state acts as a task-specific context variable. We demonstrate the accuracy of the proposed methods across diverse physical phenomena, spanning advection-diffusion, fluid dynamics, and solid mechanics. Meta-learning markedly accelerates latent-state inference and induces smoother, better-conditioned optimization landscapes, and spontaneously organizes the latent space into a structured representation that reflects physically meaningful features of the underlying dynamics. The coordinate-based decoder enables training from spatially subsampled data while recovering high-resolution solution fields at inference. The resulting approach provides an efficient and resolution-independent surrogate modeling framework for many-query simulations of time-dependent PDEs with varying initial conditions.
latent dynamics - arxiv:2610.08469 · cs.ROA Belief-State World Model for Catheter Navigation under Sparse Fluoroscopy: A Planar Proof of ConceptDamini Rijhwani
Endovascular catheter navigation relies on continuous fluoroscopy, exposing patients and clinical staff to ionizing radiation throughout the procedure. We investigate whether a physics-based world model can sustain the navigation task between deliberately sparse X-ray acquisitions, and whether the model can signal when its internal state estimate is no longer reliable. We formulate sparse-fluoroscopy navigation as a partially observable Markov decision process where a Cosserat rod simulator supplies transition dynamics, sparse noisy projections provide observations, and a particle filter maintains a belief over the device state, reduced in this implementation to a tip state with a geometric contact proxy. We evaluate this formulation in a deliberately simplified setting: a synthetic planar vessel phantom with a quasi-static rod model and simulated projections, without clinical or animal data. In this setting, the belief-state model tracks the simulated tip with a root mean square error of 1.30 mm while acquiring observations at one fifteenth of the continuous rate (0.97 mm at every frame, 1.51 mm at one thirtieth), reported 90 percent credible intervals achieve 0.92 empirical coverage, and the belief-derived contact risk estimate discriminates unsafe contact events with an AUROC of 0.68. These results constitute a proof of concept on a simplified simulation rather than a demonstration of clinical readiness; their purpose is to establish that calibrated belief, rather than point-estimate accuracy alone, is the essential property a sparse-imaging world model must deliver.
world model - arxiv:2610.08464 · cs.ROFederated Bayesian Surveillance of Mechanical Thrombectomy Adverse Events: A Population Risk Layer for Surgical Digital TwinsDamini Rijhwani
Learned surgical simulators and world models can roll out plausible procedural futures, but they carry no grounded estimate of how often interventional devices actually harm patients. We propose treating population-scale adverse-event surveillance as a distinct belief layer of the surgical digital twin, and we evaluate a federated Bayesian protocol for learning it under formal privacy guarantees. Each site holds per-class Gamma-Poisson posteriors over adverse-event rates and exchanges only Rényi-differentially-private natural-parameter updates. We benchmark on the complete FDA MAUDE cohort for thrombus-retrieval catheters (product code NRY): 8,617 reports, of which 6,491 are classified by transparent keyword rules into five thrombectomy complication classes and partitioned across $K=8$ manufacturer sites. At a matched privacy budget of $(\\varepsilon \\approx 2.09, \δ= 10^{-5})$, the conjugate protocol attains a held-out Poisson score of -5.78 per test event versus -26.58 for FedAvg with differential privacy. The non-private federated model also outperforms centralized pooling (+3.19 vs +2.93), evidence that manufacturer-specific complication profiles are real and that federation preserves them. Because MAUDE lacks procedure denominators, outputs are relative rate orderings rather than absolute risks, and we report all privacy-utility operating points.
world modelbenchmark - arxiv:2610.08463 · cs.LGUNREAL: Unifying Retrieval and Long-Context with a Single ModelEdan Kinderman, Elad Hoffer, Yochai Blau, Brian Chmiel +3
Long-context inference and Retrieval-Augmented Generation (RAG) handle evidence selection at vastly different scales, from a single long prompt to an entire corpus. We ask whether a single model-internal mechanism can select evidence across this range. We introduce UNifying REtrieval And Long-Context with a Single Model (UNREAL), a model-native evidence selection framework to span corpus retrieval and long-context inference. UNREAL encodes chunks and derives retrieval queries directly from the frozen LLM's internal representations. It adds fewer than 500K trainable parameters and leaves the backbone unchanged. On a 3B-token, 21M-chunk Wikipedia index, all four dense and hybrid UNREAL backbones outperform state-of-the-art retriever-reranker systems. The best model raises recall from 49.1% to 73.2% on HotpotQA, from 31.7% to 60.1% on 2WikiMultiHopQA, and from 8.8% to 14.4% on MuSiQue. Applied to long-context tasks, the same selection mechanism removes distractors before generation, raising NoLiMa accuracy from 1.0% to 24.83% at its maximum context length of 128K tokens, and LV-Eval's F1 score from 49.97% to 54.66% at 256K. UNREAL also reduces FLOPs and time-to-first-token relative to full-context inference from roughly 32K tokens onward, with larger gains as context grows. Together, these results establish model-internal evidence selection as a common foundation for corpus retrieval and evidence-sparse long-context inference.
long-contextretrieval-augmented - arxiv:2610.08452 · cs.LGAgentic AutoRAG: RAG Pipeline Optimization through Reasoning-Driven AgentsLasse B. Strand, Robert Jakob, Kevin O'Sullivan, Markus Kreft
Retrieval-augmented generation (RAG) is a widely used approach for grounding large language models (LLMs) in external knowledge. However, configuring a pipeline is an expensive hyperparameter optimization problem over many interacting choices, from chunking and embedding model to reranking and generation. Existing optimizers, from greedy search to Bayesian optimization, reduce each trial to an aggregate score and search without modeling why a configuration performed as it did, even though the retrieved chunks already provide evidence about whether each failure occurred during retrieval or after it. We introduce Agentic AutoRAG, an LLM-agent optimizer for multi-objective RAG hyperparameter optimization with retrieval-versus-generation failure attribution. It proposes configurations scored on a frozen exam from the corpus: after each trial a Diagnoser attributes each failed question to retrieval or generation, and a Proposer, grounded in a knowledge base of model rankings and pricing, selects the next configuration, weighing accuracy against cost to trace a Pareto frontier. On three multi-hop QA benchmarks it reaches higher LLM-judge accuracy than every baseline we compare, and within its first 10 trials it matches or beats the statistical baselines' full 30-trial judge accuracy. In its cost-aware mode on a real-world healthcare corpus it reaches a median exam accuracy of 77%, above the strongest baseline's 71.5%, at about 58% of that baseline's cost per query, and it matches that 71.5% at about 22% of the cost.
retrieval-augmentedragrag pipelineagenticbenchmark - arxiv:2610.08446 · cs.AIAssemState: Manual and Physical-State-Guided Reasoning for Zero-shot Furniture AssemblyZhiyuan Qi, Jierui Li, Yifan Shen, Cheng Qian +1
Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physical environment remains difficult. Furniture assembly requires not only recovering step-level operations from diagrammatic manuals, but also translating semantic attachment relations into 6D pose updates that enable parts to physically interact with the environment and previously assembled components. To study this problem, we propose AssemState, a zero-shot framework for manual and physical-state-guided furniture assembly. It firstly employs anchor-guided boundary assembly states to decompose manual pages into single-part operations and recover an assembly-tree. Then, it uses iterative after-state feedback refinement to guide successive (SE(3)) updates and corrections, and validates their physical plausibility through simulation-based release tests. Experiments show that compared with the strongest prior baseline, AssemState improves F1 from 38.58\% to 62.80\% and Tree Exact Match from 28.24\% to 53.92\% for assembly-tree recovery. On 243 independently evaluated part-level operations, our proposed iterative refinement improves judge-accepted operations from 0 to 5.3\% and reduces mean Chamfer distance from 5.4111 to 1.7744. However, visually plausible candidate poses may still suffer from collision, floating, mirror-orientation errors, incomplete seating, and wrong-side attachment. These results show that AssemState improves operation-structure recovery and selected local pose metrics, while MLLMs remain limited for spatial relationship reasoning.
iterative refinement - arxiv:2610.08444 · cs.ROActTune: Action-Aware Precision and GPU Operating-Point Adaptation for Energy-Efficient Vision-Language-Action InferenceZou Qingyun, Bin Gao, Wenju Zhao, Weng-Fai Wong +2
Vision-language-action (VLA) policies repeatedly invoke inference to control robots, making graphics processing unit (GPU) energy a recurring cost of task execution. Reducing energy per inference call, however, may not reduce energy per successful task if numerical errors increase failures or slower inference prolongs execution. We therefore target GPU energy per successful task while preserving task success and keeping the inference-latency increase within 10\%. Our approach builds on two observations: quantization sensitivity varies across action classes, model layers, and weights versus activations; and numerical precision changes the workload, shifting favorable GPU operating points. We introduce ActTune, an action-aware framework that connects layer-wise precision allocation with workload-dependent GPU operating-point selection over requested frequency--power-cap pairs. A lightweight decision tree learns its splits and leaf precision configurations directly from configuration action errors, then selects precision before each policy call. The controller forecasts the next workload and applies the selected GPU operating point asynchronously using a lookup table calibrated under a latency budget. A shared resident quantized weight bank enables configuration switching without weight reconstruction or additional policy evaluations. On LIBERO, a benchmark for lifelong robot learning, ActTune improves mean task success by up to 2.3\% relative to state of the art. Relative to the original BF16 implementations, it delivers up to $2.02\times$ faster inference and, with GPU operating-point adaptation, reduces energy per successful task by up to 76.8\%.
vision-language-actionliberobenchmarkpolicy evaluation - arxiv:2610.08441 · cs.ROSafe Multi-Robot Collaborative Transport Using Density FunctionsJagannath Prasad Sahoo, Sriram S. K. S. Narayanan, Umesh Vaidya
This paper presents a hierarchical density-based model predictive control framework for safe collaborative manipulation by multiple quadrupedal robots. The framework enables a team of robots to push a shared object to a desired pose using only the initial and goal poses, without requiring a precomputed reference trajectory. A centralized box-level MPC optimizes contact forces while enforcing a control-density constraint for goal convergence and obstacle avoidance. Each robot then solves its own distributed robot-level whole-body MPC, under a stated shared-information assumption, to track its moving contact location while accounting for static obstacles and the time-varying positions of neighboring robots. The approach is evaluated in MuJoCo using whole-body contact dynamics for two and three Unitree Go2 quadrupeds collaboratively pushing rigid objects through narrow passages. Comparisons with matched Control Barrier Function and RRT* based tracking baselines demonstrate the effectiveness of the proposed density-based formulation for push-only, force- and torque-coupled manipulation tasks. Implementation videos are available at https://jaggu2606.github.io/go2-density-mpc-pushing/
manipulationquadruped - arxiv:2610.08432 · cs.AIEMHO: EMbodied Agent Harness Optimization via Experience TracesHyun Jung Lee, Jungtaek Kim, Jongwon Jeong, Tae-Eui Kam +2
Improving embodied agents often focuses on optimizing the underlying model through training, while the surrounding agent harness that controls planning, context, and tool use is typically engineered. We ask whether this harness can instead improve itself directly from experience traces under sparse environmental feedback. We propose EMbodied Agent Harness Optimization (EMHO), a self-evolving framework that keeps the embodied model frozen and iteratively revises its harness by analyzing execution trajectories and prior harness history. EMHO optimizes beyond skills or recovery prompts, modifying how the agent monitors progress, uses vision tools, grounds observations, and responds to failures. To support multiple subtasks with a single harness, we introduce EMHO-Merge, which addresses trade-offs in jointly optimizing a single shared harness across subtasks by using episode-level gains and losses to guide evidence-supported refinement of when and how revised behaviors are applied. We evaluate EMHO on EmbodiedBench across navigation and manipulation tasks, and EMHO consistently improves task success for both Qwen 9B and 27B models. Qualitative analysis shows that EMHO goes beyond recovering from failures and unproductive actions to reshape how the embodied agent interprets and interacts with its environment.
embodiedmanipulationagentembodied agenttool useself-evolving - arxiv:2610.08430 · cs.AINeMo-DCR: Bit-Exact Delta-Compressed Refit for Scalable Agentic RL at Trillion-Parameter ScaleSonglin Jiang, Zhiyu Li, Terry Kong, Yu Yao +4
Agentic reinforcement learning (RL) disaggregates training from rollout, so each policy update must reach the rollout clusters before the next batch. Transferring a full 1T checkpoint for such weight synchronization (refit) takes 87.5 min between two AWS regions. Measurements of BF16 training show that about 1% of weights change their stored values per step. Recent systems exploit this sparsity but fall short on placement, exactness, or efficiency: they reimplement placement rules, assemble full tensors, rebuild values arithmetically, or use a cross-cluster collective, and none fully recovers from mid-refit failures. We present NeMo-DCR (Delta-Compressed Refit), which sends only changes yet is bit-exact: receivers obtain the same parameter and buffer bits as a dense refit. For placement, fixed affine mappings project changes from training shards into the checkpoint's canonical coordinates, residual conversion covers the other changes, and the serving runtime's native loader places all changes in receiver storage. For exactness, compressible XOR masks carry affine changes whose projection and loader preserve stored bits, and overwrites carry the others. Receivers apply both in place, retries overwrite partial writes, and a joint commit binds the policy to the baseline for the next delta. For efficiency, object storage or a relay tree streams payloads during delta construction, without a cross-cluster collective. Even at 3% and 5% change rates, NeMo-DCR refits of 30B-1T models are 12-40$\times$ faster than a transport-only full-checkpoint reference. A 1T relay-tree refit at 3% takes 150 s instead of 87.5 min, making refits practical for cross-cluster agentic RL at trillion-parameter scale.
agentic - arxiv:2610.08425 · cs.ROMIM-VLA: Learning Physical Interaction Representations from Gripper Motor FeedbackJaeyoung Lee, Jiyeon Koo, Taehwa Kim, Yerin Cha +1
Vision-language-action (VLA) policies infer grasp actions primarily from visual observations and robot state, but do not explicitly represent the physical response observed after contact. We present MIM-VLA, a motor-feedback-based architecture that encodes recent gripper current, position, velocity, and signal validity as a 128-dimensional interaction token. A motor-only Motor Interaction Module (MIM) is pretrained with human-reviewed contact and interaction-phase labels and then conditions only the gripper-action pathway of SmolVLA; arm actions and the position-control interface remain unchanged. The same token supports the MEM selector VLM that compares candidate interactions and produces evidence-conditioned selections and explanations. We evaluate MIM-VLA in three real-world settings: comparing the interaction resistance of visually different objects, disambiguating visually similar real and replica objects through active probing, and gently grasping fragile objects, including held-out instances. Across 13 object pairs, MIM-VLA selects the higher-resistance object in 75.0% of trials, compared with 48.8% for the SmolVLA baseline. For the evaluated tasks, the approach uses motor feedback already available from the gripper and does not require an additional tactile array, force-torque sensor, calibrated force estimate, or direct current control.
vision-language-actiontactilegrippergrasp - arxiv:2610.08421 · cs.ROPost-Grasp Kinematic Repair for Robotic Insertion via Object-in-Gripper ReorientationHaegu Lee, Christoffer Sloth
A stable grasp does not guarantee kinematically feasible robotic insertion because the object-in-gripper transform may force the robot towards singularities or joint limits along the prescribed insertion path. We study post-grasp kinematic feasibility repair through object-in-gripper reorientation. Given an achieved grasp and a fixed insertion path, we seek a small reorientation that restores kinematic feasibility. Sequential IK can miss such candidates by following an unfavorable joint-space path, while the nonsmooth feasibility landscape makes the search computationally expensive. We evaluate candidates using a branch-aware IK graph that maximizes the minimum feasibility margin over the discretized insertion path and use a learned task-conditioned prior to improve query ordering. The selected reorientation is executed through tactile-based extrinsic manipulation. In UR5e simulations, the planner without learned ranking reduces mean reorientation over successful trials by 51.5% compared with grid-based sequential IK. Adding learned ranking reduces this planner's mean planning time by an additional 51.1%. Real-robot experiments validate the complete pipeline.
manipulationtactilegrippergrasp - arxiv:2610.08418 · cs.CVFrom the Drosophila Visual Connectome to General-Purpose Computer VisionZongyu Li, Akito Yamauchi, Huaizhi Liu, Vishwanatha Rao +3
Biological connectomes encode structured solutions to visual computation that may provide reusable inductive biases for artificial vision. We develop ConnectomeX around FlyVision, a trainable architecture that preserves parallel ON/OFF processing, recurrent computation and population-level graph interaction while scaling model capacity across tasks. FlyVision reached 99.34% accuracy on MNIST with 80,608 parameters and 78.03% on CIFAR-10 with 81,408 parameters. On ImageNet-1K, FlyVision Base and Large reached 60.79% and 66.25% top-1 accuracy with 1.8 and 3.7 million parameters, while a Large local-k7 model with a learned low-frequency branch reached 66.53%, compared with 69.25% for ResNet18 with 11.7 million parameters. On a 22-class skin-disease benchmark, FlyVision Large achieved 63.78% accuracy and 95.28% macro-AUROC with 2.99 million parameters. In four-class chest radiography, ImageNet-pretrained FlyVision Base and Large reached 92.60% and 92.76% accuracy with 1.33 and 2.97 million parameters, compared with 91.56% for ImageNet-pretrained ResNet18 with 11.18 million. BrainAGE extends FlyVision to volumetric T1-weighted MRI by applying a shared ImageNet-pretrained FlyVision Large encoder to 24 sagittal, coronal and axial slices per scan and combining slice-level age estimates by confidence-modulated Gaussian voting. On 433 held-out scans, three-axis fusion achieved a mean absolute error of 5.98 years and R^2 = 0.868. Across the 224x224 classification tasks, the best FlyVision configuration remained within three percentage points of ResNet18 on ImageNet-1K and skin-disease classification and exceeded it on chest radiography with substantially fewer parameters. These results show that a conserved connectome-informed computation can scale from compact recognition to large-scale natural and biomedical vision.
benchmark - arxiv:2610.08413 · cs.LGKnowing When Not to Answer: Cross-Domain and Multi-Turn Generalization of Latent Underspecification SignalsJerzy Kamiński, Ilya Galyukshev, Artem Kuznetsov, Danil Fedorov +5
Large language models routinely answer questions that cannot be answered from the information given, and in dialogue they answer before enough has been said. Unanswerability is linearly decodable from hidden states, but it is unclear which of its forms share a representation and whether the signal is useful in dialogue. We contribute a turn-labeled multi-turn benchmark (423 conversations, 1,661 labeled turn-states) and an evaluation harness with a simulated user who answers clarifying questions, and use them with six datasets and six open-weight LLMs to test how far probes for unanswerability carry. Probes transfer robustly between datasets that share a ground of unanswerability: missing information in math (AUROC 0.77-0.97) and in a passage (SQuAD 2.0<->MuSiQue, 0.77-0.90). Probes for epistemic "known-unknowns" transfer poorly to math, but this separation weakens under lexical controls and changes with layer and coordinate system, so it remains unresolved. Single-turn probes fail zero-shot to detect when a conversation becomes answerable; in-structure probes recover it, but no better than a bag-of-words classifier. A gate on the calibrated probe, with no model fine-tuning, fires on underspecified turns far more precisely than chance, and its end-task success comes within 0.08 of a gate given the true labels. Yet across four models it does not reliably beat vanilla generation or prompted consolidation. The remaining gap lies mostly in how models use a clarification, not in detection.
benchmark - arxiv:2610.08403 · cs.LGSSR: Sparse Segment Reduction for Ternary GEMM AccelerationAdeline Pittet, Shien Zhu, Valérie Verdan, Gustavo Alonso
Large Language Models (LLMs) require substantial computational resources, limiting their deployment on resource-constrained hardware. Ternary LLMs mitigate these demands through weight quantization via ternary values, achieving significant compression often with 50-90% sparsity. However, existing approaches have limitations: methods optimized for ternary weights, such as BitNet, redundant segment reduction (RSR), and its improved version RSR++, do not exploit sparsity structures, while conventional sparse formats neglect ternary characteristics, foregoing dual optimization opportunities. In this paper, we introduce Sparse Segment Reduction (SSR), a ternary matrix multiplication method designed to accelerate the inference of ternary LLMs and general Ternary Weight Networks (TWNs). SSR has a dedicated optimized ternary data format and an algorithm that systematically exploits sparsity patterns through computation trees that scale with the sparsity. SSR provides theoretical gains with asymptotically faster inference than RSR++ for sparsity above 50%, while practical evaluations reveal performance improvements across all sparsity levels. Evaluation results show that SSR achieves 2.1-11.3x speedup over RSR++ on ternary GEMM with 45-95% sparsity. Furthermore, SSR achieves 3.5-6.3x end-to-end speedup and 4.9% of memory saving over RSR++ on the Llama-3 1B model inference.
memory - arxiv:2610.08402 · cs.LGVETTA: Coordinating Turn- and Token-Level Credit Assignment for Multi-Turn LLM AgentsJiaju Chen, Min Yang, Jinghua Piao, Xiaochong Lan +3
Multi-turn LLM agents often receive sparse task feedback across several interactions, while generating each response token by token. This creates two related credit-assignment questions: which responses helped achieve the outcome, and which generation decisions mattered within each response? Existing methods typically focus on only one level: turn-level methods evaluate complete responses but do not distinguish the decisions within them; token-level methods can propagate feedback across turns but do not explicitly model credit for each response. These complementary limitations motivate learning credit at both levels and coordinating it in a single policy update. We introduce VETTA, a credit assignment method that jointly learns turn- and token-level values through separate heads on a shared lightweight critic. VETTA computes advantages along both temporal sequences and combines each turn advantage with a within-response-centered token residual for PPO updates. Furthermore, to reduce value-learning cost, the critic retains only early Transformer blocks from the pretrained checkpoint used to initialize the actor. On two challenging agent benchmarks, ALFWorld and WebShop, VETTA improves success rates over PPO by 37.5% and 22.3%, respectively, with Qwen2.5-1.5B-Instruct and achieves success rates of 95.5% and 76.0%, respectively, with Qwen2.5-7B-Instruct. Critic-depth comparisons further show strong task performance with substantially lower critic-side computation. These results suggest that a compact shared critic can coordinate turn- and token-level credit to improve agent performance while keeping value estimation efficient. Code is available at https://github.com/Jiaju-Chen/VETTA-official.
agentllm agentagent benchmarkbenchmark - arxiv:2610.08401 · cs.CVGeoPID: Decomposing and Steering Visual Information in Vision-Language ModelsSeulgi Kim, Zhixiong Zhang, Xinwei Zhang, Jie Ling +1
While recent vision-language models (VLMs) have shown outstanding performance across diverse applications, they tend to under-use visual information and over-rely on textual context. In this work, we propose \textsc{GeoPID}, a training-free framework that analyzes multimodal information within VLMs from a geometric perspective. \textsc{GeoPID} decomposes information into Redundant, Modality-Unique, and Synergistic components through the geometric relationships between visual and textual representation subspaces. Through an extensive analysis across 22 VLMs and 14 benchmarks, we confirm that correct predictions exhibit stronger vision-unique components when questions strongly require visual grounding. Building on this geometric analysis, we introduce a targeted intervention technique that selectively amplifies visual representations along the vision-unique subspace during inference. As a result, visual grounding capabilities were enhanced without any additional model parameter updates, achieving an average relative accuracy gain of 7.63\%.
benchmark - arxiv:2610.08398 · cs.CVUP-MOPD: Update Projection in Multi-Teacher On-Policy DistillationTaojie Zhu, Jing Jin, Yuan Xia, Chenyang Ding +7
On-policy distillation from multiple teachers combines expertise from different domains in a single student, but conflicting gradients can hinder this integration. Gradient corrections directly constrain parameter updates under plain SGD. With optimizers such as AdamW, however, momentum, adaptive scaling, and weight decay can turn a corrected gradient into an update that increases a domain loss to first order. To address this gap, we propose Update Projection for Multi-Teacher On-Policy Distillation (UP-MOPD). UP-MOPD lets the original mixed gradient update the optimizer state and generate a candidate displacement, then projects only violating candidates before they are committed to the parameters. The projection gives the unique feasible update closest to the candidate in Euclidean distance. In experiments combining medical and general domains, UP-MOPD improves IFEval-loose accuracy late in training by 2.96 points over vanilla M-OPD. It achieves an average score of 60.03 across eight metrics, compared with 59.00 for gradient projection and 59.15 for update rejection. On a public benchmark covering mathematics, code, and instruction following, it achieves the best average across six tasks (32.67), leads on LiveCodeBench v5, and ties for the best IFEval result.These results support projecting optimizer updates to reduce interference between domains.
benchmark - arxiv:2610.08388 · cs.AIForesight-over-Graph: Reasoning Beyond Local Horizons for Knowledge Base Question AnsweringYang Hong, Yajun Yang, Xin Wang, Liping Jing +1
Large language models (LLMs) have demonstrated strong capabilities in question answering, yet they still frequently suffer from hallucinations on knowledge-intensive tasks. Knowledge graphs (KGs) provide LLMs with structured, interpretable, and updatable factual grounding, making them a promising external knowledge source for reliable reasoning. However, existing LLM-guided graph reasoning methods typically rely on hop-wise greedy or beam-style pruning during evidence retrieval. Such local decision processes are inherently myopic: evidence that appears weak near the source may become crucial only after deeper graph context is explored, causing answer-critical branches to be discarded prematurely and making the reasoning chain difficult to recover. To address this limitation, we propose Foresight-over-Graph (FoG), a foresight-aware evidence retrieval framework for knowledge base question answering (KBQA). FoG iteratively constructs a question-relevant evidence subgraph and uses far-to-near feedback to guide path exploration, and maintains a compact memory subgraph to support continued exploration. Extensive experiments on widely used KBQA benchmarks demonstrate that FoG achieves state-of-the-art performance, with a particularly large improvement of 16.58% in Hit on CWQ, while also reducing LLM calls and token usage. Our code is available at https://github.com/yhong7/FoG .
memoryknowledge graphbenchmark - arxiv:2610.08381 · cs.ROFrom Legs to Wheels: Embodiment-Aware Human Motion Retargeting for Mobile-Base HumanoidsJiyeon Koo, Eunseom Pyo, Jeonghee Seo, Taehwa Kim +1
Human video offers a scalable source of robot demonstrations, yet most human-to-humanoid retargeting methods assume a legged robot with human-like kinematics. This assumption does not hold for mobile-base humanoids equipped with a wheeled base, vertical lift, and two arms. Human walking must be expressed through base motion, while torso bending may require coordinated lift and arm motion. We address this mismatch with a task-conditioned framework that assigns reconstructed human motion to base, lift, and arm responsibilities before robot-specific realization. The allocator preserves the human-derived path, stabilizes heading, separates turn and translation when needed, retimes commands to satisfy base limits, and repairs lift and arm trajectories. A deployment adapter then converts the reference to 50 Hz commands using stationary-base detection, deadband and slew-rate filtering, time-consistent playback scaling, and separate linear and angular gains. We evaluate the resulting references with human-derived task-space comparisons, policy-free simulation replay, and a qualitative execution on a physical robot.
humanoid - arxiv:2610.08367 · cs.LGEvolutionary One-Step Generators: Fast and Diverse Sampling for Discrete DesignMarcus Vukojevic, Erik Nielsen, Veronica Lachi, Andrea Passerini +1
Several discrete design tasks, such as molecular discovery, require diverse collections of useful candidates at low computational cost. High validity alone does not guarantee a useful candidate library: repeatedly generating the same valid structures leaves few distinct alternatives. Training for both feasibility and diversity is challenging because many relevant criteria can only be evaluated after hard decoding. To address this challenge, we propose EGO (Evolutionary Generators with One-step inference), a framework for training compact generators directly on discrete outputs. The method combines distribution matching with structural constraints and optional diversity or history-dependent rewards, using antithetic low-rank evolution strategies without requiring criterion-specific differentiable surrogates. Once trained, the generator produces the entire graph in a single neural-network evaluation. On molecular generation benchmarks, our compact generator achieves over $50\times$ the valid-and-unique yield per estimated dense operation compared to recent one-step flow-map baselines while retaining high chemical validity. In scaffold completion, EGO achieves an observed $44.3\times$ speedup over MoLeR in generation to SMILES and produces approximately $10\times$ as many filter-passing proposals within matched time budgets for generation and screening. Beyond chemistry, EGO produces $1.54\times$ as many distinct held-out elite architectures as relaxed gradient training on NAS-Bench-101. The low generation cost may enable real-time candidate generation across discrete design tasks, supporting interactive exploration of constrained design spaces and rapid construction of candidate sets for downstream evaluation.
benchmark - arxiv:2610.08364 · cs.AITransect: Retaining Observability for Long-Horizon LLM Agent EvaluationsToby D. Pilditch, Konstantinos Voudouris, Alexandra Abbas, Cozmin Ududec
Frontier AI evaluations increasingly use open-ended, agentic, long-horizon tasks whose transcripts can span hundreds of pages of outputs and actions from complex multi-agent networks. The observability envelop-the range of what evaluators can reliably infer about an agent's behaviours-is therefore narrowing. Language model assistants can help classify and interpret agent behaviour but also afford human evaluators significant analytical degrees of freedom, threatening the reproducibility and auditability of language-model-based transcript analysis. Transect is an open source package built on Inspect Scout to help evaluators understand how a long agent run unfolded, identify behaviour worth investigating, and check interpretations against the transcript. Users specify task context and behavioural vocabulary in a reusable evaluation-family configuration, with judge models and analysis settings supplied separately. Transect's navigable reports align recorded events, token use, sub-agent activity, and model-generated behavioural labels on a common turn-based timeline. Reviewers can quickly grasp a run's narrative, trace any label or event to its source turns, and export the underlying data tables for cross-run analysis. We demonstrate the workflow on an AI R&D evaluation that generated almost 13 million tokens, dividing the agents' work into behavioural phases aligned with research-skill classifications, sub-agent delegations and interactions, and token use. The combined view shows a focus on operational work and manuscript production, with little evidence of a sustained hypothesis generation stage-arguably a necessary component for high-quality scientific outputs. Transect's flexible, customisable transcript-analysis pipeline will enable evaluators to keep pace with longer, more complex, more frequent AI evaluations while supporting scientific rigour, transparency, and reproducibility.
graspagentllm agentmulti-agentagenticevaluator - arxiv:2610.08363 · cs.AIExplainable Failure Prediction and Prevention in MaritimeDionisis Kalogeropoulos, Georgia Sovatzidi, Panagiotis G. Kalozoumis, Dimitris K. Iakovidis
Maritime systems operate in highly dynamic environments where unexpected equipment failures can compromise safety, reliability, and operational efficiency. Recent advances in artificial intelligence (AI), machine learning, digital twins, and predictive maintenance enable proactive failure prediction and prevention. However, ensuring trustworthy and explainable decision-making remains a major challenge in safety-critical maritime applications. This chapter reviews key AI technologies required for explainable failure prediction and prevention in maritime systems and presents a conceptual architecture capable of supporting autonomous or human-in-the-loop corrective actions. This architecture integrates data acquisition, time-series forecasting, anomaly detection, risk assessment, decision-making, and explainable AI into a closed-loop framework. With reference to the architectural components, a review and discussion of relevant maritime studies is performed, outlining their methods, advantages, and limitations. Furthermore, it highlights current challenges, including uncertainty and robustness, model generalization, explainability, limited availability of maritime datasets, and operational deployment, and identifies future research directions toward trustworthy AI-assisted maritime decision-making.
human-in-the-loop - arxiv:2610.08358 · cs.CVTest-Time Adaptation of Quantized ViTs via Single-Pass Quantizer-Aligned RecalibrationHyeongheon Cha, Young D. Kwon, Sung-Ju Lee
Post-training quantization is a standard route to fitting vision transformers (ViTs) into edge compute and memory budgets, yet quantized models become especially brittle under distribution shift. Test-time adaptation (TTA) addresses such shifts without labels, but most existing approaches are poorly aligned with the constraints of quantized inference. Prevailing TTA methods recover accuracy through backpropagation, while backprop-free methods often still incur overhead from extra forward passes or parameter updates, and lightweight feature- or logit-level methods recover only part of the loss. Across these approaches, a quantization-specific failure mode that amplifies the drop is not directly targeted: under shift, activations occupy frozen quantizers' calibrated ranges differently, distorting their code distribution. We propose Quantizer-Aligned Recalibration (QuAR), a single-pass TTA method tailored to quantized ViTs that neither backpropagates nor updates any model parameters. QuAR recalibrates activations at the input to a frozen quantizer, mapping the test stream's running per-channel statistics back toward the source calibration. On ImageNet-C with ViT-B, QuAR achieves the highest mean accuracy among state-of-the-art backprop-free TTA methods at 3-, 4-, 6- and 8-bit weight/activation precision, outperforming the strongest baseline by 2.28 points at 8 bits and 4.00 at 3 bits, with 46% lower latency and a memory overhead of only 0.17 MB (0.01% of peak inference memory). Analysis and diagnostics trace the gain to a reduced per-channel mismatch at these quantizers, which restores the code distribution the baselines leave unchanged or distort further. A single fixed configuration remains ahead across continual streams, non-i.i.d. label shift, seven out-of-distribution suites, and three other backbones.
memorypost-training - arxiv:2610.08350 · cs.ROHow Much Planning Is Enough? Reducing Search and Computation in World-Model PlanningChangbai Li, Sirui Li, Yichen Yang, Tongfei Chen +3
Visual world models enable goal-directed control through decision-time action search, but their deployment efficiency is often limited by conservatively large planning budgets. We show that competitive task performance can be achieved without agreement with the Full-budget action, that sufficient budgets vary across model--task pairs, and that iterative planners repeatedly encode solve-invariant context. To address these inefficiencies, we propose {SufficientPlan}, a simple deployment framework that requires no modification to pretrained world models or planner updates. Its {Paired Sequential Budget Certification (PSBC)} component uses paired closed-loop evidence to search for and certify a reduced model--task-specific budget within a predefined Full-performance tolerance. Its {Static-Context Reuse (SCR)} component caches observation and goal representations across search iterations while preserving candidate-dependent planning and selected actions. Experiments across multiple world-model backbones and visual-control tasks show that SufficientPlan substantially reduces search budgets and planning latency while maintaining competitive control performance.
world model - arxiv:2610.08347 · cs.MANetwork Intervention by Polling Strategic AgentsChenyu Zhang, Rohit Parasnis, Saurabh Amin
A planner in a network of strategic agents faces three entangled challenges: the optimum depends on agents' private information, queried agents may misreport to steer the outcome, and exact computation does not scale. We study these challenges in multi-activity network games with heterogeneous private technologies, in which the planner sets non-discriminatory prices. We show that the optimal prices admit a centrality-based decomposition of the welfare kernel: each agent's contribution scales with its squared centrality in a network reweighted by agents' preferences across activities. This decomposition motivates Poll, a polling algorithm in which the planner samples one agent per round, walks briefly through the agent's neighborhood, and updates the price from a local report. From the same decomposition flow three forms of efficiency: computationally, Poll uses significantly fewer operations than exact computation and other distributed methods, requiring up to three orders of magnitude less communication on a real-world network with over 300,000 agents; statistically, its query complexity scales with topology and preference heterogeneity rather than explicitly with population size; and economically, it converges to welfare-maximizing prices while admitting behavior-specific implementations that induce truthful reports and detect adversarial deviations.
agent - arxiv:2610.08346 · cs.CVPolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes EstimationBeibei Lin, Tingting Chen, Xin Zhang, Wenhao Zhao +2
Polarization imaging provides physical cues beyond intensity imaging but typically requires specialized hardware. Recent methods infer polarization from RGB-like inputs, yet predict only normalized Stokes components or relative descriptors, from which the radiometric scale needed for full Stokes reconstruction has been divided out. We introduce PolarScale, a benchmark that makes this scale an explicit prediction and evaluation target. Built on existing trichromatic full-Stokes measurements, PolarScale takes the per-scene normalized total-intensity image $s_0$ (a scene-referred linear image, not a consumer sRGB photograph) and asks models to predict normalized Stokes components, AoLP/DoLP/DoCP, and a per-scene scale. Because the scale is divided out of the input, it is not physically identifiable; PolarScale therefore evaluates dataset-conditioned semantic scale estimation against a constant-scale control, together with angular, self-consistency, and physical-bound metrics. Across seven restoration-based and generative backbones and three prediction strategies, the strongest restoration models estimate the scale with 3.6-4.3% mean relative error versus 5.7% for the constant control and violate physical bounds on fewer than 0.25% of pixels, whereas two generative baselines collapse to a near-zero scale; explicit descriptor supervision improves descriptor accuracy (23.66 vs. 18.88 dB PSNR for MAE). Predicted full-Stokes representations improve diffuse/specular separation, material segmentation, and glare classification, although in diffuse/specular separation the learned scale performs only on par with the constant control.
benchmark - arxiv:2610.08344 · cs.ROEvent-Driven Proactive Robot Assistance through Vision-Language ReasoningFengkai Liu, Hao Su, Haozhuang Chi, Rui Geng +5
Assistance in collaborative manipulation is often initiated by user instructions, making high-level reasoning request-driven. In fluent human teamwork, however, partners often infer the next helpful step from the observed outcome of an action rather than waiting for instructions. Motivated by this, we investigate an event-driven formulation of proactive assistance, where human--object interaction outcomes initiate assistive reasoning without user-provided task specifications at inference time. To this end, we propose an event-driven framework that monitors workspace state changes with an event monitor and, upon event completion, extracts stabilized pre/post snapshots that characterize the resulting state transition. A frozen pretrained Vision-Language Model (VLM) then uses its semantic priors to infer the task context, decide whether assistance is appropriate, and, when needed, generate a sequence of assistive actions from the observed transition. To make outputs executable and verifiable, we restrict actions to a set of action primitives and reference objects via integer IDs.We evaluate the same framework across three distinct real world tabletop collaboration tasks without task-specific training or fine-tuning. The event-driven framework achieves performance comparable to variants given user instructions.
manipulation - arxiv:2610.08339 · cs.CVDigital Twin-Driven Real2Sim2Real: Simulator-Conditioned Generation via Paired Driving-Scene ReconstructionHojun Lim, Hyeongseok Jeon, Donghyun Kim, Soonyoung Jung +1
Camera-based 3D perception for autonomous driving relies heavily on large annotated datasets, and deploying such a system to a new target region typically requires data collection and annotation. Generative augmentation has been proposed to reduce this cost, but existing approaches face a fundamental trade-off: label-conditioned methods consume the very annotations they aim to replace, while simulator-conditioned methods offer free annotations but lack visual grounding to specific real environments. This work investigates the extent to which a digital-twin-driven Real2Sim2Real pipeline (DT-R2S2R) can substitute for target-region real data. By reconstructing recorded driving clips inside a georeferenced digital twin (DT-R2S), we condition a diffusion model on geometrically aligned simulator renderings, establishing a digital twin-grounded Sim2Real model (DT-S2R). As a result, DT-S2R synthesizes photorealistic driving images given low-cost yet georeferenced simulator data across both reconstructed and novel simulator scenes within digital-twin coverage. The efficacy of generated data is verified on diverse 3D detectors. DETR3D, especially, reports 93.18% of mAP obtained by a target-region real-data oracle, without employing target images for detector training. Furthermore, simple co-training with existing out-of-target real data outperforms the oracle. Thus, DT-R2S2R can substantially reduce the cost of manual on-site data collection and annotation in digital twin-available districts, providing a practical foundation for scaling 3D perception.
sim2real - arxiv:2610.08337 · cs.LGMachine Learning for German Redispatch Forecasting under Data Delays and Temporal Distribution ShiftFaraz Shamim, Faris Shamim
Public redispatch records provide empirical data for grid congestion forecasting, but delayed reporting, zero-inflated distributions, and temporal shift present major modeling challenges. We assess the accuracy and reliability of probabilistic machine-learning forecasts using published German transmission records under experimentally imposed information-age constraints. The benchmark evaluates eight daily series of upward and downward intervention energy across four German transmission system operators from 2021 to 2024 (48,242 eligible records; 354 evaluation dates in 2024). We compare seasonal empirical, regularized autoregressive (ARX), quantile LightGBM, GRU, and Transformer models under a minimum seven-day target-latency constraint. Neural architectures use a zero-censored output head to accommodate exact-zero outcomes. Static, rolling, and adaptive delayed-feedback calibration are evaluated using normalized weighted interval score (nWIS), empirical coverage, and block-bootstrap inference. Raw LightGBM achieved nWIS 0.7952, outperforming ARX (1.0604) and the seasonal baseline (0.8739) by 25.0% and 9.0%, respectively (Holm-adjusted p<0.005). Rolling calibration improved LightGBM to nWIS 0.7767 versus 0.8251 for static calibration (p=0.0092), with 91.81% coverage for nominal 90% intervals. The zero-censored Transformer achieved nWIS 0.8161, with no significant difference from LightGBM (p=0.260). However, aggregate coverage concealed substantial undercoverage during high-volume interventions (61.91% coverage among above-threshold events). These results show that boosted-tree models with rolling calibration provide accurate probabilistic forecasts of aggregate redispatch volumes under target delays, while nominal aggregate validity does not ensure reliability during extreme congestion events.
benchmark - arxiv:2610.08329 · cs.AIAn AI-Assisted Formalization of the Poincaré ConjectureZhiyuan Zhang, Axel Delaval, Leheng Chen, Jinxuan Chen +5
We present an AI-assisted Lean 4 formalization of the Poincaré conjecture. The project began with limited reusable formal infrastructure for the geometric analysis behind the proof. To organize this work, we combined a proof blueprint prepared by mathematicians with explicit milestone statements. These milestones enabled parallel agent work and gave mathematicians clear points to locate blockers and provide effective mathematical guidance. Our analysis identifies the human interventions and organizational choices behind this workflow. The project provides a starting point toward reusable infrastructure for future formalization projects; such infrastructure, once developed, could eventually reduce the cost of verifying mathematical results in geometric analysis.
agent - arxiv:2610.08327 · cs.AIMedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge AccumulationXilin Dang, Weilin Ruan, Xue Yang, Jinghao Wang +3
Large language models (LLMs) have shown promise in medical question answering and clinical reasoning, yet their improvement remains constrained by static parametric knowledge and costly expert supervision. Self-evolving agents offer a promising alternative by enabling models to improve through iterative task generation and problem-solving. However, most existing self-evolving methods are designed for easily verifiable domains such as mathematics and coding, where solutions can be checked by exact answers or executable programs. Medical reasoning is fundamentally different: it is open-ended, knowledge-intensive, and often only partially verifiable. We present MedZERO, a self-evolving framework for open-ended medical reasoning. MedZERO couples an Examiner that generates frontier medical question-option pairs with a Reasoner that solves them through evidence-grounded multi-turn reasoning with external knowledge tools. To support reliable, continual improvement, MedZERO adopts controlled knowledge accumulation, which maintains temporary exploratory knowledge and curated persistent knowledge in reasoning. We evaluate MedZERO on five public medical reasoning benchmarks using 4B- and 8B-scale base models under open-ended evaluation. Across all settings, MedZERO consistently outperforms the underlying base models and prior self-evolving baselines, achieving up to 13.7 average accuracy-point gains over the next-best self-evolving baseline.
self-evolvingbenchmark - arxiv:2610.08322 · cs.LGStructure-Aware Graph Abstention for Reliable Selective ForecastingJianxiang Xie, Belal Alsinglawi
Selective forecasting abstains on high-risk test windows under a retained-coverage budget. Existing gates such as TEM (Brusokas et al., 2025) score each forecast as a whole; for multivariate outputs, trajectories can look plausible while violating dependencies among variables. We treat instance-level plausibility and relational consistency as distinct reliability axes and operationalize the latter via a learned sparse graph and a Dirichlet-style structural energy E_struct, trained with error-weighted graph regularization and score-error alignment. On seven long-horizon benchmarks and four backbones, structural gating often reduces selective MSE versus TEM at matched coverage, with the largest gains where cross-variable structure appears more informative in our benchmarks; gains are not universal, indicating a complementary abstention signal. Table 1 is a Protocol A ranking diagnostic (seed 2024); three-seed deployable Protocol B on an aligned subset is in Table 3 (full validation-to-test grids: Appendix A).
benchmark - arxiv:2610.08320 · cs.ROHumanoid Horizon: Extending Task Horizon in Whole-Body Loco-Manipulation via Parallel Training, Dynamic Starting, and Reward GatingHaozhuo Zhang, Qiang Zhang, Jian Tang, Mingzhe Ni +3
Cluttered indoor environments, where large and heavy objects are scattered across diverse surfaces, require humanoid robots to sequentially navigate, grasp, transport, and accurately place each item at its target location within a single uninterrupted episode. This long-horizon, whole-body loco-manipulation task remains a significant challenge for current methods. Previous approaches often suffer from two main issues: easy-reward bias, where training overemphasizes early transport stages at the expense of later ones, and catastrophic forgetting, where focusing on later stages leads to a decline in earlier-stage performance. In this work, we introduce Humanoid Horizon, a unified policy framework designed to overcome these limitations through three interrelated mechanisms. The Parallel Training Strategy organizes $N$ scenes into $S$ concurrent stage streams governed by a shared policy, ensuring all transport stages receive continuous gradient updates and removing the bottleneck of sequential optimization. The Dynamic Starting Mechanism updates each environment's initial state with terminal states from upstream rollouts, gradually broadening transition coverage and enhancing robustness at stage boundaries. Reward Gating sets the reward to zero for the rest of the episode in later-stage streams when the immediately preceding object is displaced beyond a set threshold, so the shared policy learns not to disturb a just-placed object and earlier placements are preserved throughout the episode. Collectively, these strategies achieve per-stage success rates exceeding 80\% on the two-object LHM-Humanoid benchmark (350 training scenes, 66 held-out scenes). As the number of sequentially transported objects grows beyond two, success declines with the horizon, but the degradation is graceful relative to the sharp drop seen in all baselines.
manipulationhumanoidgraspbenchmark - arxiv:2610.08315 · cs.CVCatastrophic Forgetting in Sequential Thermal Anti-UAV Detection: The Role of Scale-Conditioned Gradient ImbalanceKhac Duc Giang Nguyen, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor Alsahag
Counter-UAV systems based on thermal infrared detection must stay accurate as operational datasets evolve, yet sequential fine-tuning causes catastrophic forgetting of prior tasks, a problem that remains insufficiently characterized in this domain. This continual-learning study measures the stability-plasticity trade-off in YOLOMG, a YOLOv5-based detector run as a single thermal-infrared stream with the motion channel disabled, trained sequentially across three anti-UAV benchmarks of rising scale difficulty: Anti-UAV-RGBT, Anti-UAV410, and CST Anti-UAV. Naive fine-tuning on CST yields a Forgetting Measure of -0.605 against the Stage 1 ceiling, corresponding to a 90% capability loss, with -0.572 occurring in Stage 3 alone. In contrast, knowledge distillation from a frozen teacher is associated with FM = -0.033 +/- 0.004 across three seeds, corresponding to 95% retention. Because no Stage 2 no-KD control is included, this result establishes retention under KD training rather than a causal KD effect. Per-stratum analysis shows large-target detection collapsing to near zero within the first epoch, despite an inter-stage cosine similarity of 0.987 over the gradient-updated weights, pointing to scale-conditioned gradient imbalance, rather than weight drift, as a candidate mechanism. Scale-Stratified Herding (SSH), a 300-exemplar buffer balanced across four UAV size strata, roughly halves the forgetting (FM = -0.605 to -0.311) and keeps large-target detection non-zero. An ablation attributes the gain primarily to scale stratification rather than herding: random-stratified replay performs at least as well (FM = -0.221 versus -0.311 for SSH). These replay results are single-seed and should therefore be treated as preliminary.
benchmark - arxiv:2610.08312 · cs.LGCoDe-LoRA: Mitigating the Orthogonality Dilemma in Continual Learning of LLMs via Knowledge Consolidation and DecouplingMaoqi Liu, Quan Fang, Yufei He
Continual learning (CL) is essential for Large Language Models (LLMs) to sequentially adapt to evolving tasks. To mitigate catastrophic forgetting, recent advances implement low-rank adaptation with orthogonal projections (e.g., O-LoRA) to isolate task parameters. However, we reveal that such strict geometric constraints trigger an "Orthogonality Dilemma": rigid parameter isolation impedes the transfer and accumulation of shared representations across semantically related tasks. In this work, we propose a new replay-free method, called Consolidation and Decoupling LoRA (CoDe-LoRA), for CL of LLMs. CoDe-LoRA disentangles the learning process into Consolidating Universal Knowledge and Decoupling Task-Specific Knowledge. To achieve this, CoDe-LoRA leverages an adaptive null space projection mechanism and semantic routing to balance knowledge accumulation with task-specific adaptation. Experimental results across four backbones and three CL benchmarks show that CoDe-LoRA achieves the best average accuracy. Our code is available at https://github.com/Estrellajer/CoDe-LoRA.
benchmark - arxiv:2610.08311 · eess.SYDistributed Nash Equilibrium Seeking for Open Multi-Coalition Games: A Mass-Preserving Gradient-Tracking-Based AlgorithmDaning Lei, Jiamin Wang, Jian Liu, Feng Xiao +1
This paper studies distributed information aggregation and Nash equilibrium seeking over open multi-coalition networks, where both agents and coalitions may dynamically enter and leave the network. The varying network population poses a fundamental challenge to conventional gradient-tracking methods, as agent departures may cause the loss of gradient information required for distributed aggregation. To overcome this issue, a mass-preserving gradient-tracking method is designed, in which the gradient information carried by departing agents is redistributed to the remaining agents within the same coalition. The proposed method preserves the aggregate gradient information of the coalition objective over the intra-coalition communication network and achieves gradient tracking under dynamic population changes without imposing additional initialization conditions beyond those of conventional gradient-tracking methods. Based on the proposed gradient-tracking mechanism, a distributed Nash equilibrium seeking framework is developed, and its convergence is established under both uncoordinated fixed and diminishing stepsizes. Furthermore, to alleviate the slowdown of convergence caused by classical diminishing stepsize schemes ($\frac{η_0}{t}$, where $η_0>0$ is a constant), an exponential-interval diminishing stepsize scheme is designed based on the agents' exploration intervals. Finally, a numerical simulation based on an open connecting control game demonstrate the effectiveness of the proposed information-tracking and Nash equilibrium seeking framework.
agent - arxiv:2610.08303 · cs.CLLanguage Unalignability: Why Some Concepts Resist Cross-Cultural Benchmark EvaluationShu-Kai Hsieh, Da-Chen Lian
Current evaluation of multilingual Large Language Models (LLMs) rests on an implicit Translation-Isomorphism Assumption (TIA): that semantic structures across languages are congruent and mutually mappable without loss of information. We argue that this assumption is not merely violated in practice, but ill-posed in principle for a typologically identifiable class of concepts, including pragmatic markers, honorifics, and diachronically stratified terms. We formalize this failure using a usage-cloud framework, representing concepts as point sets of contextualized embeddings. We define $α$-unalignability as the impossibility of any mapping that simultaneously preserves lexical faithfulness (centroid correspondence) and structural faithfulness (local neighborhood topology). We provide three layers of evidence. Behaviorally, we show that FLORES-200 translation failures are predicted by language family and resource class but not by script, and that LOBSTER reasoning scores vary by family. Mechanistically, we report a Representation-Intervention Gap (RIG) in a nine-model case study on Yami: the models' activations encode a regularity along which Yami groups with other low-resource and Austronesian languages, yet interventions on language-specific neurons show no demonstrated advantage over random masks: the regularity is visible but not usable by this intervention. Finally, we operationalize these findings into a multidimensional diagnostic profile: Cycle-Consistency, Pragmatic-Load Disagreement, Manifold-Curvature Mismatch, and RIG. We argue that collapsing cultural competence into a single scalar incentivizes "probabilistic flattening," and that recognizing the unalignable class is a precondition for AI that respects, rather than erases, cultural divergence. This suggests that multilingual alignment is not a single well-defined objective, but a set of mutually incompatible projections.
benchmark - arxiv:2610.08300 · cs.CLMemory Depth and Reconstructed Context Width: A Controlled Evaluation of Hierarchical RetrievalMichael Andreev
Long-term conversational memory is becoming an integral component of modern LLM systems. Proposed architectures group records by topics and events, construct hierarchies and graphs, and connect facts through causal and temporal relations. We experimentally study the interaction between two memory parameters: structural depth and the width of context supplied to the answer model. Using EverMemBench, we evaluate depths D1-D4, core budgets of 1,024/2,048/4,096 tokens, and additional Production and Oracle conditions up to the full archive. Increasing width from 1K to 4K improves Accuracy by 10.11-17.98 percentage points, whereas increasing depth provides no monotonic gain. Beyond 8-16K, Production performance reaches a plateau while tokens per correct answer continue to increase; Oracle preserves quality on full archives of 68-71K tokens. These results motivate further investigation of large, coherent context blocks instead of progressively deeper memory structures.
memory - arxiv:2610.08297 · cs.ROMitigating Concept Drift in QoS Prediction for Teleoperation of Autonomous Vehicles Using Historic DataXiyan Su, Jianning Gao, Mahmoud Ashri, Frank Diermeyer
Teleoperation serves as the fallback solution to autonomous driving but reliable functions of the teleoperation require a certain amount of mobile network resources, which cannot be guaranteed at all times. Therefore, predictive quality of service (pQoS) is introduced as a concept to increase the resilience of the teleoperation. In this paper, based on a data measurement campaign, we propose a prediction framework to prediction two important network KPIs of teleoperation: uplink data-rate and round-trip latency. Furthermore, we introduce a method to alleviate the performance degradation of machine-learning-based prediction models on previously unseen data due to concept drift by incorporating historic data into the prediction pipeline. Additionally, we introduce the metric of critical scenario detection to evaluate the prediction performance specifically for teleoperation.
teleoperation - arxiv:2610.08292 · cs.LGWhere Do Two Populations of Persistence Diagrams Differ? Calibrated Local Inference at a Fixed BudgetPramita Bagchi, Edward Bae, Atish Mitra, Alexander D. Silberman +2
Many two-sample tests for populations of persistence diagrams assess global differences without identifying the regions of the birth-death plane that contribute to them. We study simultaneous inference for local mean contrasts when the number of available diagrams is fixed. They are differences in expected weighted feature mass within $\ell_\infty$ neighborhoods at several centers and radii. We estimate these contrasts using additive landmark responses. A Gaussian multiplier bootstrap calibrates simultaneous confidence intervals while allowing unequal group covariances. The neighborhoods whose intervals exclude zero form a map with approximate family-wise error control, and selecting a subset of original intervals for display preserves their joint coverage guarantee. On the simultaneous coverage event, every reported neighborhood lies within twice its radius of the support of the mean-measure difference. A geometric result gives sufficient radius conditions for a displaced feature to produce a nonzero contrast. A comparison of sufficient detection thresholds quantifies the tradeoff between reducing the number of tested coordinates and reserving observations for an independent pilot. In simulations with 40 to 120 diagrams per class, the bands achieved 94%-98% simultaneous coverage under both the strict null and equal means with unequal covariances. In the latter setting, a permutation maximum and the pooled-t implementation of the two-stage persistence-image test of Moon and Lazar rejected in up to 32% and 26% of runs, respectively. In the fixed-budget simulations, spending a third of the observations on a pilot to choose landmarks or radii located changes less often than a prespecified grid at a single radius. On the MUTAG benchmark, the localized region concentrates on rings of fused-ring systems, an exploratory reading.
benchmark - arxiv:2610.08258 · cs.AIzkLLMPoT: Efficient Zero Knowledge Proof of Training for Large Language ModelsJunkai Liang, Zhanpeng Guo, Pengfei Wu, Qingni Shen +4
Auditing the claimed outcomes of large language model (LLM) training is challenging when model weights and training data are private, while cryptographically proving the full training process is prohibitively expensive at Transformer scale. We present zkLLMPoT, a zero-knowledge framework that certifies auditor-defined properties of a trained checkpoint through forward evaluation rather than verification of its optimization trajectory. zkLLMPoT includes 2 phases: 1) The trainer fixes the architecture and the model weights are committed. Then the auditor selects challenge sequences, preventing the trainer from modifying the checkpoint in response to the audit data. 2) Then the trainer proves the objective value attained by the committed model on those sequences. This formulation makes the certification cost independent of the number of training iterations, without revealing model weights or requiring access to private training data. We build on sumcheck- and lookup-based arguments to certify Transformer computations, while supporting next-token loss and task-specific audit objectives. Across four model families, operator-level benchmarks yield proving times of 41-59 seconds for 1.1-1.5B-parameter models and 131 seconds at 13B for the covered operators, with verification below half a second at a sequence length of 512.
benchmark - arxiv:2610.08250 · cs.AIMASC: A Multi-Agent Self-Calibration Framework with Latent Construct Alignment for Consistent Client Role-Playing in Psychological CounselingShixin Peng, Kun Jiang, Jiaxing Zheng, Qihao Yang +1
Large language models are increasingly used to simulate clients for counselor training and psychological counseling research, but reliable simulation requires clients to remain psychologically coherent across extended interactions. Existing role-playing methods largely rely on static profile prompts and may exhibit persona drift, unrealistic cooperativeness, or inconsistent psychological states, communicative actions, and emotions. Existing evaluations also lack a unified testbed for both stable client characteristics and evolving psychological dynamics. We propose MASC, a Multi-Agent Self-Calibration framework with latent construct alignment for consistent client role-playing in psychological counseling. MASC combines construct-guided generation, collaborative refinement, consistency verification, and memory-based revision in a closed calibration loop that detects and corrects inconsistencies as dialogue unfolds. We further introduce CRPC-Bench, a benchmark covering session-level profile information and Big-Five personality traits, as well as turn-level psychological state, communicative action, and emotion expression. CRPC-Bench contains 38 motivational interviewing client profiles augmented with personality and emotion annotations. Experiments show that MASC outperforms existing methods across profile, personality, receptivity, and turn-level consistency, with the heterogeneous configuration achieving the strongest overall performance. MASC and CRPC-Bench provide a unified foundation for developing and evaluating psychologically coherent client simulations for AI-assisted counseling research and training.
multi-agentbenchmark - arxiv:2610.08246 · cs.LGLeanPlan: Optimal Planning with LLM-Generated Heuristics and Admissibility ProofsAndré G. Pereira, Augusto B. Corrêa, Felipe Meneguzzi, Jendrik Seipp
Frontier large language models (LLMs) can generate heuristic functions that guide search to achieve state-of-the-art performance in satisficing planning, where any plan is acceptable. However, these heuristics are not guaranteed to be admissible and can lead to suboptimal plans. We introduce LeanPlan, the first planning system that finds optimal plans with LLM-generated heuristics whose admissibility is machine-checked. Given a domain description and training tasks, an agentic loop uses planner feedback to iteratively improve a reusable domain-specific heuristic, its admissibility proof and the required domain assumptions. LeanPlan implements the heuristic, its proof and an efficient planner with machine-checked grounding and search in Lean 4. We evaluate LeanPlan on ten domains from the International Planning Competition and three new domains, using test tasks with up to 57 times as many objects as the training tasks. With GPT-5.6 Sol in the agentic loop, we successfully generate heuristics and admissibility proofs for all these domains. With the resulting heuristics, LeanPlan usually expands fewer states than the state-of-the-art Scorpion planner and solves more tasks overall.
agentic - arxiv:2610.08244 · cs.AISensor-Language-Action ModelsYuekai Xu, Zitao Shuai, Yuzhe Yang
Sensors are useful not only for understanding the world but also for deciding what to do next. Existing sensor models however largely stop at perception: they recognize states or predict outcomes, leaving actions modeled separately through task-specific and often closed label spaces. We introduce Sensor-Language-Action (SLA) modeling, a framework that connects multimodal sensor observations, natural language, and actions within a unified model. SLA uses language as a semantic interface between sensing and acting, allowing heterogeneous actions to be represented, predicted, and explained while remaining grounded in the underlying sensor evidence. We build a large-scale SLA benchmark consisting of datasets that span more than 116,000 individuals, 79 sensor modalities, and 60 action groups, together with a multi-faceted captioning pipeline that aligns user context, sensor dynamics, and action evidence. Building on this framework, we present OpenSLA, a unified SLA model for hierarchical action prediction, state understanding, and action explanation. Extensive experiments on real-world tasks in clinical prediction, operating rooms, and metabolic health verify its superior performance over the state-of-the-art. OpenSLA also demonstrates intriguing capabilities including language-guided evidence grounding and zero-shot generalization to unseen actions and cohorts.
benchmark - arxiv:2610.08220 · cs.ROVOMMI: Collecting and Leveraging Portable Demonstrations for Mobile ManipulationYutian Zhang, Xingrui Xiong, Siyuan Ma, Yang Li +11
Portable mobile-manipulation demonstrations can help alleviate data scarcity for embodied intelligence, but obtaining reliable, low-cost, and robot-free motion supervision from RGB observations remains challenging. Existing approaches often rely on teleoperation or specialized devices equipped with additional sensing hardware, while directly using estimated visual odometry (VO) trajectories can introduce inconsistencies due to accumulated drift and imperfect motion supervision. We present the Visual-Odometry-Conditioned Mobile Manipulation Interface (VOMMI), a portable demonstration collection and learning framework that connects portable RGB demonstrations to vision-language-action (VLA) post-training through offline trajectory reconstruction and online visual-motion conditioning. VOMMI synchronizes body and hand views to capture navigation context and local object interactions without requiring human-robot kinematic correspondence calibration. R2-VO refines offline demonstration trajectories using sparse geometric anchors and produces causal local-motion tokens over multiple prediction horizons for online policy conditioning. An action-group residual adapter incorporates these tokens only into the base branch. Experiments use a 500-trajectory portable for each task, with 75 trajectories held out for RGB-VO evaluation, and 200 robot demonstrations as references. Our policy, post-trained only on portable demonstrations, achieves 18.2% lower base-velocity error than a policy trained with robot-collected demonstrations, while maintaining comparable end-effector translation accuracy. Offline reconstruction reduces absolute trajectory errors for the body and hand streams by 24.6% on average relative to the best evaluated baseline for each stream. The complete system improves the mean success rate by 8.3 percentage points over OpenPI 0.5 across three real-robot tasks.
vision-language-actionembodiedmanipulationteleoperationpost-training - arxiv:2610.08215 · cs.AILearn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?Yibo Li, Jinhang Qiu, Zhi Zheng, Qianyun Guo +3
Learning from experience is essential for LLM agents to adapt to unfamiliar and dynmaic environments. Evaluating this ability is therefore important for understanding how effectively agents acquire and use new knowledge. Existing benchmarks have sought to evaluate this ability, but they primarily evaluate tasks whose rules are provided in the instructions or already familiar to pretrained models, making it difficult to distinguish learning from interactions from reasoning with existing knowledge. To address this, we introduce Learn2Play Bench, a benchmark of newly designed text-based games, whose rules are novel or counterintuitive, requiring agents to acquire knowledge through interaction rather than rely solely on pretrained knowledge. These games provide reproducible feedback and automatic scoring, enabling controlled evaluation of learning across repeated attempts. We also vary game instances to test whether agents can apply what they have learned to new situations. Therefore, we evaluate how backbone models, self-evolving methods, and agent harnesses affect agents' learning ability, revealing three findings: (1) Experience retention: Retaining complete records of actions and feedback can support more effective learning than summarizing these experiences into rules or strategies. (2) Human agent gap: Top-performing human players achieve higher peak scores than the evaluated agents. Human explore more varied strategies, and repeat actions less. (3) Harness matters: With the backbone fixed, changing the harness can improve performance while reducing estimated inference cost. Together, these findings provide insights into how LLM agents learn from experience and suggest directions for future work to improve their learning ability. Project website: https://liushiliushi.github.io/learn2play-bench-website/
agentllm agentself-evolvingbenchmark - arxiv:2610.08208 · cs.AISTRUCTURALCOST: A controlled reading time dataset for modeling human sentence processing difficultyNina Nusbaumer, Iria de-Dios-Flores, Corentin Bel, Christophe Pallier +2
We introduce STRUCTURALCOST, a self-paced reading dataset of 475 participants and 40,800 observations isolating the processing cost of long-distance subject-verb dependency resolution. We replicate a low-powered psycholinguistic finding at NLP scale, namely that human reading times at the main verb increase with dependency length, driven by syntactic embedding beyond linear distance. Different language models -- spanning n-gram models, SSMs, and transformers -- partially mirror this graded difficulty profile, yet underestimate the integration cost humans incur, with a gap that persists across architectures and model sizes. This suggests these models capture the predictive component of human processing but not the full integration cost that working memory imposes. STRUCTURALCOST provides data needed to drive progress toward evaluating the cognitive plausibility of language models.
memory - arxiv:2610.08205 · cs.AITool-calling retrieval versus vector RAG for a small Greek--English knowledge base: accuracy and robustness to how users type GreekNikolaos D. Tantaroudas, Ilias Karachalios, Andrew J. McCracken
Assistants grounded in a small, frequently edited knowledge base can retrieve through tool calls to a live data interface or through vector retrieval-augmented generation (RAG). We compare the two on KyGround, a benchmark of 198 questions drawn from the published records of a Greek--English agricultural platform on Kythera, Greece, with answers verified automatically against the records and each question posed in up to nine forms, including Greek without accents, in capitals and in three Latin-script (Greeklish) schemes. With Claude Haiku 4.5 as router and answer model, a reconstruction of the platform's tool agent answered 71.6\% of canonical Greek questions correctly and vector RAG 95.3\% (difference $-23.6$ percentage points, 95\% CI $-33.1$ to $-15.1$). Letting the router write the vector query changed nothing, and placing the whole knowledge base of about 26,000 tokens in the prompt reached 99.3\%. The tool agent's losses arose in retrieval. Its literal searches returned nothing when the router's arguments did not occur verbatim in a record, for example when it transliterated Greek into Latin script or combined words that occur in a record but not as one phrase, and the agent then abstained. Unaccented and capitalised questions cost the tool agent about 20 points and vector RAG at most 2; accent-insensitive search removed this loss, and matching stemmed tokens raised the tool agent to 83.8\% on canonical Greek. Greeklish cost both designs about 21 to 32 points. Tool interfaces for community knowledge bases need search that tolerates how users type.
retrieval-augmentedragagentbenchmark - arxiv:2610.08188 · cs.CVPIE-PS: Photometric Stereo from Physical Irradiance Event StreamsXiangze Meng, Guangyu Li, Jing Li, Di Mei +3
Event cameras record asynchronous log-image-irradiance changes with microsecond latency and high dynamic range. These properties are useful for photometric stereo under moving illumination, but raw events are sparse and depend on an unknown contrast threshold. We start from the event trigger model and derive a physical relation between adjacent events, light motion, and surface normals. This relation gives a direct physics-only solver, but the solver needs the threshold, enough events at each pixel, and independent per-pixel optimization. To address these limits, we introduce PIE-PS, a learning-based framework for dense surface normal reconstruction from raw event streams and known lighting. We form Physical Irradiance Events (PIEs) by pairing two adjacent events at the same pixel with their corresponding light directions. Each PIE provides a Physical Irradiance Event Feature (PIEF), defined as the signed event rate. PIEF does not require the unknown contrast threshold. To share spatial and temporal context across nearby PIEs, we introduce PIE-GNN, which treats each PIE as a graph node and encodes it with its light-pair geometry. Since the reliability of PIE observations can vary with local appearance, illumination geometry, and sensor noise, Reliability-Grading Attention (RGA) predicts reliability weights to down-weight unreliable PIEs. Pixel aggregation then produces dense normals. Experiments on synthetic and real data show that PIE-PS outperforms prior event-based photometric stereo methods and the direct solver baseline.
event camera - arxiv:2610.08183 · cs.ROCompact Robot Policies Need Fine-Grained Visual RepresentationsNanhe Chen, Runqiu Yang, Jiawei Tang, Sichao Liu +1
Multi-task manipulation policies differ in architecture, scale, and pretrained priors all at once, so published comparisons cannot attribute performance to any single component. We argue that most of it comes from the visual representation, and that parameter scale and generative priors are largely incidental. To test this, we build CoRP (Compressed Representation Policy), a deliberately compact policy (48.9M parameters, no vision-language model and no video-generative prior) that factorizes into a representation extractor and a flow-matching action generator. It reaches 97.0% on LIBERO and 75.78%/73.36% on RoboTwin 2.0 Clean/Randomized, matching systems 40.9-163.6x larger. Holding the action generator fixed, we then vary one extractor property at a time. Pretrained initialization is decisive: a random ViT-S/14 drops to 78.1% and an ImageNet ResNet-34 to 74.5% on LIBERO. Pretraining alone is not enough, as freezing the encoder costs 19.8 points. Compression matters as much: resampling each view to 48 tokens beats passing all patch tokens (97.0% vs 83.2%), and a variational information bottleneck over those tokens is worse than a hard token budget, cutting LIBERO-Goal from 95.8% to 33.0% by suppressing the instruction-dependent token selection the policy relies on. Language conditioning contributes only where the observation leaves the goal ambiguous (LIBERO-Goal: 9.2% to 95.8%), while on RoboTwin 2.0, where observations are unambiguous, removing it slightly improves success. Therefore, we argue that a compact policy works when its representation is pretrained, task-adapted, and compressed. Project page: https://corp-policy.github.io/
manipulationliberorobotwin - arxiv:2610.08176 · cs.LGLFHE: Local-First Heuristic Evolution for Bounded Local Topology Search in Decentralized Learning with Non-IID DataYin-Kuan Liang, Yan Gao, Yang Long
Decentralized learning is highly sensitive to communication topology under non-IID data. Adaptive peer-selection methods can exploit local model information, but broader peer discovery may require increasingly large control state, whereas direct spectral optimization typically relies on graph-wide information. We study the intermediate setting of bounded local topology search and propose Local-First Heuristic Evolution (LFHE), a representation-driven rewiring framework whose candidate discovery and scoring use only ego-neighborhood and friend-of-a-friend (FoF) information. The structural score admits an exact interpretation through graph Dirichlet energy: its sum across clients equals twice the representation Dirichlet energy, which under standard linear consensus dynamics governs the instantaneous dissipation of representation disagreement. LFHE combines this state-dependent structural signal with early exploration and degree control, while algebraic connectivity remains an offline graph diagnostic. Under bounded sparse degree, its FoF candidate state remains local rather than expanding toward population-wide peer tracking. Across four image, speech, and text benchmarks, LFHE achieves competitive decentralized learning performance. Matched-protocol controls identify the structural term as the principal empirical topology-selection signal, while comparison with broader peer discovery exposes a trade-off between predictive performance and discovery-state locality. Together, these results motivate state-aware bounded local topology search between pairwise peer selection and globally informed topology optimization.
benchmark - arxiv:2610.08173 · cs.LGBeyond the Leaderboard: Multi-Dimensional Evaluation of Dense and Mixture-of-Experts Models for Automated Program RepairAnvi Kalpesh Shah, Umamaheswara Sharma B
Automated Program Repair (APR) with language models is usually evaluated by whether a generated patch passes the test suite, which can hide differences in maintainability, security, and computational cost. We propose a Weighted Quality Index (QI), inspired by the ISO/IEC 25010 software quality model, that combines functional correctness, maintainability, security, and generation efficiency under configurable weighting schemes. We evaluate three dense Qwen2.5-Coder models (3B, 7B, 14B) and the 16B-parameter DeepSeek-Coder-V2-Lite Mixture-of-Experts (MoE) model (2.4B active parameters) on 40 QuixBugs and 90 Defects4J bugs, all run locally on identical hardware to control for infrastructure effects. Model rankings change with the weighting scheme, showing that single-metric evaluation can hide trade-offs. The MoE model shows almost no statistically significant difference in correctness from the 7B and 14B dense models (McNemar's exact test) while using 3-6 times fewer active parameters, whereas correctness increases significantly across the three dense scales. These results suggest that active parameter count can be a more informative lens than total parameter count for sparse code models.
leaderboard - arxiv:2610.08170 · cs.CVVisual Orchestration Tax in Agentic VLM Pipelines: Auditing and Certifying Visual Evidence ReuseLingteng Zeng
Agentic VLM pipelines increasingly pass the same static visual evidence through multiple specialist agents and tools. This design creates an orchestration-level redundancy mode: semantically unchanged images are repeatedly reconstructed as image-conditioned requests at the VLM API boundary. We call this phenomenon visual orchestration tax and develop a measurement-to-certification framework for visual evidence reuse in agentic VLM pipelines. The audit side defines $\mathrm{M1}_{\mathrm{trace}}$ to count raw visual-evidence touches and M2 to measure structural touch redundancy, with query-level distributions, bootstrap confidence intervals, and paired quality tests. Across SeeingEye and MAMMQA on chart, document, general-VQA, and multi-modal-QA tasks, audits reveal 66.8-75.6% visual-evidence touch redundancy, and every audited query exceeds the predefined gate. The certification side introduces SharedVisCache, a contract-aware evidence reuse hook keyed by image content, preprocessing fingerprint, and encoder assumptions. On SeeingEye, contract validation certifies 75.0-75.5% repeated touches as reusable while preserving 350/350 output strings and $Δ\mathrm{M5}{=}0$. At the physical layer, certified hits reduce $F_{\mathrm{vision}}$ from 800 to 200 in ChartQA-200 trace replay and from 200 to 50 inside live SeeingEye translator-stage physical integration, preserving 800/800 replay strings and 200/200 integrated call outputs. The results position visual reuse as a measurable, behavior-preserving property of agent orchestration and define an agent-layer contract that makes backend prefix or token reuse semantically interpretable.
agentagentic - arxiv:2610.08162 · cs.CVThe Failure Is in the Readout: Fine-Grained Emotion Recognition Benchmarks Measure Elicitation, Not PerceptionTobias Hallmen, Fabian Deuser, Robin-Nico Kampa, Norbert Oswald +1
Fine-grained emotion recognition supports therapy tools and social robots, but it needs facial data, which raises privacy and data-protection concerns. EmoNet-Face-HQ answers that with generated portraits, expert-rated over a $40$-category taxonomy far finer than the usual six to eight basic emotions. Under the protocol it ships with, vision-language models (VLMs) score poorly on that taxonomy, and the benchmark concludes that a dedicated fine-tuned model is necessary: Empathic-Insight-Face (EIF; Small/Large). We show that off-the-shelf VLMs match or beat that fine-tuned model when the answer is not generated but read from the logits, as one binary query per category. We keep the benchmark's images, taxonomy and ratings, and change only how the answer is read. Experts agree at $κ_w = 0.468$ on the five categories they measure most reliably. Generatively, no interval among eleven open-weight VLMs lies entirely above that anchor ($κ_w=0.268$-$0.486$). Under verification all eleven clear it, each of them significantly better at $κ_w=0.507$-$0.586$. Three also significantly beat EIF sitting at $κ_w = 0.551$ (Small; $0.534$ Large). The gain comes from the graded probability and not from asking a yes/no question: as a control, thresholding those same probabilities to yes/no costs 142% of the average gains and drops binarization below generative elicitation to $κ_w=0.254$-$0.423$. A replication on real photographs (FACES) is weaker and mixed: of the ten models that pass a validity gate, six gain, three are neutral to positive and one is negative, so the effect is not confined to synthetic data.
benchmark - arxiv:2610.08161 · cs.LGSymphony for Text Generation: Benchmarking Clinical Note GenerationDaniel Varab, Victor Petrén Bach Hansen, Asbjørn W. Helge, Kevin Pelgrims +7
Ambient documentation systems are rapidly gaining adoption, yet their impact on clinical note quality remains poorly characterized. We introduce MedConv, a multilingual dataset of 300 clinical encounters in English, Danish, and German, and use it alongside the Ambient Clinical Intelligence benchmark (ACI-BENCH) to compare Corti, a clinical AI platform, with two leading, accessible ambient scribe software applications built on general-purpose AI. We present a controlled clinical evaluation framework that combines entailment metrics with LLM-judged pairwise comparisons across eight dimensions adopted from PDSQI-9. Results show that Corti's API-based text-generation infrastructure is on par with or outperforms leading commercial scribes. We further show that Corti's configurable API provides the flexibility necessary to fine-tune quality dimensions for specific documentation use cases. We present the evaluation methodology and release a dataset to support future reproducible comparison of ambient documentation systems.
benchmarkevaluation framework - arxiv:2610.08159 · cs.LGMaking COMET Comparable Across Scripts: Diagnosis and Correction of Tokeniser-Induced Script Bias in Indic MT EvaluationG. L. John Salvin, Swapnil Hingmire
COMET reports translation quality as a single number, and that number is routinely compared across target languages written in different scripts. Such a comparison assumes Script Invariance: the score should not depend on the writing system that carries the target. We test it on IndicMT Eval by re-encoding the target into Latin script, which changes orthographic form while holding content and human ratings fixed. Script identity then accounts for 22.9% of native-script COMET variance, and agreement with annotators falls in all five languages studied. We trace the effect to the tokeniser and measure it with three label-free diagnostics. The bias is two faults, not one. Scores from different scripts occupy incompatible ranges, and within a single script the metric orders translations less accurately. No order-preserving transform of the score can repair the second fault. The first is removed exactly by COMET-QN, which maps the score distribution of each (language, script) pair onto a shared reference. Pooled agreement with annotators rises from 0.300 to 0.399, which is what makes scores from different scripts safe to place on one axis, and every within-language ordering is provably preserved. A regressor over parity features recovers a further 17.1% of the lost sensitivity. The remainder belongs to the encoder, and no post-processing can reach it. We therefore recommend publishing the normalised score, the three diagnostics, and the identity of the tokeniser they were computed against, so that a reader can tell how much of a score reflects translation quality and how much reflects the writing system.
eval - arxiv:2610.08155 · cs.AIToken-Efficient Multi-Agent Collaboration via System One-Guided Computational Division of LaborZihan Zhou, Xinzhe Hu, Hanxu Yang, Liangjian Wen +1
Large language model (LLM)-based multi-agent systems (MAS) have become a promising paradigm for complex information-seeking and reasoning tasks by enabling collaborative problem solving among specialized agents. However, existing MAS frameworks tightly couple task reasoning with coordination operations, including task selection, role assignment, message routing, and context management. As interactions grow, using powerful LLMs for these bounded control decisions introduces substantial token overhead and latency, limiting the scalability of agentic Web services. In this paper, we investigate whether coordination can be decoupled from expensive reasoning without compromising collaborative performance. We propose S1-MAS, a token-efficient multi-agent framework based on System One-guided computational division of labor. S1-MAS assigns bounded coordination decisions to lightweight System One models while reserving open-ended reasoning for capable LLM workers. Specifically, a lightweight controller selects inspection conditions, chooses subsequent tasks, and determines termination, while a compact reader retrieves condition-relevant evidence from authorized sources to support these decisions. Through a decision-evidence loop, selected tasks dynamically determine worker roles and source access, enabling adaptive collaboration without task-specific training. Extensive experiments on seven diverse benchmarks demonstrate that S1-MAS achieves superior accuracy while substantially reducing the inference cost. Across individual comparisons with AgentVerse, DyLAN, and SelfOrg on seven benchmarks, S1-MAS reduces GPT-4o token consumption by 44.9%-97.2% and measured end-to-end latency by 37.8%-93.0%. These results highlight its potential for scalable and cost-effective agentic Web applications.
multi-agentagenticagent frameworkagent systembenchmark - arxiv:2610.08150 · cs.ROViDAL: A Visual Dynamics-Grounded Action Latent Space for Vision-Language-Action ModelsYuan Xu, Yixiang Chen, Qisen Ma, Jiabing Yang +9
Vision-Language-Action (VLA) models have become a central paradigm for robot policy learning, which predict actions in three forms: raw action chunks, discrete action tokens, or continuous action latents. However, existing action representations primarily model action trajectories, with limited consideration of the visual dynamics induced by these actions. We introduce ViDAL, a Visual Dynamics-grounded Action Latent Space that anchors continuous action latents in the future visual dynamics of the scene. Specifically, ViDAL learns action latent space by training an Action Variational Autoencoder (Action VAE) to reconstruct action chunks while aligning its latent with future scene dynamics. When integrated into downstream robot policies, the proposed Action VAE serves as a plug-in action interface compatible with multiple VLA architectures and enables optional future-video prediction as an additional capability. Empirically, ViDAL outperforms competitive baselines on LIBERO with 98.1% average success, improves a multi-task $π_{0.5}$ policy on RoboTwin 2.0 from 54.3% to 65.5% (Clean) and from 33.2% to 43.1% (Random) success rates over 50 dual-arm tasks, and yields 20.0% and 23.4% absolute success-rate gains on real-world single-arm Franka and dual-arm ARX robot platforms.
vision-language-actionvlarobot policyliberorobotwinfranka - arxiv:2610.08142 · cs.AIPartially Observable Zero-shot coordination by Predicting Intention of PartnerJinnyeong Yang, Yuhwan Jeong, Hoyong Kwon, Minseok Kim +2
Zero-shot coordination in embodied settings requires acting while the partner is intermittently out of view, leaving existing methods with ambiguous partner representations and uncertainty over hidden partner states. We propose Predicting Intention of Partner (PIP) to jointly address these challenges. PIP uses a Joint-view VAE to distill richer training-time evidence from the union of both agents' local observations into a partner representation available from local observations alone. Partner-state Belief networks further infer the partner's hidden location and behavioral tendencies from the ego agent's interaction history. We evaluate PIP in Burrito-PO, Overcooked-PO, and a Melting Pot substrate, together with a human evaluation in Burrito-PO. PIP attains the highest mean performance among the compared methods across all three benchmarks. Human evaluation and diagnostic analyses further support coordination with unseen partners and the contributions of both components under partner occlusion.
embodiedbenchmark - arxiv:2610.08138 · cs.AITest-Time Agent Evolution for Long-Horizon Legal ReasoningHaotian Chen, Shuaicheng Niu, Haocong Rao, Kaisong Song +4
Legal intelligence aims to support reliable decision-making across long-horizon legal processes involving evolving case states and multiple roles. However, real-world legal deployment exhibits substantial case heterogeneity in facts, evidence, and procedural contexts, exposing the limitations of static agent strategies. Moreover, legal reasoning is inherently interdependent across roles and procedural stages, making global reliability fundamentally different from isolated role competence. To address these challenges, we study training-free test-time agent adaptation, where agents continuously exploit deployment-time signals from preceding cases and ongoing interactions without updating model parameters. We propose \method, which introduces \emph{Test-Time Memory Evolution} to retrieve reusable experience from previous cases, adapt it to the current factual and procedural context, and consolidate accumulated experience for subsequent decision-making. Further, \emph{Rubric-Aligned Collaboration} verifies and revises role-specific actions according to behavioral and procedural requirements, enabling coordinated decision-making across roles and stages. Extensive experiments on J1-EVAL and LegalWorld across five backbone models demonstrate consistent improvements over representative reasoning and agent baselines with reasonable interaction and computational costs. Ablation and case studies further show that the two components provide complementary benefits in experience adaptation and cross-role coordination, improving the reliability and efficiency of long-horizon legal reasoning.
memoryagent - arxiv:2610.08133 · cs.ROVLA-ACL: Action-Consistent Visual Token Pruning for Efficient Vision-Language-Action ModelsOwen Du, Yang Yue, Jie Zhang, Jiaqi Pi +2
Vision-Language-Action (VLA) models achieve strong robotic manipulation performance but incur high computational costs from processing long token sequences at every control step, limiting real-time deployment. Visual token pruning offers a direct solution, as visual patches dominate the input sequence and contain considerable redundancy. Existing approaches, however, either rely on indirect training-free heuristics, such as attention scores and motion thresholds, or require costly fine-tuning of the base VLA model. We introduce VLA-ACL (Action Consistency Learning), which learns a lightweight visual token pruning policy through action-level supervision while keeping the base VLA model entirely frozen. The training objective encourages actions produced from pruned visual contexts to remain consistent with the full-context teacher, with ground-truth actions as auxiliary supervision. This directly ties token selection to its effect on the downstream control output. Experiments on LIBERO and real-world manipulation tasks show that VLA-ACL prunes up to 87.5% of visual tokens while retaining competitive performance, reduces computation by up to 75%, and achieves a 1.5x inference speedup. These results establish a stronger performance-efficiency trade-off than existing frozen-VLA pruning methods and demonstrate the value of action-level supervision for visual token selection. Code is available at https://github.com/du-owen/VLA-ACL.
vision-language-actionvlavla modelmanipulationlibero - arxiv:2610.08132 · cs.LGBeyond Marginal Monitoring: Distributed Joint-Distribution Testing for Data Concept Drift in Large Scale E-Commerce OperationsCagdas Pullu, Mahmut Emir Arslan, Bugra Balkac, Aylin Ondersev Balta +3
Concept drift threatens production machine learning, yet the empirical behavior of multivariate two-sample drift detectors at scale remains under-characterized. Existing benchmarks rarely address the hundreds of millions of rows and high-cardinality features typical of industrial-operational datasets. We evaluate five multi-column two-sample tests (marginal, projection-based, and kernel embedding methods) across three complementary environments: the Harvard Dataverse, a validated Failing Loudly reproduction (mean absolute error between 0.030 and 0.053), and a novel synthetic-injection benchmark on the 137.5-million-row Trendyol collection-ranking feature table. Testing four drift types across two severity-scope regimes, we demonstrate that distributed Maximum Mean Discrepancy with Random Fourier Features on Apache Spark scales robustly. Averaged over the four drift types in the strong regime and under a calibrated threshold, it achieves a Pearson correlation of r = 0.940 with expected drift magnitude, an 80.4% true positive rate, and a 3.2% false positive rate. Conversely, the per-dimension Kolmogorov-Smirnov test failed due to statistic saturation from ID-like columns under asymmetric sampling, establishing a critical constraint for large-scale sampling design. At weak configurations (realized-flip fractions of at most 0.57%), detectors struggled to reliably discriminate, highlighting the need for future intensity-grid power analyses to distinguish fundamental sensitivity bounds from scalable threshold shifts.
benchmark - arxiv:2610.08123 · cs.ROBeyond Waypoint Regression: Query-Based Cost Learning over Reachable Ego Futures for End-to-End DrivingAhmed Abouelazm, Rupert Polley, Qingyuan Zhang, Yin Wu +3
End-to-end planners based on waypoint regression achieve strong open-loop accuracy, but they primarily learn to mimic expert geometry and remain difficult to adapt to deployment-time safety constraints. We propose a query-based cost-learning framework that estimates bounded costs for dynamically reachable ego trajectory queries, rather than dense BEV cells or a small regressed trajectory set. Compact joint scene tokens capture coherent multimodal agent futures, while contingency-aware cost aggregation and cost-guided intra-cluster MPPI mixing convert the learned cost topology into feasible ego plans. On nuScenes, our method improves over prior cost-estimation planners such as ST-P3 and NMP, outperforms most regression baselines in collision rate, while remaining competitive in L2, and retaining an interpretable cost interface. On real-world driving logs, the proposed planner reduces collision rates compared with SparseDrive and Alpamayo without fine-tuning, while maintaining a diverse set of candidate trajectories.
agent - arxiv:2610.08120 · cs.ROiGPC: Generative Motion Priors for Object-Aware Humanoid InteractionAnujith Muraleedharan, Abdul Ahad Butt, Nolan Fey, Yash Prabhu +4
Humanoid robots operating in unstructured environments must combine robust whole-body control with the ability to perceive and physically interact with surrounding objects. While large-scale human motion data provides powerful priors for natural and versatile humanoid control, effectively transferring such priors to perception-driven object interaction remains challenging. To address this bottleneck, we propose a framework that extends the recently proposed Generative Pretrained Controller (GPC) from general human motion to full-body humanoid-environment interaction. First, we adapt GPC into interaction experts conditioned on scene affordance cues and privileged state information. These experts leverage the pretrained human motion prior while learning task-specific contact behaviors, including reaching toward objects, grasping environmental supports for stabilization, and pushing movable objects. Second, we introduce a perception-driven student that retains the pretrained GPC policy and distills interaction skills from the experts using onboard sensory observations. To bridge the gap between privileged expert observations and sensory inputs, we propose two complementary training objectives that enable effective adaptation of the pretrained motion prior during distillation. Notably, our experiments across multiple whole-body interaction tasks demonstrate that large-scale generative human motion priors provide an effective foundation for learning deployable policies for humanoid interactions in contact-rich real-world environments.
humanoidwhole-body controlgrasp - arxiv:2610.08119 · cs.ROAutodidactWAM: Cross-Modal Self-Distillation from Generated Video to Robot ActionsSergei Kurchev, Iaroslav Kolomiets, Miguel Altamirano Cabrera, Artem Lykov +1
World-action models (WAMs) such as Cosmos 3 jointly generate future video and robot actions from an observation and instruction. Adapting one such model with a lightweight LoRA fine-tune to a previously unseen robot, a Unitree G1 humanoid with five-fingered BrainCo hands, exposes a video-action asymmetry: the video renders plausible task executions, while the co-generated action is systematically mis-targeted. We evaluate closed-loop real-robot trials at three cumulative stages: pre-grasp, grasp, and pick-and-place. The native action succeeds only approximately 17%, 10%, and 7% of the time, respectively, and performs worse on held-out objects. We propose AutodidactWAM, a hand-pose estimator trained without teleoperation, followed by inverse kinematics, that runs on the model's generated video to recover action estimates. Paired with the native prediction, these recovered actions provide preferred targets for fine-tuning only the action-related layers, while the generated video is teacher-forced. We compare supervised relabeling with a rectified-flow adaptation of Diffusion-DPO. After one-time embodiment adaptation, self-distillation requires no additional task-specific teleoperation. The recovered-action gate reaches approximately 75%, 47%, and 42% pre-grasp, grasp, and pick-and-place success, compared with 17%, 10%, and 7% for the native action. A hybrid objective combining preference supervision, supervised target fitting, and Cartesian trajectory anchoring (DPO+SFT+DTW) performs best: on Oreo, the training object, it reaches 90% pre-grasp and 20% full-task success; on a held-out object, it reaches 80% and 30%. Plain Flow-DPO reaches 0% success despite 1.000 validation preference accuracy, indicating that the combination of training objectives, rather than the contrastive objective alone, drives the observed gains.
humanoidteleoperationgrasp - arxiv:2610.08110 · cs.ROReactive Exploration of Unknown Environments for Redundant Robots using Virtual Model ControlAlessio Canzolino, Omar Faris, Alessandro De Blasi, Fulvio Forni
The exploration of confined, occluded, and partially known spaces poses significant challenges in robotic manipulation. The overall pose of the robotic arm must be carefully controlled to respect tight geometric constraints while avoiding newly discovered obstacles. We address this problem by proposing an active exploration approach for redundant robotic arms with an eye-in-hand camera configuration. Our approach navigates and acquires information in real-time based on a novel scoring method that directly selects a target voxel from the unexplored space using the robot's current state and expected information gain. To move the robot safely toward the target voxel, we utilize Virtual Model Control, which guarantees compliance and enables whole-body reactive obstacle avoidance without the need for path replanning. Simulated and real-robot experiments in both confined and open environments demonstrate the effectiveness of our approach, achieving over $90\%$ mapping coverage across all tested environments in under $120$ seconds without colliding with obstacles.
manipulation - arxiv:2610.08109 · cs.CVBeyond Training from Scratch: Foundation Models for Data-Efficient and Generalizable Cardiac MRI ReconstructionAnam Hashmi, Mayug Maniparambil, Julia Dietlmeier, Kathleen M. Curran +1
Cardiac magnetic resonance imaging reconstruction aims to recover high-quality images from undersampled acquisitions, enabling faster scans while preserving diagnostic fidelity. Recent reconstruction methods are typically trained from scratch and often require large amounts of task-specific data, limiting their robustness under data scarcity and distribution shifts. In this work, we investigate whether pretrained vision foundation models can serve as effective priors for accelerated cardiac MRI reconstruction. We propose a reconstruction framework that integrates frozen and parameter-efficiently adapted visual encoders, including CLIP, BiomedCLIP, and DINOv2, within a transformer-based reconstruction architecture. Extensive experiments on the CMRxRecon2023 and CMRxRecon2024 benchmarks demonstrate that pretrained representations consistently outperform a transformer trained from scratch across multiple acceleration factors. We further evaluate performance under limited supervision and cross-dataset transfer, showing that foundation models provide superior data efficiency and generalization. While frozen representations are particularly effective in extreme low-data regimes, Low-Rank Adaptation (LoRA) yields additional gains when moderate amounts of training data are available. Among the evaluated backbones, DINOv2 achieves the strongest overall performance. These findings highlight the potential of vision foundation models as robust and transferable priors for cardiac MRI reconstruction.
benchmark - arxiv:2610.08108 · cs.LGEnhancing Diffusion Language Models with Autoregressive Post-Training WeightsYiming Qin, Ke Wang, Amel Abdelraheem, Adam Hazimeh +1
Diffusion language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) language models, offering flexible token-update orders and parallel decoding. Recent dLLMs are often initialized from pretrained AR models before diffusion conversion in order to inherit their learned representations. After the conversion, however, they typically ignore the extensive post-training ecosystem of their AR ancestors. In this work, we show that these existing AR post-training weight updates can instead be effectively recycled to enhance diffusion models. Despite the changes by AR-to-diffusion conversion, directly adding an AR post-training weight update to a diffusion base model remains effective, bringing its performance close to that achieved by direct diffusion post-training. Notably, AR and diffusion post-training updates are nearly orthogonal in weight space, yet induce substantially more aligned representation changes in the diffusion model. Their distinct updates are also complementary: composing their weights can retain gains from both regimes and further improve the post-trained diffusion model. Based on these findings, we propose A2D, a simple training-free framework for enhancing diffusion models with existing AR post-training resources. A2D can transfer capabilities from AR post-trained models to diffusion base models, and further improve already post-trained diffusion models by composing AR and diffusion post-training updates. Across various dLLMs, including Dream, DreamReasoner, DiffuCoder, Dream-Coder, Nemotron-Labs-Diffusion, and DiffusionGemma, A2D reliably improves instruction following, mathematical reasoning, and coding with both supervised fine-tuning and reinforcement learning updates, without additional training, or inference-time computation.
post-training - arxiv:2610.08107 · cs.AIExploiting Acoustic and Content-Oriented Speaker Verification Attacks Against Multilingual Voice AnonymizationRidwan Arefeen, Ze Li, Rong Tong, Ming Li +1
Attacker ASV systems for voice anonymization have been studied primarily in English, leaving their behavior in multilingual settings largely unexplored. Conventional ASV has shown that both acoustic and contextual information are important for multilingual speaker verification. Inspired by this, we investigate whether the same holds for attacker ASV on anonymized speech. We evaluate both acoustic- and content-oriented attackers on multilingual anonymized speech and construct a multilingual voice-converted dataset to improve cross-lingual generalization. Our results show that attacker effectiveness depends on the linguistic utility of the anonymized speech. Overall, acoustic-oriented attackers achieve better performance. However, when linguistic information is well preserved, the performance gap between content- and acoustic-oriented attackers narrows compared with conditions involving stronger speech distortion. The multilingual voice-converted dataset further improves performance and partially reduces the cross-lingual gap. These findings highlight the need for more comprehensive attacker modeling and evaluation protocols that consider both privacy and utility, rather than relying on a attacker strategy\footnote{Full code and pretrained models and MultiVC Dataset link are available at: https://github.com/monkeyDarefeen/DAST
evaluation protocol - arxiv:2610.08106 · cs.AIChartBmkAgent: Harness-Governed Multi-Agent Construction of Chart QA Benchmarks from Sparse Error-Taxonomy SpecificationsLangxi Huang, Pingping Zhang, Lanyun Zhu, Chunyang Jiang +3
Multimodal large language models (MLLMs) advance rapidly, while conventional benchmark development lags behind, delaying investigation of newly observed capability gaps. Such investigation requires an expressive task format and an on-demand construction process: information-rich charts make chart question answering (Chart QA) suitable for probing coupled perception and reasoning. Automated Chart QA construction is intended to shorten the benchmark-development cycle by turning identified gaps into targeted samples on demand. Current methods, however, commonly separate target guidance from scratch generation: target-guided systems often require prepared data, charts, or templates, while scratch-generation systems primarily ensure artifact validity, without explicitly controlling whether newly synthesized requirements and content remain aligned with an externally specified diagnostic target. We introduce ChartBmkAgent, which turns an identified capability gap into targeted diagnostic evidence by constructing complete Chart QA samples from sparse error-taxonomy specifications. Throughout construction, a central harness governs specialized agents, requires stage-specific evidence of alignment with the original error category, and records the basis for each acceptance decision. On 300 taxonomy-wide samples, MLLM accuracies ranged from 32.7% to 84.3% with distinct category profiles, showing that generated samples reveal capability differences. Across three source-model comparisons, targeted follow-ups scored 50.0% versus 82.2% on matched controls ($p=8.96\times10^{-6}$); all six cross-model comparisons had the same direction, demonstrating targeted validation and diagnostic-data generation. Multiple evaluator models assessed whether each sample tested its specified error category; 86.4% met this criterion, providing empirical evidence of target preservation.
multi-agentbenchmarkevaluator - arxiv:2610.08105 · cs.RONavigation with RF Cues: Embodied Perception Action under Multipath UncertaintyWenlihan Lu, Tianshun Li, Liuqing Yang, Shijian Gao
Smart factory inspection requires robots to reach connected equipment without a prior map or known target coordinates. Radio frequency (RF) signals from the target can provide directional cues to complement visual observations when occlusion or poor lighting limits target detection. However, multipath propagation can distort these cues, making it difficult to infer the target's true direction from instantaneous RF measurements. To enable navigation research under these conditions, we first construct a Habitat Sionna RT benchmark that uses detailed scene geometry and assigned material properties to generate aligned visual and RF observations in response to robot actions. Building on this benchmark, we propose an uncertainty aware multimodal navigation framework that jointly estimates target direction and its uncertainty from a history of RF, visual, and pose observations. These estimates inform action selection alongside visual context. Experiments in unseen scenes show relative improvements of 18.2% in success rate (SR) and 11.5% in success weighted by path length (SPL) over the strongest evaluated baseline.
embodiedbenchmark - arxiv:2610.08102 · cs.AIDSV-Mem: Evaluating Multimodal Memory in Professional Workflows for MLLM AgentsJike Zhong, Ritwick Chaudhry, Xuanbai Chen, Tianchen Zhao +3
Conversational MLLM agents are increasingly expected to assist in professional workflows, from AI research and engineering design to product management and business operations. Yet this capability remains underexplored: existing benchmarks largely focus on informal, everyday interactions and personal-life scenarios featuring photographic natural images, isolated static artifacts, and recall-oriented questions. In contrast, professional scenarios often involve structured, information-heavy artifacts that undergo frequent revisions and authority updates, and compositional queries requiring reconciliation of many artifact versions while tracking state precisely. To address these challenges, we introduce DSV-Mem, a benchmark for evaluating Dense Stateful Visual Memory. DSV-Mem comprises expert-reviewed scenarios and 1,000 questions across five user-oriented categories (Current State, Past State, Derived State, Change History, and Conflict/Refusal). A Hartley-inspired criterion favors questions with broader visual-evidence inspection demands. We also introduce a generation harness that produces evaluation suites by decoupling state-transition synthesis from conversation filling. Evaluation over 27 configurations spanning frontier and open-weight models and memory management methods reveals that the strongest baseline scores below 45% on DSV-Mem. Analysis surfaces findings: 1) multimodality and information density both contribute to difficulty, but state evolution, particularly the number of governing updates, is the dominant tested factor. Raw conversation/haystack length, OCR, and arithmetic are not the primary bottlenecks; 2) models often fail to verify user premises against prior state updates before answering; 3) increased reasoning effort and memory management methods yield limited gains, whereas state-aware designs prove more effective. The benchmark and code will be publicly released.
memoryllm agentbenchmark - arxiv:2610.08101 · cs.AIBeyond Corrected Memory: Execution Consistency in Multi-Agent SystemsZhe Yu, Zixuan Wang, Peidong Wang, Hehai Lin +2
Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and failure diagnosis regulate or inspect recorded information; they do not by themselves establish whether it is sufficient to judge task duties. We define execution consistency through duties governing state use, information handoffs, and final-state agreement, with explicit evidence conditions for judging fulfillment. Our core claim is that identical retained records can correspond to compliant and violating executions under the same task rule. Controlled removal of evidence such as receipt, action dependence, or response validity leaves 82.4% of opposite-label pairs indistinguishable; restoration separates 97.9% of the merged pairs. Natural-log annotations identify the defined violations in actual executions. However, existing logs do not always explicitly represent the execution relationships needed for these judgments. To assess the definition's practical value, we use CAVERT, a framework for consistency diagnosis and recovery, to extract supported relationships from logs and apply these criteria. It consistently outperforms contract-prompted LLM and rule-based baselines in diagnosis across all 12 benchmark-executor settings. Under the same gate and executor limits, it also outperforms rule-guided recovery in all four evaluated environments. These findings identify execution evidence that agent-memory and execution interfaces should preserve for reliable judgment.
memorymulti-agentagent systembenchmark - arxiv:2610.08098 · cs.LGSurviving the Router: Optimizing Skill Injections for Retrieval and ExecutionHaneen Najjar, Luca Scionis, Haritz Puerto, Sahar Abdelnabi
AI agents increasingly rely on modular third-party "skills" that are dynamically selected by skill routers to execute complex tasks. While recent studies highlight the threat of prompt injections embedded in these skills, existing evaluations often assume settings where the malicious skill is already selected for execution. We show that this assumption can substantially overestimate attack success. In realistic multi-skill environments, injected skills must first compete for retrieval, reducing the effective attack success rate (ASR) of existing injections by 87-97%. To address this limitation, we introduce CORSA (Cluster Optimization for Router-Aware Skill Attacks), a router-aware attack that optimizes skill injections for both retrieval and execution across clusters of related tasks. We evaluate skill injection attacks under router-managed multi-skill settings by extending the benchmark introduced by SkillRouter with eight malicious payload categories. CORSA uses successive optimization stages to first improve retrieval and then optimize end-to-end attack success, while we evaluate user utility and injection naturalism separately. Our experiments show that CORSA substantially improves both retrieval and end-to-end attack success over existing skill injections while preserving user utility, and that the resulting attacks transfer across different router architectures and LLM backbones.
ai agentbenchmark - arxiv:2610.08095 · cs.AINatural Language Questions as an Interface for Knowledge Graphs: QRAKEN Graph Distillation and Semantic Self-HealingRemo Grillo, Lukas Klic, Giovanni Colavizza
Natural-language access to RDF knowledge graphs is a core Semantic Web ambition. Large language models (LLMs) have advanced Text-to-SPARQL, yet on unfamiliar graphs they often generate valid queries that misrepresent the populated data model. QRAKEN is a training-free, ontology-agnostic neurosymbolic pipeline grounding generation in empirical graph evidence rather than schema expectations. An offline distiller produces TTQL, a compact description of populated multi-hop patterns, conditional frequencies and path-conditioned literal examples, plus a class-property co-occurrence matrix. Online, TTQL guides the LLM, while deterministic syntax, vocabulary and data-model checks provide diagnostics for iterative refinement. On CK25 (First International Text2SPARQL Challenge), under matched-condition recomputation on a QLever snapshot, QRAKEN achieves strict F1 of 0.643 $\pm$ 0.026 with GPT-4.1 mini and 0.652 $\pm$ 0.012 with GPT-5.4: relative gains of 30% and 32% over the strongest recomputed participant, outperforming systems using the same base model family. Ablations identify TTQL patterns as the dominant driver (+0.31 strict F1 over a shape-only baseline); the refinement loop provides a cheap safety net, rejecting triple patterns unsupported by the co-occurrence matrix. Compared with auto-derived SHACL, TTQL yields 64% higher strict F1, supporting the value of empirical patterns beyond schema exposure. With two local 35B 4-bit open-weight models at zero marginal cost, the same pipeline matches the strongest recomputed participant, and TTQL advantages over shape-only and SHACL baselines persist. Results on a single, relatively small benchmark provide an initial empirical signal; monolithic TTQL injection on very open cross-domain graphs remains the main limitation.
knowledge graphiterative refinementbenchmark - arxiv:2610.08093 · cs.AISAGE: Semantic Anchor-Guided Evolution for Grounded Medical QA Data SynthesisChuan Li, Chengyu Wang, Cen Chen, Ye Lyu +2
Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-quality, expert-annotated training data. This challenge is exacerbated by stringent privacy requirements and the impracticality of utilizing large open-source corpora or proprietary cloud APIs within resource-limited clinical settings. To address these obstacles, we introduce SAGE (\textit{Semantic Anchor-Guided Evolution}), a novel data synthesis framework that enables small, locally deployed models to generate high-quality medical training data. SAGE leverages lightweight, publicly available taxonomies such as MeSH as semantic anchors, imposing a structured prior to effectively guide and ground the data generation process. At its core, SAGE iteratively interleaves atomic (individual concept-based) and associative (relation-based) synthesis, bootstrapping training data from minimal seeds. This approach eliminates the need for large collections of medical documents or reliance on external APIs, providing a practical solution for on-premises data creation. Extensive experiments across multiple medical question-answering benchmarks demonstrate that models fine-tuned with SAGE-synthesized data consistently outperform those trained using self-derived or conventional document-based paradigms, highlighting tangible improvements in data efficiency and resource utilization for medical LLM development. Code is available at https://github.com/DIaacKr/SAGE.
benchmark - arxiv:2610.08082 · cs.AIPOLAR: Ontology-Guided Risk Prevention for Tool-Calling LLM AgentsYunju Kang, Seonghyeon Cho, Irene Li, Yeo-Chan Yoon +1
LLM tool-use agents operate in dynamic environments where many actions carry operational risk. However, most safety mechanisms react only after errors manifest. Existing pre-emptive approaches either fine-tune the agent on chain-of-thought deliberation or compile natural-language guardrails into runtime checks, but they do so without exposing a structural, auditable verdict. We propose POLAR, a guardrail framework for small tool-calling agents that assesses reversibility through a structured two-layer ontology. POLAR assigns each action a graded reversibility score by deriving a candidate inverse sequence; calls failing a threshold are pruned before execution. Evaluated on $τ^2$-bench across six agent models, POLAR improves mean task reward by 0.11 to 0.18 points on airline for four of six agents, but only eight of eighteen model--domain cells improve overall; retail and stronger agents often regress. POLAR provides an auditable structural check and characterizes its task-utility trade-offs. Reward is not a direct measure of prevented harm.
agentllm agenttool-use - arxiv:2610.08077 · cs.LGSelf-Retrospection Distillation: Turning Post-hoc Experiences into Prior ForesightHaoxiang Zhang, Qinglin Chen, Hiroaki Hayashi, Zhuofeng Li +8
Reinforcement learning with verifiable rewards (RLVR) turns agent experience into learning signals primarily through scalar outcome rewards after interaction. For group-relative objectives, however, this signal vanishes when all rollouts receive the same reward, even though their trajectories may reveal useful information about what the task requires and how the agent fails. We ask a complementary question: can hindsight teach an agent what it could have anticipated before acting? We introduce prospective learning, which uses post-hoc experience to supervise foresight predictions from the pre-interaction view, and instantiate it with Self-Retrospection Distillation (SRD). Intuitively, a completed trajectory reveals knowledge that would have been useful and pitfalls that should be avoided; SRD distills this privileged hindsight into trajectory-blind foresight of the same policy. Foresight serves only as a training target and need not be explicitly generated at inference time. Across 10 tool-integrated reasoning and long-horizon agentic tasks, SRD complements RLVR and self-distillation baselines with gains of up to $24.2$ pp. Its advantage is especially pronounced when reward contrast is scarce: when $37$--$98\%$ of rollout groups are reward-uniform across model scales, yet SRD can still exploit learning signal from sampled trajectories. In the 2B setting, where $98\%$ of groups are all-failure, the RLVR training ends up at $0.0\%$ success, while adding SRD reaches $60.6\%$ under the same rollout budget. Our results suggest that post-hoc agent experience is useful not only for evaluating or improving behavior, but also for shaping predictive representations before available interaction.
agentagentic - arxiv:2610.08076 · cs.AISpeedrunBench: Challenging LLM Agents with Video Game SpeedrunningYoshinari Fujinuma, Keisuke Kamahori, Ryuto Koike, Abdelrahman Madkour +7
Frontier LLM agents have been shown to be capable of solving increasingly complex tasks for which humans have measurable solutions. This begs the pertinent question of whether LLM agents can go beyond what humans have already solved. The ability to develop sophisticated strategies to tackle consequential problems becomes paramount as well-trodden, human-developed solutions become insufficient for problems for which we lack context or enough training data. We study agents' capability of such strategy formation through the communal practice of video game speedrunning. In speedrunning, practitioners compete to find the fastest way to complete a video game under certain conditions, and in so doing uncovering interesting unorthodox play styles that require a thorough understanding and mastery of the underlying game mechanics. We introduce SPEEDRUNBENCH, a benchmark that evaluates frontier LLM agents across 9 different games. To perform well in this benchmark, agents must repeatedly improve their strategy, reflect on their performance, exploit their gained knowledge, and reason across a long-horizon of actions to improve on an increasingly difficult problem: being faster than themselves and everyone else. Our experiments show that while frontier agents approach human world records in simple platformer games, they remain behind human performance on longer, more complex games under practical budgets. These results suggest that SPEEDRUNBENCH is a useful testbed for studying agents' strategy formation capabilities as well as being a saturation-resistant evaluation measure, as there is almost always a faster completion time waiting to be discovered.
llm agentbenchmark - arxiv:2610.08068 · cs.CVPhysTacGen: Physics-Aware Visual-Tactile Sensor Image GenerationGuo Tang, Yongtao Wang
Realistic physical interaction is a cornerstone of embodied intelligence, yet collecting paired visual--tactile data remains costly. Visual-to-tactile synthesis offers a promising approach to augmenting such data, but learning this mapping is complicated by the gap between visual appearance and contact-related material properties, as well as spatial misalignment in paired observations. To address these challenges, we present \textbf{PhysTacGen}, a visual-to-optical-tactile image generation framework that integrates material-aware descriptions with geometric conditioning. First, we introduce Group Tactile Policy Optimization (GTPO), a reinforcement learning strategy that refines a vision--language model to generate structured material descriptions using task-specific rewards. Second, we combine DINOv2-based pair curation with monocular relative-depth estimation to select training pairs and provide geometric priors. Finally, an SDXL ControlNet synthesizes optical tactile images conditioned on RGB, relative depth, and GTPO-generated text. Experiments on curated SSVTP data demonstrate improved structural similarity over the compared baselines, while a blinded user study shows a preference for GTPO-generated descriptions. Generated tactile inputs also improve performance on an attribute-derived force-coefficient prediction proxy. Together, these results demonstrate the effectiveness of PhysTacGen for optical tactile image synthesis and its utility in the evaluated downstream task.The code will be available at https://github.com/VDIGPKU/PhysTacGen.
embodiedtactile - arxiv:2610.08048 · cs.LGDAEDALUS: Bootstrapping Agent Memory from Self-Generated TasksAntoine Edy, Max Conti, Victor Xing, Marc-Antoine Allard +2
LLM agents often lack the operational knowledge to act reliably in new environments, as they must discover specific tool behaviors or environment conventions on their own. Without memory of past attempts, they repeat the same mistakes across tasks, leading to more task failures and longer trajectories. To address this, agentic systems typically rely on human-written guidelines or on procedural memory built from training tasks and an oracle verifier, both of which require prior knowledge of the environment. We present DAEDALUS, a method for bootstrapping reusable agent memory from self-generated practice without existing tasks or oracle verifiers. DAEDALUS pairs two agents: an explorer that interacts with the environment to generate challenging yet solvable tasks, and a solver that attempts them. A heuristic is derived from each solver failure and accepted only after the solver repeatedly succeeds with that heuristic in context. These outcomes also provide feedback for the explorer to refine the difficulty of future tasks. Accepted heuristics are then consolidated into a memory bank for test-time use. Across AppWorld, $τ^2$-bench, and AutomationBench, DAEDALUS improves mean success rates by up to 15.9 points and pass^5 by up to 2.2x over a no-memory baseline, and is competitive with methods using training tasks, at a lower inference cost than most. We show that performance gains already emerge with a small exploration budget, and that its heuristics also benefit agents from other model families. Our ablations further reveal that solver traces provide the key information needed to derive effective heuristics, while factorizing early discoveries makes exploration more cost-efficient. Beyond memory construction, we find that the tasks generated by DAEDALUS can serve as a proxy for benchmark tasks when ranking models by performance. Code and artifacts: www.github.com/illuin-tech/daedalus.
memoryagent memoryagentllm agentagenticbenchmark - arxiv:2610.08036 · cs.AISame Feedback, Different Answer: Measuring Run-to-Run Instability in Frontier-Model Customer Feedback AnalysisViraj Bagal, Raviraja Ganta, Prabhath Chellingi
AI agents are increasingly being programmed to automate knowledge work over large collections of unstructured data. Such automation requires repeatability: when the underlying evidence is unchanged, the agent's categories, priorities, and counts should not shift materially between runs, even if each individual answer appears plausible. We introduce a repeat-run evaluation framework that aligns semantically equivalent categories and focuses on two operating metrics: theme churn, the normalized change in the returned category set, and volume disagreement, the change in counts for categories that persist. We evaluate three recurring customer-feedback tasks across eight frontier models, corpus sizes from 100 to 5,000 records, multiple prompts, and three execution designs: raw generation, taxonomy-free hierarchical decomposition, and a taxonomy-grounded agent (TGA) using persistent themes, subthemes, and record-level predictions. With Claude Opus 4.8 and the 1,000-record corpus fixed, TGA reduces theme churn by 86--88% relative to both raw generation and hierarchical decomposition, while matched-theme volumes have zero disagreement. The taxonomy-grounded agent is more stable than every raw model in the screen, remains more stable at each corpus size, and keeps this advantage when theme matching is made stricter or looser. Although evaluated on customer feedback, the framework targets repeated synthesis of unstructured corpora more broadly, including financial reports, legal documents, incident records, and scientific literature. Overall, these results show that taxonomy grounding produces more consistent and repeatable outputs for recurring knowledge work.
agentai agentevaluation framework - arxiv:2610.08033 · cs.AILearning in Dreams, Winning in Reality: A Continuous Dyna Loop for a Ten-Hero MOBAJordy Kieto
World models are usually judged from the inside: by prediction loss, by the return a policy earns in imagination, or by how convincing their frames look. We judge one from the outside. We learn a structured, multi-agent world model of a complete ten-hero MOBA (206 units, every hero acting every tick, games of up to 6,000 ticks), train a policy only inside it with 1,400-tick free-running imagined episodes, and measure that policy in the real game against the opponent the game ships with. The real game never provides a gradient; it provides the policy's own games as training data for the world model, and an online evaluation that selects and anchors the policy. Run as a continuous asynchronous Dyna loop, the policy wins 70.2% of real games as radiant (421 of 600; 95% CI 66.4-73.7) on seeds never used for any decision, up from 0% for dream training alone and 33.7% before the loop. It wins none as dire, and neither does the shipped opponent when it plays itself. Four findings explain the result. Model exploitation is invisible from inside the dream: every unanchored run collapsed within a few updates while no in-dream metric tracked the collapse. A world model that is accurate on its training corpus is badly wrong on the policy's own games, and Dyna repairs it there, which is worth +9.2 points of real win rate with the policy recipe held fixed. Finally, the policy inherits its world model's fidelity profile mechanic by mechanic: the model represents the macro game but not crowd control, cast timing or lethality, and the policy wins by map-wide pressure with almost no coordinated fighting. We release the world model, the dream-PPO harness, a world-model debugger, the evaluation protocol, and every policy and log.
world modelmulti-agentevaluation protocol - arxiv:2610.08026 · cs.CLThe Labeling Problem in Hallucination Detection Benchmarks: An Empirical EvaluationJorma Valjakka, Juhani Kivimäki, Juha Mylläri, Jukka K. Nurminen
In recent years, several methods for detecting when large language models (LLMs) hallucinate have been developed. These methods are often benchmarked with open-domain question answering (QA) datasets containing questions and corresponding short reference answers. First, an LLM is used to generate answers to questions within the QA dataset. Then, some automated labeling strategy is used to label these answers as hallucinated or not by comparing them with the reference answers in the dataset. This evaluation setting creates a methodological ambiguity between two criteria: reference faithfulness (whether the answer is fully supported by the reference) and factual correctness (whether the answer is free from contradictions and factually false specific claims). In practice, automated labelers may apply the former criterion even when the intended target is the latter. We study this potential criterion mismatch using 900 human-labeled question-answer pairs spanning three commonly used QA datasets and three generator models, with labels targeting answer-level factual correctness. We evaluate lexical similarity metrics, a reference-entailment NLI baseline, and seven LLM judges under controlled prompt variants as automated labelers. Our experiments reveal substantial disagreement both among automated labeling strategies and between these labels and human annotations. Many strategies also exhibit strong directional error biases, and for most judge-generator pairs, replacing a faithfulness-oriented prompt with a factual-correctness prompt improves agreement with human annotations and reduces false-positive dominance, indicating that automated hallucination labels depend strongly on how the target criterion is specified. Label-source choice should therefore be considered a fundamental part of benchmark design and made explicit, validated, and matched with the benchmark goal.
benchmark - arxiv:2610.08021 · cs.LGSpectra: Exact Component Transport for Test-Time Prior Adaptation in Simulation-Based InferenceXin Zhao, Nico Scherf, Robert Trampel, Kerrin J. Pine +1
Simulation-based inference (SBI) has become a powerful approach to Bayesian inference in complex scientific models whose likelihoods are difficult or impossible to evaluate. Amortized SBI learns reusable inference models from simulated data, enabling rapid posterior inference for new observations, and modern generative models have made these models increasingly expressive. However, this reuse is limited to the prior distribution chosen during training, whereas scientific analyses often need revised priors as knowledge accumulates or alternative assumptions are tested. We introduce Spectra, a test-time adaptation method for diffusion-based SBI. Spectra uses an exact score-transport identity to obtain the adapted score from a frozen diffusion model in closed form for structured prior changes, without additional simulation or training. Across six SBI benchmarks, Spectra achieves accurate adaptation under strong prior shifts at low online sampling cost. This enables pretrained SBI models to incorporate updated prior information at test time.
benchmark - arxiv:2610.08020 · cs.LGLearning consistent molecular mechanics force fields from first principlesBerkay Günes, Leif Seute, Jigyasa Nigam, Frauke Gräter
Classical force fields (FFs) remain the workhorse for large-scale simulations even as machine-learned interatomic potentials (MLIPs) approach ab initio accuracy. They decompose total configuration energies into simple effective interactions whose parameters are traditionally assigned based on atom or bond types, enabling efficient simulations but also limiting their ability to adapt across configurations. Recent machine learning approaches have improved the accuracy and transferability of bonded parameters in these FFs by inferring them as functions of local atomic environments, but still rely on empirical nonbonded parameters for practical simulations. In this work, we introduce a unified approach, \texttt{grappa-fullFF}, which learns both bonded and nonbonded parameters \emph{consistently} and simultaneously from ab initio reference data. By incorporating physically inspired regularization via supervision of the electrostatic potential and an architecture that facilitates charge equilibration, our model recovers accurate electric response properties, achieves state-of-the-art accuracy on geometry optimization benchmarks, and reproduces the conformational sampling of both classical and existing machine-learned FFs, without relying on externally assigned nonbonded parameters.
benchmark - arxiv:2610.08018 · cs.CLStructured but Silent: Probing Capability Requirements in LLM Hidden StatesKyojun Choo, Minsoo Song, Yunju Kang, Chanjun Park
Reliable tool use requires more than triggering a mechanism or matching a query to an API description. Before selecting a specific tool, an agent must first infer the capability requirements implied by the user query. In this paper, we investigate whether these query-side capability requirements are linearly decodable from LLM hidden representations prior to generation, and how this hidden-state accessibility compares with explicit verbal classification. We introduce TACIT, a framework that decomposes external requirements along three fundamental axes: Source, Transformation, and World Effect, defining eight structurally distinct capability classes. Using 1,600 balanced training queries from benchmarks, synthetic examples, and new domain scenarios, we train linear probes on pre-generation hidden states from four open-weight LLM families. Our empirical results demonstrate that fine-grained capability structures are linearly decodable with high accuracy across all models. Crucially, however, we expose a representation-to-verbalization gap: these same models are significantly less reliable when asked to explicitly classify the same queries in natural language. This disconnect indicates that information about required external capabilities is linearly accessible in LLM hidden representations but not reliably expressed, a phenomenon we define as "structured but silent."
agenttool usebenchmark - arxiv:2610.08003 · cs.ROReactive Task-Oriented Robot-Human Handovers via Generative Hypothesis SelectionCarmen Scheidemann, Andreea Tulbure, Pascal Burkhardt, Marco Hutter
When humans hand each other objects, they incorporate both geometric and semantic information into this process. For example, passing a knife with the handle towards the recipient, rather than the blade, is both more ergonomic and safer. Recent state-of-the-art methods for task-oriented robot-human handovers have progressed from modeling object geometry to incorporating object affordances. However, they often forgo predicting the explicit, task-specific hand poses a human selects to utilize an object. Since many objects support multiple interaction modalities, e.g., a claw hammer used to strike or pull nails, this variability must be modeled to achieve robust task-oriented handovers. To tackle this, we propose a novel approach, GENESIS-Handover (GENErative HypotheSIS), which leverages VLM image generation to produce a variety of task-specific hand-object interaction hypotheses. These hypotheses are matched in real time to the observed human hand pose, enabling inference of the most suitable handover configuration. By leveraging VLMs as priors of plausible hand-object interactions, the method produces task-conditioned handover strategies for previously unseen object-task pairs. We evaluate the standalone interaction proposal module before deploying the full system on a mobile manipulator. In a user study with 12 participants across five task-object pairs, 83.3% perceived our method to have better task understanding than the previous state of the art.
manipulator - arxiv:2610.07987 · cs.CVVisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMsYuan Feng, Qize Yang, Ruizhe Chen, Sibo Song +8
Multimodal large language models have become the dominant paradigm for visual understanding, but incur substantial costs by encoding inputs into dense, fixed-size patch tokens. However, visual information is unevenly distributed: some regions require fine-grained detail, while others admit compact representations. Downsampling sacrifices this detail, while existing token pruning and adaptive approaches remain limited in content-adaptive granularity, task generalization, and integration with modern MLLMs and serving infrastructure. Overcoming these limitations calls for foundation models that learn, end to end, where-and at what granularity-to allocate visual representations, a native capability we term elastic visual representation weaving. We introduce VisionWeave, establishing this capability in frontier-level MLLMs through large-scale training. It combines two components: a gated spatial pooler constructs coarse-grained representations alongside native fine-grained representations within a shared MRoPE coordinate, while a granularity router learns their content-adaptive allocation. Through self-distillation alone, we validate this capability on Qwen3.5-4B and scale to Qwen3.8-27B with over 30K A100 GPU-hours. Based on Qwen3.8-27B, VisionWeave adaptively adjusts token savings to visual content, saving 43.0% tokens on average while retaining 98.9% native performance across eight benchmarks, versus only 88% performance preserved for token pruning baselines with a fixed 50% savings target. Extensive evaluations confirm robust efficiency-quality trade-offs across diverse tasks, resolutions and video frames. When deployed on SGLang serving engine, our method achieves a 2.3x throughput gain while reducing mean TTFT by 54.4% and mean TPOT by 60.6%. Together, we believe these results position elastic visual weaving as a promising capability for next-generation multimodal models.
benchmark - arxiv:2610.07984 · cs.CVDecide Before You Look: Learning Which Retrieved Memories Deserve PixelsYouxing LI
Multimodal assistants answer questions from long-term memories that contain images. After retrieval, each retrieved image reaches the answering model either as pixels, at about a thousand visual tokens per image, or as a stored text proxy that often misses the detail the question asks about. We find that the benefit of pixels usually comes from one or two retrieved memories, and that it can be predicted before the answering model runs, without reading any full-resolution image. In PixelTriage, a plug-in placed after retrieval, a small model that does not generate text reads the dialogue, a short note and a thumbnail of each retrieved memory and predicts how much its pixels would add. It is trained on synthetic memory episodes labeled by a frozen 27B model that answers each question with and without each memory's pixels. With a 7B answering model, PixelTriage lies on the accuracy--cost frontier of M$^3$Exam, DMV and MemEye and uses 11--23\% of the visual tokens without a significant loss of accuracy. On DMV it answers 2.9 times faster than opening all images. It outperforms retrieval order and uniform down-sizing at equal budgets and transfers to other memory systems and to a 397B answering model.
memory - arxiv:2610.07982 · cs.CVM3SunAgent: Monocular 3D Spatial Understanding Agent for Metric Depth Estimation and 3D Visual GroundingJinsong Zhang, Kejun Wu, Ming Zhu, Renjie Qiao +2
Monocular metric depth estimation and 3D visual grounding represent the two complementary cornerstones of monocular 3D spatial understanding (M3Sun), from which the fundamental 3D spatial information required by M3Sun can be acquired. However, these complementary tasks are generally conducted by separate frameworks, which pose challenges of inflexible and unaligned spatial information access for embodied intelligence systems. In this paper, we propose a unified agent for monocular 3D spatial understanding (M3SunAgent) that leverages a large language model (LLM) as a task planner for spatial visual programming, which flexibly generate structured programs and coordinate tools. For instance-level metric depth estimation task, M3SunAgent invokes an object detector tool to locate the target, estimates depth at selected points with a depth estimation tool, and aggregates these predictions into an instance-level depth estimate. We also construct the M3Sun Instance (M3SI) dataset, a benchmark with 2,910 samples for evaluation. For monocular 3D visual grounding task, M3SunAgent uses a vision-language model (VLM) tool to locate the target and output basic spatial attributes, then combines back-projection tool with a dimension-lifting tool to predict its 3D bounding box. Experimental results demonstrate the superior performance of M3SunAgent. Specifically, in evaluations of instance-level monocular metric depth estimation, M3SunAgent achieves the best performance among all compared models, 52.61% of predicted instances are distributed below depth error 0.25 ($δ< 0.25$). In evaluations of monocular 3D visual grounding, M3SunAgent demonstrates overall competitive performance than vision and VLM models, reaching a 3D mean intersection over union (mIoU) of 41.73% and exceeding the state-of-the-art MonoVLM model by 3.62%.
embodiedagentbenchmark - arxiv:2610.07981 · cs.LGDo Higher-Order Models Win for Higher-Order Reasons? Rethinking Performance Gains in Hypergraph LearningFanchen Bu, Fan Li, Geon Lee, Sunwoo Kim +3
Higher-order models (e.g., hypergraph neural networks) often outperform lower-order baselines on hypergraph learning benchmarks, and their advantages are commonly attributed to their ability to exploit higher-order information. However, better performance alone does not establish this explanation. We therefore ask: Do higher-order models win for higher-order reasons? To investigate this question, we introduce a controlled performance-attribution framework that perturbs higher-order information while preserving the lower-order, i.e., pairwise, information. Across 25 commonly used hypergraph learning benchmarks spanning three tasks, we frequently observe an intriguing pattern: higher-order models originally outperform lower-order baselines, yet retain most of their advantage after perturbation. This suggests that much of the observed advantage remains achievable without the higher-order information. We then investigate potential lower-order explanations for these remaining gaps. We find that simple additions to a lower-order baseline, e.g., richer pairwise weighting, more steps of pairwise feature propagation, and normalization, reduce the remaining performance gaps, supporting lower-order explanations for part of the observed advantage. Our analysis calls for the hypergraph learning community to rethink performance attribution by distinguishing performance gains from their explanations, adopt stronger lower-order baselines, and use suitable benchmarks that better test the value of higher-order information.
benchmark - arxiv:2610.07979 · cs.AILearning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving AgentsQianhan Feng, Zhongzhen Huang, Yakun Zhu, Xiaofan Zhang +1
As agents continuously improve by generating and revising Skills, the process that discovers and refines those Skills becomes a learnable object in its own right. Task-Skills directly act on task execution, whereas Meta-Skills govern how agents discover and improve future Skills; their value therefore emerges through the subsequent search processes they induce. Existing approaches improve Meta-Skills from observed raw Skill-search trajectories and branch outcomes. However, branch performance entangles the effects of the initial discovery state and the Meta-Skill revision that generated the search process, making it difficult to characterize what a particular revision actually changed, and pushing updates toward revisions that benefit from favorable states rather than those that improve the process. We introduce HMED (Hindsight Meta-Experience Distillation), a mechanism for constructing Meta-Experience for self-improving agents. HMED revisits the completed event from which a revision originates and re-executes the incumbent and revised Meta-Skills from the same restored discovery state, so that the changes associated with the revision can be observed under a shared condition. Each comparison is distilled into a Meta-Experience, a structured record that can be reused by future updates, so that even revisions that are not ultimately retained still contribute a learning signal. Across three interactive agent benchmarks and both open-source and closed-source models, HMED consistently improves Skill discovery performance over strong baselines, shifting Meta-Skill learning beyond branch outcomes toward the consequences of changing the improvement process.
agentagent benchmarkself-improvingbenchmark - arxiv:2610.07969 · cs.ROEmbodiedSmith: Scaling Embodied Data through Recursive Self-Improvement Flywheel in SimulationYikai Qin, Yifei Deng, Mingjian Liang, Wenxuan Song +12
Scaling robotic foundation models requires diverse training data and reliable evaluation environments. Simulation offers a scalable solution, yet existing generation pipelines remain constrained by predefined assets and skills, a disconnect between scene generation and task generation, and limited support for complex embodiments and physics. We introduce EmbodiedSmith, a framework for scalable embodied data generation through recursive self-improvement (RSI). EmbodiedSmith unifies asset, scene, and task generation in a pipeline that supports autonomous creation and language-driven customization. Its core is an agentic refinement loop: scene generation anticipates downstream task requirements, while task generation guides targeted scene edits, allowing scenes and tasks to iteratively improve one another. This joint refinement improves task generation success, including for long-horizon tasks. The framework further supports mobile manipulators, humanoids, and dexterous hands, as well as interactions involving deformable objects and fluids, broadening the range of behaviors and physical phenomena represented in generated data. Together, these capabilities provide a flexible simulation engine for both robot pretraining and evaluation. Extensive experiments validate the quality, diversity, and generation efficiency of the resulting data, while downstream policy experiments demonstrate that increased data diversity improves generalization.
embodieddexteroushumanoidmanipulatoragenticself-improvement - arxiv:2610.07967 · cs.LGDecepEval: A Benchmark for Evaluating Deception in LLM AgentsYiming Xu, Hongyue Yu, Beihua Yang, Zihan Chen +7
As large language model (LLM) agents become increasingly autonomous, they may pursue task performance through deception, raising concerns about their reliable deployment. Existing evaluations show that LLM agents can deceive, but often examine isolated scenarios or narrowly defined conditions, limiting systematic understanding of when deception becomes more likely. To address this gap, we introduce DecepEval, a benchmark comprising 1,532 instances across 3 task families and 28 professional scenarios. Drawing on classical fraud theories, we propose the LLM Deception Diamond framework, which characterizes four external conditions that may induce deception: pressure, incentive, opportunity, and conflict. DecepEval pairs neutral and induced versions of each instance to measure condition-dependent changes in deception rates, while explicit task facts and observable agent behavior help distinguish deception from capability-related errors. Evaluations of nine frontier LLMs show that inducements increase deception across models and task families, even among models with low baseline deception rates. DecepEval makes these vulnerabilities measurable, providing a shared benchmark for progress toward trustworthy artificial intelligence.
agentllm agentbenchmark - arxiv:2610.07962 · cs.AIReGraph: A Computational Account of Emergent Generalization in the "what" and "where" Dual Visual StreamsHyewon Kang, Jungmin Lee, Ilgyu Lee, Seok-Jun Hong
Where generalization capacity--the ability to extract context-invariant relational structures--first emerges remains a central question in AI and neuroscience. The foundation for this capacity lies upstream of the hippocampus, within the entorhinal cortex, where parallel pathways dissociate relational structure in the medial entorhinal cortex (MEC) from sensory content in the lateral entorhinal cortex. However, as Eichenbaum argued, such factorization likely originates earlier, driven by the segregation of the dorsal ('where') and ventral ('what') visual streams. Supporting this, grid-like firing patterns--a signature of MEC (context-invariant codes)--also appear in preceding neocortical regions along the dorsal pathway. Yet, how such representations are computationally formed along upstream pathways remains unknown. To investigate this in silico, we developed ReGraph, a recurrent dual-stream graph model with biological inductive biases, including retina-driven stream-specialized encoding, dorsal-to-ventral modulation, and dynamic lateral connectivity. Trained on the action benchmark Something-Something V2, ReGraph revealed a pathway-specific emergence of relational mapping: context-invariant codes and grid-like spatial bases uniquely co-emerged along the extended dorsal stream. In contrast, their absence in single-stream, unmodulated variants, and standard baselines implies that these inductive biases are prerequisites for relational structures. Crucially, our post-hoc analyses demonstrated that these grid-like bases serve as reusable routing templates for information processing via lateral connectivity. Together, our findings provide a computational account that generalization may not be a faculty that emerges abruptly within a dedicated region, but a property that already takes shape as sensory information is parsed into factorized streams of hierarchical visual processing.
benchmark - arxiv:2610.07961 · cs.ROIronMan: Information-Constrained Video-Action Learning for Robot ManipulationYuanshuo Zhang, Wenzhe Zhao, Zixing Lei, Bin Chen +1
Video Action Models (VAMs) couple visual dynamics modeling with action generation for robot manipulation. However, video representations are not naturally suited to action generation, as exposing the action policy to excessive visual detail can impair its generalization ability. Therefore, we introduce IronMan (Information-constRained videO-actioN learning for robot MANipulation), a robust video-action learning framework built on the information bottleneck principle. The core principle of this framework is to impose information constraints that suppress irrelevant visual information while preserving action-relevant dynamics cues. IronMan employs a dynamics-aware bottleneck that distills noisy, entangled one-step video features into compact world representations. Extensive simulation and real-world experiments demonstrate strong in-distribution (ID) performance and out-of-distribution (OOD) robustness while maintaining efficient inference. IronMan achieves success rates of 99.0% on LIBERO and 79.4% on RoboTwin clean2clean, outperforming all the evaluated baselines. Under OOD shifts, IronMan achieves a success rate of 79.1% on LIBERO-Plus, exceeding the strongest baseline by 10.4 percentage points. Project page: https://youngsoul0731.github.io/ironman-project-page/
manipulationliberorobotwin - arxiv:2610.07958 · cs.CVDensiTok: Making Feed-Forward 3D Gaussian Splatting See More Views Than It Is GivenMinhyeok Lee, Jungho Lee, Minseok Kang, Heeseung Choi +2
Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a scene in a single forward pass, replacing per-scene optimization with a network trained across many scenes. Its quality, however, degrades sharply as the number of input images drops. The bottleneck is upstream of the reconstruction heads: from a few unposed views, the internal representation they read carries no evidence for unobserved regions, leaving holes, floaters, and blur. The common remedy supplies that evidence as pixels, synthesizing extra views with an image or video generator and re-encoding them, which is costly and not 3D-consistent by construction. We instead densify the evidence itself. We present DensiTok, a plug-in module for pretrained feed-forward 3DGS models that densifies their internal geometry tokens directly, making a frozen backbone behave as though it had observed many more views than it was given. DensiTok compresses those tokens into a compact latent space, completes the latents of the unobserved viewpoints in a single flow-matching step conditioned on camera geometry, and decodes them back into tokens that the original reconstruction heads. The same module design can be integrated into different pretrained predictors while keeping each backbone and its reconstruction heads frozen. Completion in a low-dimensional latent space requires no image synthesis or additional encoder passes. Across three pretrained backbones and two benchmarks, DensiTok consistently improves sparse-view reconstruction and recovers much of the gap to dense-view reconstruction.
benchmark - arxiv:2610.07954 · cs.CVRevisiting Numerical Forecasting Models for Language-Based Trajectory PredictionJunGyu Lee, Inhwan Bae, Hae-Gon Jeon
Language-based trajectory predictors represent coordinates as discrete tokens and learn auxiliary tasks such as destination and group reasoning. This formulation enables the model to capture behavioral intent and social context beyond coordinate dynamics alone. However, token-level objectives provide only indirect guidance for continuous coordinate-space dynamics. To address this limitation, we introduce MoRE (Mixture of Reward Experts), a refinement framework that transfers numerical forecasting priors into a pretrained language-based predictor through reinforcement learning. Five frozen numerical predictors provide complementary coordinate-level knowledge of motion and interactions. Their predictions are converted into expert rewards and combined through an uncertainty-weighted consensus that penalizes disagreement. A ground-truth reward anchors the prediction to the target trajectory. To focus refinement on difficult cases, MoRE refines the policy using the top 1% of training samples ranked by predictive entropy. Expert predictions are computed once and cached before PPO training, so the experts are not run during policy updates or inference. In this way, MoRE combines the contextual modeling of the language-based predictor with coordinate-level feedback from numerical experts. On ETH-UCY, MoRE reduces ADE from 0.22 to 0.20 m and FDE from 0.32 to 0.29 m. Relative to the base policy, ADE decreases by 17.9% on SDD and 12.7% on NBA. On ETH-UCY, MoRE also reduces collision rates and better matches ground-truth pedestrian spacing, without increasing measured inference memory or latency. The project page is available at https://jungyu0413.github.io/MoRE/.
memory - arxiv:2610.07949 · cs.ROCommit While Futures Agree: Consequence-Aware Adaptive Action Chunking for Robot ManipulationYuyan Li, Yujia Wang, Yusong Huang, Junjie Yang +7
Action-chunking policies predict multi-step control sequences, but a fundamental question remains: how much of a predicted action chunk should be committed before replanning? Existing systems typically execute a fixed-length prefix, implicitly assuming that the same execution horizon remains trustworthy across states. Some adaptive methods estimate this horizon from the similarity or stability of predicted actions. However, different actions may lead to the same successful outcome, whereas similar actions can produce different futures, suggesting that commitment should be determined by agreement among imagined futures rather than by similarity in action space. To this end, we propose Consequence-Aware Adaptive Action Chunking (CA$^3$C), an inference-time framework built on a simple principle: commit while imagined futures agree, and replan when they diverge. Without modifying or retraining the base policy, CA$^3$C uses an action-conditioned world model to imagine the future consequences of multiple candidate action chunks under the same sampling noise. Using these imagined consequences, we formulate execution-horizon estimation as a Bayesian change-point inference problem and select the execution candidate through future consensus. Across multiple simulation benchmarks and real-world robot manipulation tasks, CA$^3$C consistently improves diverse action-chunking policies, achieving up to a 71.8% relative reduction in failure rate over the corresponding base policies.
manipulationaction chunkingworld modelaction-conditionedbenchmark - arxiv:2610.07948 · cs.AIConfidence Reasoning Graphs: Structured Confidence Estimation for LLM AgentsBrendan King, Farima Fatahi Bayat, Jean-Flavien Bussotti, Pouya Pezeshkpour +1
When using an LLM agent in a consequential domain, making an informed decision about whether to trust its output or intervene requires calibrated confidence in the agent's success. Confidence estimation for agents is difficult because evidence about success is distributed across heterogeneous, interdependent steps of an agent's trajectory. Practical agentic deployments introduce further challenges: frontier LLMs often provide limited access to internal signals, agent roll-outs are costly, and training data may be unavailable or quickly become outdated. To address these challenges, we introduce Confidence Reasoning Graphs (CRGs), an inference-time framework that estimates the probability an agent accomplished its task from a single trajectory, without privileged model access or training data. Rather than compressing an execution into a single holistic judgment, a CRG begins with the claim that the agent accomplished its task, decomposes it into contextualized sub-claims grounded in trajectory evidence, estimates confidence for each terminal claim, and finally aggregates these into an overall confidence estimate. Across three agentic benchmarks, three backbone models, and three agent frameworks, CRGs yield better-calibrated confidence and stronger risk-aware decision making than verbalized, sampling-based, and white-box surrogate baselines. We further find that calibration error alone can be misleading: a white-box surrogate baseline appears well calibrated while providing near-chance discrimination. Ablations attribute CRG's improvements to claim-level confidence estimation and aggregation rather than graph construction alone. Finally, a CRG exposes the claims and trajectory evidence underlying each confidence estimate, enabling it to be audited at decision time.
agentllm agentagenticagent frameworkbenchmark - arxiv:2610.07946 · cs.ROAdapting Vision-Language-Action Models to Unknown Visual Disruptions During ExecutionAhin Lee, Jinwoo Seo, Youngsoo Jang, Taesik Gong
Visual disruptions can arise while a robot is executing a task, leaving a vision-language-action (VLA) policy to respond without knowing the disruption type or timing. We introduce Self-supervised Adaptation from Leftover Trajectories (SALT), which uses the leftover trajectory, the unexecuted part of the previous action chunk, as self-supervision for test-time adaptation. Because consecutive chunks overlap in time, the leftover provides a temporally aligned target for the current prediction over the same future control interval. At the onset of a visual shift, the leftover can retain a plan formed before the corruption, so updating the policy toward it anchors the adaptation across the shift (Transition Anchoring). SALT keeps the adapted policy and regenerates the current chunk, whose leftover becomes the target at the next replan, carrying the correction forward along the execution trajectory (Sequential Correction Propagation). Supervision comes entirely from the policy's own predictions, requiring no disruption annotations, expert actions, or target-domain demonstrations, and a lightweight adaptation gate calibrated only on nominal trajectories decides when updates begin. On LIBERO-10, SALT increases average success across five persistent visual corruptions from 43.9% to 53.2% with SmolVLA and from 58.7% to 66.0% with GR00T N1.7, while largely preserving nominal performance. On a real robot, it raises task progress averaged over digital and physical disruptions from 0.49 to 0.61.
vision-language-actiongr00tlibero - arxiv:2610.07940 · cs.AIHybrid Latent Attention for Looped Language ModelsYuhan Chen, Siyuan Zhang, Nan Wang, Feiyang Kang +1
Looped language models apply the same stack of layers T times to each token, which deepens the model without adding parameters but multiplies its key-value (KV) cache by T. The larger cache limits how many sequences a GPU can decode at once and slows each decoding step, which reads the whole cache. We propose Hybrid Latent Attention (HLA), which keeps exact keys and values within a sliding window of W recent tokens and stores each older token as a compact latent that the query of each loop reads directly, without reconstructing keys and values. We uptrain HLA on Ouro looped models (T=4) with 1.4B and 2.6B parameters, keeping the pretrained weights frozen and training only the added parameters to reproduce the original attention. The cache shrinks by 10.7x per token, fitting 4.0-8.8x as many concurrent sequences per GPU, and decoding throughput improves by 2.5x at 1K-token contexts and by up to 7.4x at 16K. HLA retains over 97% of the original accuracy on math, knowledge and reasoning benchmarks, and 96-100% on long-context retrieval up to 16K tokens. After supervised fine-tuning, it performs on par with the fine-tuned original model on competition-level math.
long-contextbenchmark - arxiv:2610.07939 · cs.CVCCDF: A Benchmark Dataset for Deepfake Detection in Real-World Surveillance FootageBaptiste Chopin, Thomas Swearingen, Arun Ross, Antitza Dantcheva +1
Due to rapid advances in Generative AI, commercial video generation tools can be used to produce fabricated surveillance footage that can fool both human viewers and automated synthetic video detectors. Since these tools are so widely accessible, a malicious user can create a harmful video clip at minimal cost. The production and dissemination of such videos in high-stakes settings, such as crime reporting and elections, can misdirect emergency response efforts or distort political discourse. Existing deepfake video datasets, used by the research community to develop deepfake detection algorithms, exhibit two limitations: (1) they emphasize benign web content rather than footage of possibly malicious activity, and (2) they rely on older or open-source generators that do not represent recent advances in generative systems. We assemble CCtv DeepFakes (CCDF), a video deepfake dataset, to address both gaps. CCDF contains 1840 videos (460 real and 1380 generated) spanning 16 crime and accident categories, with generated content produced using three leading commercial systems: Grok Imagine, Google VEO 3.1, and OpenAI Sora 2. CCDF is a highly realistic, small-scale, manually annotated dataset targeting evaluation of detection models. We release three versions of the dataset: the raw generated data, a cleaned version in which video metadata are standardized between real and synthetic samples to prevent detectors from exploiting trivial cues, and an altered version simulating low-effort post-processing attacks. We evaluate CCDF with ten recent state-of-the-art detectors covering different detection approaches. Our results suggest that these approaches do not reliably distinguish CCDF's generated videos from real ones, despite their strong reported performance on existing datasets. These results further confirm that existing datasets are not well-suited to evaluating certain threats.
benchmark - arxiv:2610.07937 · cs.CLLeveraging a four-quadrant approach for evaluating Redpine ScienceFilip Dorm, Leonora Vesterbacka
Redpine Science gives models and agents a single access point to a wide range of peer-reviewed literature, queried directly through the Model Context Protocol (MCP) and an API. This report evaluates Redpine Science on two levels: the relevance of the retrieved chunks, and a model's answer when it has access to Redpine Science compared to web search. Both public and expert-validated benchmarks are used. Public benchmarks are a widely accepted way to test model development and are comparable across labs, but risk saturation and memorization. To address this, we complement them with an expert-validated question set. In total, this report presents four evaluations. On ScholarQABench SciFact, the public answer-quality benchmark reported here, an agent with Redpine Science answers 94.4% of claims correctly against 87.6% with no retrieval. On the expert-validated question set, an agent with Redpine Science states 80.1% of the required claims against 70.2% for an agent restricted to web search. On the 668 queries of a public retrieval benchmark whose gold paper Redpine holds, stripped of any model reasoning, Redpine Science places the correct source paper in its top ten results for 83.1% of queries (Recall@10), against 79.3% for the benchmark's creator. A blinded expert relevance panel places Redpine Science's Precision@5 at 75.2% against 39.8% for the PubMed search tool. We release the expert-validated question set and instructions to reproduce every headline result above, at https://github.com/redpine-ai/benchmarks.
agentbenchmark - arxiv:2610.07935 · cs.AISIGMA: Self-Improving Alignment Generalization from a Model SpecJingyu Zhang, Shruti Palaskar, Daniel Khashabi, Benjamin Van Durme +2
LLM agents are increasingly capable of executing complex tasks and of recursively improving themselves on easy-to-verify objectives such as software engineering and mathematics. Since alignment is much harder to verify, this creates a growing risk of capabilities increasing without appropriate safety alignment, especially as capabilities expand to auto-research and cybersecurity. Existing approaches focus on capability self-improvement using verifiable feedback or on alignment training with supervision from stronger models or curated data, creating an external supervision bottleneck for alignment. We ask whether current models can improve their own safety alignment, and propose SIGMA, a data generation and training pipeline enabling alignment self-improvement that generalizes to out-of-distribution settings. Given only a "Model Spec" stating the model's desired behavior, SIGMA leverages a model's reasoning capabilities to strengthen its own safety reasoning. SIGMA first performs spec-guided task synthesis, using the candidate model as a task designer agent to generate diverse alignment dilemma scenarios and convert them into training tasks that stress-test its understanding of the Model Spec. Next, SIGMA conducts self-judged alignment training through supervised fine-tuning and rubric-based reinforcement learning with the model itself as the reward model. Despite training only on single-turn chat data, SIGMA improves safety alignment in multi-turn agentic environments (AgentHarm harmfulness decreases from 22.6 to 14.8; Agentic Misalignment decreases from 79.1 to 3.8), outperforms Deliberative Alignment and Constitutional AI baselines, and retains general capability. Analyses show that a Model Spec balancing harmlessness and helpfulness, test-time reasoning for safety deliberation, and high-quality rubrics from SIGMA's task designer agent are crucial for effective self-improvement.
agentllm agentagenticself-improvingself-improvement - arxiv:2610.07928 · cs.CVDynamic Alignment and Calibration for Multimodal LearningJinghao Xu, Zhenhua Guo, Xiaofeng Zhu, Xiaoshuang Shi
Dynamic multimodal learning aims to learn robust representations by adaptively modeling information discrepancies across modalities. However, existing methods still suffer from two limitations: (i) static cross-modal alignment strategies usually impose uniform constraints on all samples while overlooking sample-wise variations, potentially leading to unreasonable over-alignment; and (ii) confidence- or uncertainty-aware fusion methods often fail to adequately account for feature magnitude and confidence differences across modalities. For modality pairs with significant feature magnitude differences or small confidence gaps, it might be unreliable to strictly align fusion weights according to confidence. To address these issues, we propose an Alignment- and Calibration-driven Multimodal Learning framework (ACML). Specifically, ACML incorporates a dynamic cross-modal triplet alignment module, which enforces strong semantic consistency for high-confidence positive pairs while encouraging diverse representation learning between high- and low-confidence positive pairs according to their confidence gaps. Additionally, ACML introduces a difference-aware attention calibration strategy that adaptively adjusts attention regularization based on feature magnitude and confidence differences across modalities, thereby mitigating biases caused by unreasonable fusion constraints. Extensive experiments on multiple multimodal benchmark datasets demonstrate that ACML consistently achieves superior performance and robustness over recent state-of-the-art methods.
benchmark - arxiv:2610.07922 · cs.ROOpenWAM: An Open Framework for Composable World-Action ModelsHeng Yu, David D. Yuan, Juze Zhang, Changan Chen +6
World-action models (WAMs) couple future prediction with robot control, yet existing systems often vary the video backbone, interaction structure, supervision, and inference procedure simultaneously, making their design choices difficult to compare. We introduce OPENWAM, an open world-action modeling framework built around a common causal robot-video foundation and configurable video-action interaction. Starting from Wan2.2-5B, we perform causal robot-video pretraining on over 10,000 hours of video, then integrate an action expert through a shared Mixture-of-Transformers architecture that supports joint, video-then-action, action-then-video, and decoupled generation. OPENWAM achieves high success rates on four LIBERO suites and real-world bimanual tasks; robot-video training with causal adaptation improves VTA success on LIBERO-Long from 68.4% to 97.8%. The same configurable architecture naturally extends to inverse and forward dynamics, allowing us to study how counterfactual transitions improve independently trained dynamics models beyond demonstrations alone. When only the video predictor is adapted to a new task, a frozen local-context inverse dynamics model trained on counterfactual data and demonstrations achieves 84.0% mean success across four held-out LIBERO-90 tasks, compared with 47.0% for a full-context inverse model and 21.5% for a local-context model trained only on demonstrations. For forward dynamics, counterfactual supervision reduces RGB prediction error by 34.5% and raises outcome identification from 21.1% to 71.3% among 16 same-state outcomes. OPENWAM provides a common testbed for comparing WAM interaction designs and for studying dynamics learning from video data beyond successful demonstrations.
libero - arxiv:2610.07917 · cs.ROPACE: Stage-Consistent Long-Horizon Robot Manipulation via Progress-Aligned Context for ExecutionYenan Chen, Junjie Shi, Lu Chen, Zhongxiang Zhou +1
Demonstration-conditioned policies provide a natural interface for specifying robot behavior, yet long-horizon manipulation remains difficult when visually similar states recur across different stages or when demonstrations and executions proceed at different speeds. We identify the resulting failure mode as stage confusion and introduce Progress-Aligned Context for Execution (PACE), a stateful method that continually reinterprets a complete demonstration according to realized execution progress. PACE compresses the demonstration into ordered multimodal prompt tokens and uses training-only dual-edge attention supervision to expose its latent stage structure. During execution, an episode-local fast-weight memory causally encodes realized action-observation transitions and modulates prompt cross-attention, producing a progress-aligned context for a unified diffusion action expert without test-time stage labels or stage-specific policies. PACE improves success from 88.9% to 94.0% on LIBERO-Gen Goal Chain, from 79.1% to 83.3% on Spatial Combination, and from 33.3% to 73.3% on the two-step Block Routing tasks. Failure analysis further indicates that structured demonstration alignment and causal execution memory jointly mitigate stage confusion.
manipulationliberomemory - arxiv:2610.07916 · cs.CVCan We Model the Artifacts Explicitly? Disentangle Artifacts via Pairwise Edit Relations for Image Manipulation LocalizationXuekang Zhu, Kaiwen Feng, Ruifeng Wang, Xiwen Wang +9
Image Manipulation Localization (IML) is commonly formulated as a fully supervised learning task that estimates the optimal manipulation mask $y$ for a given image $x$. In this work, we first reveal the latent nature of artifacts and thus reinterpret IML as a latent-variable problem, $P(y|x)=\int P(y|z)\,P(z|x)\,dz$, where $z$ denotes the artifacts. Following this interpretation, we pinpoint the cause for the current IML models' insufficiency as their implicit artifacts modeling strategy, highlighting the necessity of modeling $z$ in an explicit manner. Without direct labels, feature disentanglement is the most appropriate solution for this explicit modeling. Accordingly, we propose a two-stage learning paradigm with the Pairwise Artifacts Learning (PAL) and Standard Localization (SL) phases to estimate $P(z|x)$ and $P(y|z)$ via edit relations. To support our edit-relation-based learning, we further curate EditGroup-45K, a source-anchored dataset organized into edit groups for pair construction. Extensive experiments show that our PAL paradigm yields consistent improvements across diverse IML architectures, and empirical analyses further verify that PAL does capture artifacts explicitly through feature disentanglement. Code and dataset are available at https://github.com/venus-guangjian/PAL
manipulation - arxiv:2610.07913 · cs.CVMultimodal Knowledge Distillation for Gastric Adenocarcinoma Classification from Whole-Slide ImagesShrihari Dumbre, Bikash Santra
Gastric adenocarcinoma (GA) is a leading cause of cancer-related mortality worldwide, and accurate histopathological subtype classification from whole-slide images (WSIs) is essential for effective treatment planning. While multimodal approaches that integrate pathology report text with WSIs can improve classification, existing methods often depend on computationally expensive transformer architectures and large language models. We propose a multimodal knowledge distillation (MKD) framework that combines a pretrained WSI image encoder and a clinical text encoder using Low-Rank Multimodal Fusion (LMF) to efficiently model cross-modal interactions during training. Each WSI is represented as a bag of patches paired with a slide-level diagnostic caption. The teacher model learns fused image-text representations for subtype classification, while the student model distills this knowledge to enable accurate image-only inference. We evaluate our method on the PatchGastric benchmark dataset and achieve at least 3.35% higher mean accuracy than state-of-the-art approaches, without relying on transformer-based fusion, multi-task learning, or large language models. The source code is available at https://github.com/helomelo1/MKD-LMF.
benchmark - arxiv:2610.07907 · cs.AIContinuous Memory MachinesCiaran Regan, Kai Arulkumaran, Luke Darlow, Stefania Druga +2
Recurrent neural networks typically compress information into a single vector-valued recurrent state, forcing short-term computation and long-term retention to share the same representation. Past extensions alleviate this bottleneck by increasing the memory capacity or separating timescales, but lack the combination of rapid neuron-level processing and longer-term retention found in biology. To that end, we introduce the Continuous Memory Machine (CMM), a recurrent architecture with matrix-valued short- and long-term memory states serving distinct functional roles. Building on the Continuous Thought Machine (CTM), the CMM's short-term memory tracks recent neural activity, with uniquely parameterized neuron-level models learning to use these activity patterns for computation. A persistent long-term memory stores information for later use, with a Transformer jointly updating both memory stores, providing an expressive bidirectional read--write mechanism such that each store can reorganize its own contents and both read from and write to the other. Across algorithmic, in-context learning, and recurrent reasoning tasks, the CMM outperforms a broad suite of baselines, exhibiting stronger generalization than prior memory-augmented networks while preserving the CTM's interpretable attention patterns. Code is available at https://github.com/SakanaAI/continuous-memory-machines.
memory - arxiv:2610.07903 · cs.CVUnsupervised Long-Tailed Adaptation of Vision-Language ModelsKeliang Chen, Yaxin Hou, Hui Liu, Yuheng Jia
Adapting vision-language models to downstream tasks has achieved remarkable success by leveraging pseudo-labels generated from unlabeled data. Existing methods typically assume a uniform unlabeled data distribution, and thus the resulting pseudo-label distribution is likewise uniform. However, real-world data distributions are often long-tailed. To tackle this, we formalize a new scenario termed Unsupervised Long-Tailed Adaptation (ULTA). Under this scenario, existing methods exhibit a contrasting phenomenon: head-class performance drops sharply, which is distinct from supervised long-tailed learning where tail classes suffer the most. In particular, we uncover that the distributional mismatch not only erodes head-class boundaries, but also pushes head samples into confusable classes, reinforcing the model's inherent bias. To address these issues, we propose a novel model called Margin-Aware Refinement with Structural alignment (MARS). Specifically, we mitigate head-class boundary erosion via Boundary-Preserving Alignment, which takes the zero-shot VLM as a fixed visual reference to suppress probability increases that lack visual support in the training targets. Building upon this, we introduce Margin-aware Self-Refinement, which employs a dynamic adjustment strategy to refine tail and confusable classes while preventing prediction bias. Extensive experiments on nine benchmark datasets demonstrate that MARS outperforms state-of-the-art methods, achieving an average accuracy improvement of 4.71 percentage points.
self-refinementbenchmark - arxiv:2610.07902 · cs.CLARIA: Audio-Driven Melody-Tone Relation Modeling for Cantonese Lyric AuthoringShengyu Li, Jinting Wang, Li Liu
Cantonese lyric writing requires close alignment between lexical tones and melodic pitch. Existing melody-guided lyric generation methods typically rely on symbolic melody to generate lyrics. However, in real songwriting scenarios, melodies are often expressed as raw singing audio or hummed recordings, where pitch is implicit, noisy, and unstructured, making these methods difficult to apply directly. To address this limitation, we propose ARIA, a two-stage audio-driven melody-tone relation modeling framework for Cantonese lyric authoring that generates Cantonese lyrics from singing recordings with provided character-level timestamps. Specifically, we first design a Tri-Stream Relation-Aware Tone Estimator (TRATE) to predict 0243 sequences from timestamped singing audio by modeling multi-stream acoustic cues and relational tonal structure. We then propose a Decoupled Retrieval-Augmented Tone-Conditioned Lyric Generator (DRA-TCLG) to generate fluent lyrics conditioned on predicted tonal plans with retrieval-enhanced lexical guidance. Moreover, we construct a large-scale aligned audio-Jyutping-0243 dataset from real Cantonese singing recordings to support this new task. Experimental results demonstrate that ARIA achieves strong performance in both 0243 prediction and tone-consistent lyric generation, validating the effectiveness of the proposed framework.
retrieval-augmented - arxiv:2610.07898 · cs.LGFC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering AgentsJia Liufu, Bin Hu, Linglin Jing, Terry Kong +4
Repository-level software engineering (SWE) is a challenging long-horizon setting: agents must reason over extended interactions, use tools, and adapt to stateful environments. Recent work trains SWE agents with reinforcement learning methods such as Group Relative Policy Optimization (GRPO), which independently sample multiple trajectories per issue, test the resulting patches, and compare terminal rewards within a fixed group. However, this training setup does not reuse verifier feedback from failed patches as context for subsequent attempts, even though this feedback contains valuable diagnostic information about what went wrong. Training on recovery trajectories is challenging because the preceding outcome determines whether the next trajectory is generated, while the failed execution determines its conditioning context. We introduce FC-SWE, a failure-conditioned RL framework that incorporates recovery attempts into policy training. After a patch fails verification, FC-SWE restores the repository to its original task state and uses the failed patch and verifier feedback as context for a recovery trajectory. FC-SWE adapts GRPO to these chains of complete, multi-turn tool-use trajectories through two mechanisms. Trajectory-local rewards preserve each attempt's verifier outcome, preventing recovery success from rewarding an earlier failed patch. Active-set advantage estimation forms a comparison group from all initial and recovery trajectories actually executed for the same issue, so failed attempts remain in the group while unexecuted attempts are excluded. On all 500 SWE-bench Verified tasks under a verifier-assisted protocol, FC-SWE with Qwen3.5-4B and SWE-agent achieves 41.7% Resolved@1 and 52.8% Resolved@2, compared with 38.9% and 48.5% for GRPO. Although trained with at most two attempts per chain, FC-SWE reaches 70.7% Resolved@11 under an eleven-attempt test-time budget.
tool-use - arxiv:2610.07894 · cs.LGRethinking Faithfulness in LLMs: A Pairwise Context-Sensitive PerspectiveZizhuo Zhang, Xiong Peng, Jingwei Sun, Rong Yao +2
Large language models (LLMs) are expected to answer questions faithfully based on the provided context, abstaining when the context information is insufficient to answer the questions. Existing faithfulness evaluations typically assess each question-context instance in isolation; however, such instance-level evaluation fails to capture a fundamental requirement of faithful behavior: the ability to adapt model responses to changes in available contexts. In particular, a model should provide correct answers when sufficient evidence is present and abstain when it is not. In this work, we propose a Pairwise Faithfulness Benchmark (PFaithBench) that evaluates whether a model can switch between answering and abstaining for the same question under supporting versus non-supporting contexts. Our evaluations across thirty-nine models with seven model families demonstrate that faithfulness fundamentally involves a trade-off between answering and abstaining, and that most current models exhibit a strong bias toward answering, with most faithfulness errors arising from over-answering, i.e., models tend to fabricate a response even when the provided context is insufficient. We further conduct a series of studies on faithfulness training under different data constructions. Our results show that training outcomes are highly sensitive to the specific composition of answering and abstaining data. Constructing answering and abstaining data from mismatched sources can cause models to rely on dataset-specific shortcuts rather than actual context sufficiency. Moreover, increasing answer-supervised data improves answering performance but exacerbates over-answering, while increasing abstaining data reduces hallucination but leads to over-abstention. The code and data are released at https://github.com/tmlr-group/PFaithBench.
benchmark - arxiv:2610.07891 · cs.ROBeyond Retargeting: Low-Latency and Robust Humanoid Whole-Body Teleoperation with Learned Atomic Motion PrimitivesXiayan Xu, Jiyu Yu, Xingzhou Chen, Siyi Qian +4
Humanoid whole-body teleoperation translates human motion into stable robot behavior in real time. Existing systems typically rely on online motion retargeting to bridge human--robot morphological differences, but this process adds latency and can produce physically infeasible targets. Meanwhile, diverse, noisy, and partial human-motion observations often fall outside the training distribution, potentially causing unstable robot behavior. We propose a retargeting-free policy that maps raw human motion directly to robot joint commands in a single forward pass, eliminating online kinematic adaptation. To improve robustness, we learn a codebook of full-body motion primitives that projects out-of-distribution observations onto plausible motion prototypes and recovers full-body motion from partial inputs. Experiments on a Unitree~G1 in simulation and on hardware, using virtual reality, optical mocap, text-to-motion generation, and monocular video inputs, show that our method outperforms baselines in latency and robustness.
humanoidteleoperation - arxiv:2610.07887 · cs.CVVisual Abstention in Unified Multimodal ModelsChufan Shi, Cheng Yang, Tiannuo Yang, Isadora White +3
Unified multimodal models (UMMs) integrate understanding and generation, yet their generative behavior is rarely governed by what they understand about the task. We formalize visual abstention: when a requested visual transformation is impossible under the task's rules, the model should recognize that no valid solution exists, state this, and decline to generate. We introduce Draw-or-Decline (DoD), a benchmark of 1,050 feasible-infeasible request pairs across 7 task categories that jointly measures editing success and the refusal of infeasible requests. Evaluating 8 UMMs, we find that editing ability and abstention are distinct capabilities: even the strongest editor, at 68.4% editing accuracy, refuses only 0.4% of infeasible requests under ordinary instructions. Their reasoning shows why: the models rarely notice the conflict, and instead plan the edit as if the request were possible, often describing objects that are not in the image, or quietly change the request into one they can complete. Explicitly prompting these UMMs to report infeasibility increases textual refusals but reduces editing accuracy. We propose VisTA (Visual Transformation and Abstention), a training method that pairs feasible and infeasible examples so that a model judges feasibility before deciding whether to generate. We train VisTA-BAGEL to perform feasible edits and decline infeasible requests. Without any reminder, it refuses 93.0% of infeasible requests, up from 0.4% for the strongest editor, while falsely refusing only 0.8% of feasible ones. Unlike a reminder, this does not cost editing accuracy: VisTA-BAGEL completes 74.3% of feasible edits, more than any of the 8 evaluated UMMs.
benchmark - arxiv:2610.07886 · cs.AIShanLiangRen: A Nutrition Agent for Personalized Daily Meal PlanningMiao Xie, Xiao Zhang, Yuan Wang, Ruixin Zhu +1
Dietary nutrition planning plays an important role in chronic disease management and maintaining a healthy body. In applications, it must simultaneously satisfy personalized constraints and reasonable multidimensional nutritional goals. These two aspects often conflict, and user constraints evolve with feedback, resulting in a substantial gap between generic guidelines and executable plans. To bridge this gap, we first propose the personalized fully quantified multiobjective dietary planning problem (MDP). To tackle MDP, we develop a nutrition agent, ShanLiangRen. The system first transforms dietary specifications, nutrient data, user attributes and natural language requirements into an individualized constrained planning instance. It then employs an exact retrieval-augmented generation method to shrink the feasible candidate set from a large scale ingredient and recipe space. Finally, it adopts a refinement guided by Pareto principles, where an LLM iteratively revises candidate plans under deterministic nutrition computation and feedback from constraint verification. The system outputs fully quantified meal plans with explicit ingredients and portion sizes, together with reports on nutrition compliance that show constraint satisfaction and nutrient interval attainment. We have released the system online as a WeChat Program, ShanLiangRen. A demo video is available at https://www.youtube.com/watch?v=652OtY5VlGA.
retrieval-augmentedagent - arxiv:2610.07885 · cs.LGLabel-Efficient Deep Learning for ECG Delineation: A Multi-Dataset Benchmark against Widely Used Delineation ToolsJeonghwa Lim, Minje Park, Yeongyeon Na, Yujin Eom +5
Electrocardiogram (ECG) delineation, the identification of waveform boundaries, is a foundational step that translates raw ECG signals into clinically interpretable measurements. Deep learning has advanced this task but remains dependent on costly expert annotations. Label-efficient strategies such as self-supervised pretraining and semi-supervised learning are expected to ease this burden, yet it remains unclear whether they yield reliable delineation and whether the deep models they produce outperform the delineation tools used in practice. We address this in two stages. First, comparing self-supervised objectives with supervised or semi-supervised fine-tuning across one internal and four external datasets, we find that pretraining helps but the objective matters, and that the value of semi-supervised fine-tuning depends on the pretraining objective. Second, we benchmark the selected deep learning model against widely used open-source (NeuroKit2, Prominence, ECGdeli) and commercial (CalECG) tools using three complementary metrics. The model ranks best on every metric and dataset, outperforming the strongest tool by a clear margin on the rhythm-diverse set (mIoU 71.3 vs. 54.8%; averaged point-wise sensitivity 92.6 vs. 76.4%), and degrades the least from sinus to arrhythmia. A rhythm-stratified and point-wise analysis further characterizes the distinctive behavior of each tool, yielding practical guidance for tool selection. These results provide systematic, multi-dataset evidence that self-supervised pretraining is effective for ECG delineation and enables a label-efficiently trained deep learning model to outperform widely used delineation tools by leveraging abundant unlabeled data. This supports adopting such models in diverse, real-world clinical settings.
benchmark - arxiv:2610.07884 · cs.LGLearned Adaptive Multiresolution Diffusion ImagingChristian Tantardini, Stig Rune Jensen, Roberto Di Remigio Eikås, Joakim Henrik Beck
Adaptive multiresolution methods reduce representation cost by concentrating fine-scale degrees of freedom where needed, but their tree updates are usually governed by fixed local criteria. We introduce Learned Adaptive Multiresolution Diffusion Imaging (Learned AMDI), which preserves the AMDI fixed-tree propagator and hierarchy constraints while replacing the post-propagation selector with a shared local policy trained by proximal policy optimization. Regression tests reproduce deterministic AMDI trajectories to machine precision when identical trees are used. In the Haar implementation studied here, the deterministic one-step selector accepts no refinements in 54 decisions. Across nine held-out cases, Learned AMDI executes 393 refinements and reduces the mean terminal reference discrepancy from $0.17496$ to $0.13657$, while occupancy rises from $0.13737$ to $0.26660$. Step-resolved diagnostics reveal occasional small adaptation-energy increases; fixed-tree energy stability therefore does not guarantee monotonicity of the learned outer iteration. At comparable occupancy, a validation-tuned observed-detail threshold reaches a discrepancy of $0.13792$ with slightly better RMSE and SSIM, placing both methods on essentially the same accuracy--occupancy tradeoff. A decision-1-only control reaches $0.13742$, indicating that most of the improvement on this static benchmark arises from the initial allocation. The shared actor transfers without retraining to $64\times64$ and $128\times128$ images, improving reference discrepancy, RMSE, and SSIM relative to deterministic AMDI, while the frozen threshold rule remains competitive. Learned AMDI thus provides a hierarchy-constrained, resolution-transferable mechanism for adaptive allocation and clarifies the contribution of sequential decisions.
benchmark - arxiv:2610.07881 · cs.AISelf-Referenced Social Preferences: Cooperation without Observing Others RewardsMohamed Ayman Mohamed, Harshil Kotamreddy, Marcos Menon Jose
Social preferences can promote cooperation in multi-agent reinforcement learning, but existing approaches often require agents to observe the rewards of their peers. In many real-world interactions, however, an agent can, as humans do, observe others' behavior and outcomes without access to their private reward signals. We introduce self-referenced social preferences, in which each agent learns a model of its own reward, applies it to other agents' observed transitions to assess their outcomes from its own perspective, and feeds these self-referenced assessments into standard social preferences. We study two ways to incorporate these assessments: modifying the learning reward, or using them to weight policy updates. We evaluate the approach on three sequential social dilemmas, Escape Room, Clean Up, and Commons Harvest, which require volunteering, public-good contribution, and resource restraint, respectively. Across all three environments, agents learn cooperative behavior without observing others' rewards, including in settings where independent learners fail to cooperate, and frequently achieve more equitable divisions of jointly produced returns than agents with access to true rewards. The effective integration point depends on the social preference: inequity aversion works best in the reward together with a value look-ahead, whereas a purely benevolent preference benefits from policy-update weighting. Under partial observability, the policy-update approach continues to support cooperation. These results show that explicit access to other agents' reward signals is not necessary for learning cooperative behavior: social preferences can instead be grounded in self-referenced assessments of others' outcomes derived from their observed behavior.
agentmulti-agent - arxiv:2610.07874 · cs.LGOn-Policy Distillation with Negative-Policy RolloutsJaehui Hwang, Dongyoon Han, Sangdoo Yun, Byeongho Heo
On-policy distillation (OPD) has been widely studied as a post-training method in which a student model obtains token-level supervision from a stronger teacher on its own rollouts. Recent studies have improved OPD through alternative distillation reward formulations and teacher configurations, while the objective of distillation remains centered on mimicking the teacher. However, when a stronger teacher has limited distributional overlap with the student, such positive guidance can provide insufficient learning signals. In this work, we introduce Negative-Policy OPD (NP-OPD), which complements teacher supervision with rollouts from a lower-performing, lower-capability negative policy that serves as a negative reference for the student. Rather than modifying the distillation reward formulation, NP-OPD introduces the negative policy at the rollout stage, continuously supplying tokens preferred by the negative policy over the teacher so that they remain exposed to teacher supervision throughout training. This provides an explicit negative signal through negative-policy rollouts while preserving the positive teacher supervision used in OPD. Through extensive experiments, we show that NP-OPD improves OPD across model scales, generation modes, reasoning domains, and different OPD variants. Furthermore, our analyses show that NP-OPD effectively suppresses tokens preferred by the negative policy over the teacher and moves the student away from the negative policy. These results support our design of introducing negative signals through negative-policy rollouts and provide new insight into the role of the rollout policy in OPD. Code will be available at https://github.com/naver-ai/np-opd.
post-training - arxiv:2610.07868 · cs.CVCueRator: Agentic Search for Symbolic Rules to Adapt Frozen Multimodal EncodersSunchan Park, Beomkwon Cho, Kyeongbo Kong
Large language model agents have been used to search over symbolic structures such as programs and equations. We propose CueRator, an agentic framework for policy-aware decision-rule discovery, which adapts frozen contrastive multimodal encoders by searching for the decision rule that converts their cross-modal similarities into predictions. We validate it on open-vocabulary audio-visual event perception, where existing methods involve a trade-off between adaptivity and generalization to unseen categories: trained modules adapt at the cost of generalization, and fixed rules the reverse. The framework pairs a symbolic formulation for generalization with a lightweight policy that predicts its parameters per video for adaptivity. A report-guided multi-agent loop discovers the formulation offline, evaluating each candidate on its expressive ceiling and on whether a trained policy can realize it. On OV-AVEBench, CueRator raises the total average from 57.8 to 60.2 and unseen-category performance from 55.8 to 59.9 over the best existing method, reducing the seen-unseen gap from 7.1 to 1.2. Ablations attribute the gains to both the formulation and the policy and show that both feedback signals are necessary for effective search. CueRator also improves over the respective baselines on two further audio-visual event perception tasks, and the discovered rule remains competitive across encoders with only the policy retrained. Code is available at https://github.com/cvsp-lab/cuerator.
multi-agentagentic - arxiv:2610.07863 · cs.LGReFold: Training-Free Reversible Inter-Turn Context Folding for Long-Horizon AgentsYupeng Su, Jiayi Tian, Zheng Zhang, Souvik Kundu
Long-horizon LLM agents act on an append-only interaction history that is re-sent to the model at every step, so the context and its cost grow with steps until the sessions exceed the context window. Existing methods manage the context through context requirement prediction, relying on additional model calls, heuristic rules, or trained policies. However, these predictive approaches introduce runtime overhead, invalidate prefix caches, and permanently discard content with no guarantee of recovery. To overcome these limitations, we introduce ReFold: a training-free rendering layer that preserves the underlying interaction history while compressing only the model's rendered context. It removes two kinds of inter-turn redundancy without an auxiliary predictor: content an earlier turn already displayed, replaced by a stub, and turns the agent itself reports finished, folded into a one-line note. Both operators use chunked rendering, rewriting the cached prefix once every few steps rather than at every step. Every removal is strictly reversible, a wrong removal costs one restore from the history rather than permanent content loss. Because it operates at the rendering layer, ReFold is plug-and-play across standard ReAct-style harnesses. Evaluations across five long-horizon benchmarks and two frontier LLMs demonstrate that ReFold reduces token consumption by up to 2.5x and halves the KV-cache memory per session without degrading task success rates. Under capped context budgets, it avoids up to 92% of forced compactions. Under concurrent serving workloads, it reduces request queuing delays by up to 100%, accelerating inference by up to 1.7x, while cutting inference costs by up to 3.4x.
memoryagentllm agentbenchmark - arxiv:2610.07862 · cs.LGA self-learning scientific agent for X-ray diffractionBin Cao, Huichi Zhou, Runyu Yang, Jingsong Li +6
A central challenge for scientific agents is to turn analytical experience into reusable expertise grounded in physical evidence. Here we introduce Gan Jiang, a self-learning agent for powder X-ray diffraction built on a diffraction-analysis ecosystem we developed: XMatcher, XQueryer, XDecomposer and WPEM. Together, these engines span phase identification, multiphase decomposition and physics-constrained whole-pattern modelling. Gan Jiang converts analytical experience into executable skills by diagnosing failures, revising skill instructions and code, and validating revisions before reuse, without retraining the language model or changing the underlying physical models. Skills selected using development data and frozen before held-out evaluation achieve higher refinement scores than the original expert-designed skills across FullProf, GSAS-II and PyWPEM. The agent resolves strongly overlapping reflections, quantifies a five-phase ancient Egyptian cosmetic, tracks lattice evolution in an operating battery and compares atomic configurations in a disordered oxide catalyst. On DeltaXRDbench, it leads the evaluated methods in single- and multiphase identification across simulated and experimental data. Without supplied composition, single-phase top-1 accuracies reach 96.30\%, 81.78\% and 40.83\% on MP500, RRUFF and opXRD, respectively, compared with 58.00\%, 58.47\% and 26.45\% for the strongest comparator. These results demonstrate how an integrated scientific tool ecosystem can support agents that extract structural knowledge from measurements while accumulating validated analytical expertise that transfers to new samples.
agent - arxiv:2610.07860 · cs.AIWorkflowOps: Learning Agent Collaboration Priors for Multi-Agent Workflow OrchestrationQi Cheng, Shengyu Chen, Wei Cheng, Zhengzhang Chen +3
Multi-agent systems are increasingly deployed for complex knowledge work, yet their orchestration layers remain largely memoryless: each new task is decomposed, assigned, and executed from scratch with no benefit from prior successful executions. We present WorkflowOps, a multi-agent workflow orchestration framework that learns agent collaboration priors from historical workflows and expands its agent pool on demand to cover new capability requirements. Our approach introduces three coupled mechanisms. First, a transition probability matrix captures pairwise agent collaboration frequencies from past workflows and applies them as soft guidance during DAG workflow construction through intra-layer ordering optimization, probability-thresholded edge suggestion, and transitive reduction for parallelism maximization. Second, a sufficiency-driven agent creation loop detects capability gaps via semantic matching scores, generates specialized agents through an LLM, and simultaneously injects them into the collaboration matrix, so that newly created agents are immediately usable with predicted collaboration priors. Third, a layered semantic matching strategy uses pre-trained sentence embeddings for fast, deterministic capability matching as a first pass, invoking LLM verification only for low-confidence cases, thereby reducing LLM routing calls by over 80\% compared to pure-LLM approaches. Experiments on mixed code, math, and question-answering suites show that WorkflowOps improves end-to-end pass rates over recent workflow-construction baselines, with the largest gains on structured, decomposable tasks where past agent handoff patterns transfer.
agentmulti-agentagent system - arxiv:2610.07851 · cs.AIRA-MoWE: Workflow-Affinity Embeddings for Query Clustering and Agentic Workflow GenerationQi Cheng, Shengyu Chen, Wei Cheng, Yiqun Xie +3
Agentic workflows enable large language models (LLMs) to solve complex tasks by coordinating reasoning, tool use, and verification. However, a workflow optimized for an entire task collection can overlook differences in the reasoning strategies that individual queries need, while searching for a new workflow for every query repeats costly optimization. To address this tradeoff, we introduce RA-MoWE, a framework that uses workflow-affinity embeddings to cluster queries and guide the generation of reusable expert workflows. Each embedding records how well a fixed set of reference workflows solves a query, revealing similarities in which reasoning strategies are effective. RA-MoWE uses each cluster's queries and average embedding to initialize and refine a specialized workflow through execution feedback. An embedding encoder predicts these embeddings from query text, allowing new queries to select a generated expert without first executing the reference workflows. On a 300-query test set drawn from four benchmarks spanning mathematics, science, and programming, RA-MoWE improves average task score by 4.04 percentage points over selecting among the reference workflows, while using 27.7% fewer language-model calls at inference.
agentictool usebenchmark - arxiv:2610.07848 · cs.AIDynamic Positional Attention Modulation for Parameter-Efficient Fine-Tuning of Large Language ModelsDayan Pan, Jingyuan Wang, Xie Yu
Parameter-efficient fine-tuning (PEFT) has become a standard approach for adapting large language models to downstream tasks. However, most existing PEFT methods rely on uniform and static adaptations, without accounting for the structured heterogeneity of attention across dimensions, heads, layers, and input tokens. In practice, attention representations exhibit non-uniform behavior, and positional encoding mechanisms such as rotary positional embeddings (RoPE) induce dimension-dependent positional structure, making uniform adaptation suboptimal. In this work, we propose DyPAM (Dynamic Positional Attention Modulation), a PEFT method that adapts how positional information contributes to attention by operating directly on the query and key representations. DyPAM combines input-conditioned, dimension-wise modulation with head-wise and layer-wise structural modulation, performing fine-grained adaptation of positional attention aligned with the RoPE-induced structure without modifying the pretrained backbone. Extensive experiments on mathematical and commonsense reasoning benchmarks across multiple backbone models demonstrate that DyPAM consistently outperforms existing strong PEFT baselines.
benchmark - arxiv:2610.07847 · cs.CLOMIT the Action: Measuring Framing-Invariant Omission Bias under Philosophical DisagreementSihyeon Lee, Jihun Song, Chanwoo Kim, Jiwoo Kum +1
As LLMs increasingly assist in moral reasoning, omission bias, the tendency to prefer inaction even when equivalent framings reverse substantive outcomes, poses a significant risk of skewed decision-making. Yet omission bias remains underexplored in LLM evaluation, with the few existing studies limited in scale and focused largely on utilitarian-deontological conflicts. To address this gap, we introduce OMIT, a benchmark consisting of 218 paired-frame scenarios across 10 conflict types, constructed by leveraging disagreement patterns from an LLM-based, five-perspective philosophical persona panel (utilitarianism, deontology, virtue ethics, care ethics, and contractualism). Evaluating eight LLMs, we find that omission bias is pervasive but inversely correlates with model size within families. We further evaluate four inference-time interventions and find that interventions encouraging models to consider moral principles before committing to a yes/no answer reduce omission bias and increase frame-consistent responses, although lower omission bias rates can also coincide with shifts toward action-biased responses. Ultimately, this work contributes not only the OMIT benchmark, but also a methodology for using diverse philosophical disagreement signals to evaluate framing-sensitive inaction preferences and the distributional effects of mitigation attempts in LLMs under complex moral conflicts.
benchmark - arxiv:2610.07846 · cs.LGScen-Opt: A Scenario Optimization Toolbox for Data-Driven Convex ProgrammingBen Wooding, Simone Garatti, Marco C. Campi, Abolfazl Lavaei
The scenario approach is a well-established statistical framework for data-driven decision-making. In particular, in data-driven optimization, the scenario approach unveils how the problem structure governs out-of-sample generalization, and offers a principled basis for assessing and certifying the reliability of the optimal solution as per constraint satisfaction. Despite its strong theoretical development and wide applicability, no software toolbox has been available to date that enables user-friendly, data-driven convex optimization within the scenario-approach framework. In this paper, we introduce Scen-Opt, an open-source software tool that integrates convex programming with data samples while providing statistical guarantees grounded in scenario theory. Scen-Opt is implemented in Python, supporting data-driven linear, quadratic, and semidefinite programming, and offers a Python-based web application with an intuitive and reactive graphical user interface (GUI) built using modern web technologies. Scen-Opt can be used directly through its online interface or installed locally, accommodating both manual input and data-file uploads (CSV, JSON, TXT, TSV, MAT, Excel, NPY, NPZ, Parquet). Built on a Python backend with a modern JavaScript frontend, Scen-Opt offers a highly user-friendly experience and efficient usability across desktops, laptops, tablets, and mobile devices. In this paper, Scen-Opt is applied to a set of representative benchmarks, demonstrating its practical effectiveness for data-driven convex optimization with guaranteed performance.
benchmark - arxiv:2610.07835 · cs.AIDHCG: Dynamic Construction of Hierarchical Collaboration Graphs for LLM-Based Multi-Agent ReasoningJie Ren, Jiakang Yuan, Chenyu Huang, Hezeer Ma +2
LLM-based multi-agent systems (MAS) have demonstrated strong capabilities in solving complex problems across diverse domains. Recently, the dynamic orchestration of agent systems has become an important research direction. However, existing methods suffer from limited composition, misaligned dependencies, and inflexible scale, restricting their ability to adapt to reasoning requirements during execution. To address these limitations, we reframe MAS design as a partially observable Markov decision process, in which both the composition and scale of the MAS are dynamically determined. We propose DHCG, a novel framework that coordinates three modules (Planner, Worker, and Generator) to progressively construct a dynamic hierarchical collaboration graph from scratch based on the query and evolving execution feedback. At each step, guided by feedback, the Planner generates a set of distinct and complementary roles tailored to the current reasoning needs and selectively routes relevant information to each role. It can also finalize the hierarchical collaboration graph early or progressively expand it when additional reasoning is required. We further introduce action-aware preference optimization to train the Planner to make more effective decisions when constructing hierarchical collaboration graphs. We systematically evaluate DHCG across code generation, mathematical reasoning, and domain-specific reasoning benchmarks. DHCG achieves state-of-the-art average performance among the compared methods, improving over the single-agent baseline by 13.06 points and outperforming both static and dynamic MAS baselines by 2.77-8.02 points. Additional experiments further demonstrate its generalization across different Planner backbones and unseen Worker models.
agentmulti-agentagent systembenchmark - arxiv:2610.07834 · cs.LGRetrieval Is Not Enough: Refreshing Memory for Frozen Time-Series ForecastersChao He, Jianyu Xu, Xinyi Guo, Ruiqi Liu +3
Retrieval-augmented time-series forecasting uses the continuations of historical segments similar to the current context as references for a forecaster. Most existing methods build the retrieval memory once from the training segment, leaving observations revealed after deployment unavailable as references, and generally do not calibrate how much the retrieved information should influence a frozen forecaster. We identify two key determinants of retrieval utility for a frozen forecaster: whether the history still reflects the current state, and whether the correction it induces aligns with the forecaster's residual errors, an alignment that can shift between validation and deployment when the memory becomes stale. We propose FreshCast, a plug-in retrieval framework that keeps the forecaster frozen, continuously updates a non-parametric memory with new observations, forms a memory forecast through relational kernel regression, and calibrates its weight in closed form on the validation segment. Under a simplified generative model, we characterize the optimal combination gain through the second-order relation between forecaster error and memory correction, and show that a sufficiently long look-back can make periodic memory information redundant. Across seven benchmarks and ten forecasting architectures, FreshCast reduces average MSE for every evaluated forecaster and input length, by 14.6% and 5.6% at input lengths 96 and 720, and achieves lower MSE than the evaluated retrieval-augmented and online baselines in their comparison settings. Ablations show that freezing the memory at the end of training removes most of the gain, identifying post-training observations as a primary source of improvement. For a frozen forecaster, useful historical references must remain timely and provide information that helps correct its remaining errors.
memoryretrieval-augmentedpost-trainingbenchmark - arxiv:2610.07832 · cs.AIHarness Engineering for Software Engineering via Modular Executable Dev-PrimitivesHaibo Jin, Xinjie Li, Peng Kuang, Haohan Wang
Large language models (LLMs) equipped with terminal access have demonstrated strong capabilities in automating software engineering tasks. However, existing agents remain brittle on long-horizon workflows, where they must repeatedly reconstruct program state scattered across source files, configurations, tests, dependencies, and runtime behavior, leading to increasingly long interaction histories, context explosion, and semantic drift. Large repositories further complicate the identification of task-relevant components. To address these challenges, we introduce \textbf{Dev-Primitives} (\emph{Development Primitives}), a modular and executable abstraction that transforms repository components from passive software artifacts into active participants in software engineering. Each Dev-Primitive pairs a repository artifact with a resident LLM, which gives the artifact an agent-native interface grounded in its own implementation and dependencies, enabling natural-language reasoning, inter-component communication, and localized self-modification. Building on Dev-Primitives, we propose \textbf{HERMES}, a Harness Engineering framework for software engineeRing via Modular Executable Dev-PrimitiveS, which instantiates these primitives at repository scale through a dependency-aware dynamic activation mechanism and a bug diagnosis mechanism that maps execution evidence back to the components that must be revised. Extensive experiments on four software engineering benchmarks demonstrate that HERMES outperforms matched baseline harnesses by 12.4\% on average. Moreover, when paired with strong activation and diagnosis models, HERMES, even with Qwen3-8B Dev-Primitives, remains within 4.5\% of the homogeneous GPT-5.6 Sol configuration across all four benchmarks, while reducing inference cost by 26.2\% on Terminal-Bench 4.0, highlighting the importance of harness design in software engineering agents.
benchmark - arxiv:2610.07829 · cs.AIAgentic Semantic Sensing for Resource-Adaptive AI-RANZhongqin Wang, Xiaoqi Zhang, Nan Yang, Kai Wu +2
Semantic sensing (SemS) acquires task-relevant information rather than reconstructing complete physical information. Existing SemS formulations typically operate open loop: sensing configurations and observation schedules are fixed before inference and cannot respond to evolving task-level evidence. We propose Agentic SemS, a closed-loop framework for AI-enabled radio access networks (AI-RANs) that controls sensing within a communication-feasible profile set. A profile-conditioned causal Transformer updates the semantic belief from streaming observations, while key-value caching enables efficient state updates across profile changes without repeatedly processing the complete history. A semantic utility network estimates the task-level benefit of acquiring the next observation block under each feasible profile after accounting for sensing cost. The resulting continuation utilities jointly support next-profile selection and semantic early exit, adapting sensing configuration and duration to evolving evidence. The expected semantic gain is further related to conditional mutual information, providing a value-of-information interpretation of continued online sensing. Experiments on Widar3.0 with six emulated sensing profiles show that, in comparison with full-sequence High, the resource-efficient Agentic setting reduces normalized cumulative sensing cost by 25.33% while achieving 85.79% Macro-F1. At the same utility checkpoint, semantic early exit provides a further 12.35% cost reduction over adaptive sensing without early exit, with a 0.97-percentage-point Macro-F1 decrease.
agentic - arxiv:2610.07823 · cs.LGTTNet: Multi-Task Deep Learning for Table Tennis Player Analysis with Smart RacketKo-Hsun Chen, Xiang-Wei Ke, Hsien-Cheng Huang, Shang-Kuan Chen
The AI CUP 2025 Precise Analysis of Table Tennis Smart Racket Data Competition introduced smart table tennis rackets that collect extensive player swing data, enabling research on table tennis big data. These data support in-depth analysis of players' return techniques and swing-force consistency, improving the accuracy of player skill assessment. This study focuses on six-axis sensor data collected by smart table tennis rackets and proposes TTNet, a novel deep learning model with multitask learning capabilities, to advance table tennis data analysis and related applications. TTNet combines convolutional neural networks (CNNs), residual networks (ResNet), and self-attention mechanisms to simultaneously predict four player attributes: gender, playing hand, years of experience, and skill level. We adopt a two-stage training strategy that incorporates data augmentation and task-specific loss functions to improve generalization on imbalanced data. Our approach achieved second place on the official competition leaderboard.
leaderboard - arxiv:2610.07819 · cs.LG$α$Transfer: Coefficient Transfer for Efficient Model MergingShih-Cheng Huang, Zhi Rui Tam, Chieh-Yen Lin, Yun-Nung Chen +2
Model merging offers a promising solution for combining multiple fine-tuned checkpoints into a single model through parameter arithmetic. However, finding optimal merging coefficients requires an extensive search that becomes prohibitively expensive as models scale in both size and number, due to high memory requirements and combinatorial growth in the search space. We show that, within the same model family, models exhibit highly congruent performance distributions over merging coefficients across different model sizes. This distributional similarity enables a practical paradigm we call \textit{$α$Transfer}: searching for optimal coefficients on a small proxy model, then directly transfer them to larger target models. We verify $α$Transfer across multiple merging methods, model families, and tasks. Experimental results demonstrate a 6$\times$ speedup and 70\% memory reduction on vision transformers, and a 20$\times$ speedup and 85\% memory reduction on large language models, while maintaining comparable performance. Our findings establish $α$Transfer as an efficient and generalizable approach to scaling model merging.
memory - arxiv:2610.07817 · cs.AIOne Step at a Time: Trading LLM Autonomy for Process PredictabilityHans Schabert, Christoph Peters
Organizations automating operational processes need more than a correct outcome: they need to predict how a process will run, know which one actually ran, and inspect it step by step. When an agent is the executor that predictability is normally lost: the prescribed procedure goes into the system prompt, and only a final answer comes back. We deliver the procedure step by step over the Model Context Protocol (MCP) instead: a server releases one step at a time, the agent executes it, and each step returns a structured step_output. This trades autonomy for predictability, and two properties then follow by construction, independent of the executor. The execution path is prescribed before the run, so the process is predictable in advance rather than reconstructed afterwards; and the completed step records form a machine-readable execution log that downstream tooling can audit and optimize step by step. Evaluating 15,475 trials across 13 SOP-Bench domains and four open-weight executors from frontier (Kimi K2.5) to lightweight (Ministral 3 8B), we find step-level delivery makes the executed process predictable and inspectable for every executor, and additionally raises accuracy when the executor is small. Across all four, process adherence rises significantly (76-95% to 95-99%) and ungrounded answers (correct outputs produced without executing the SOP) near-vanish, falling from 2.1-4.5% to 0.2-0.3% of trials (all 95% CIs exclude zero); under prompt-based delivery, 31-49% of correct answers on know_your_business bypass the SOP entirely, even for the frontier executor. Accuracy is where the executor's capability enters: the lightweight executor gains +6.5pp grounded accuracy because supplying the process externally removes a reconstruction burden it cannot carry, while capable ones trade a small raw-accuracy decrement for a predictable, auditable process.
agent - arxiv:2610.07816 · cs.LGDo I Need the Cloud? Uncertainty-Aware Step-Level Handoff for Small Language Model AgentsAbolfazl Younesi
Small language models (SLMs) are attractive as local agent controllers because they reduce remote inference, latency, and deployment footprint, yet structured tool errors can cause an agent step to fail. Existing routers typically select a model once per query. However, agents expose sequential decision points whose difficulty dynamically changes based on intermediate observations. We propose STEPGATE, an uncertainty-aware handoff framework that scores each local SLM action and selectively escalates challenging steps to a stronger model. On a 52-task held-out single-step BFCL-derived test split, the Qwen2.5-1.5B/7B pair attains 82.7% task success with 30.8% escalation, versus 67.3% local-only and 75.4% random escalation (which uses 33.8% escalation). In a separate multi-turn evaluation, STEPGATE achieves 69.0% trajectory success and 84.0% action success using only 30.0% cloud actions, compared with 48.0%/70.5% local-only, 60.0%/78.2% random escalation, and 57.0%/77.1% query-level routing (strong-only achieves 82.0% trajectory success at 100% cloud actions). These results suggest that step-level escalation recovers a large share of the performance gap to the stronger Qwen2.5-7B backend at a matched cloud-action rate while transmitting fewer tokens remotely. However, our evaluation is limited to one model family, a single stronger backend, and scripted tasks. Furthermore, the test sets are small, multi-turn comparisons rely on paired intervals and statistical tests, and our risk tiers serve as research annotations rather than formal safety guarantees.
agent - arxiv:2610.07809 · cs.LGMASKerade: Token-Routed Mask Experts for Dense-to-MoE UpcyclingMingyuan Zhang, Yue Bai, Zhongruo Wang, Yupin Huang +4
Sparsely activated Mixture-of-Experts (MoE) models increase model capacity without a proportional increase in per-token computation. Dense-to-MoE upcycling reuses pretrained dense models to construct such systems, commonly by copying feed-forward networks (FFNs) into independently trained experts. We introduce MASKerade, a dense-to-MoE training method that instead learns experts as sparse subnetworks of a frozen pretrained FFN. Each expert is defined by a learned binary mask, and a token-level router selects which masked FFNs to execute and combine. The router and mask scores are optimized jointly, while the underlying FFN weight values remain unchanged. This formulation supports neuron-structured, semi-structured, and unstructured experts within the same routing architecture. Our main configuration uses four 2:4 experts with top-2 routing, where two half-dense expert passes have the nominal FFN arithmetic of one dense pass, without requiring independent expert weight matrices. On five vision-language benchmarks with Qwen and Gemma backbones, this configuration achieves the highest performance among the compared baselines. Comparisons across mask granularities, routing interventions, and compute-matched controls distinguish the effects of learned connectivity from expert activation count. These results establish mask learning over frozen weights as a practical alternative for constructing token-routed MoE experts.
benchmark - arxiv:2610.07803 · cs.AIThinkFuse: Trajectory-Aware Test-Time Fusion for Small Reasoning ModelsMyunghoon Kang, Jungseob Lee, Jaehyung Seo, Heuiseok Lim
Small reasoning models (SRMs) have shown strong performance on complex reasoning tasks by generating extended chain-of-thought trajectories, but they often fail to recover once their reasoning enters an erroneous path. Existing test-time fusion methods rely on local fusion signals to determine when to trigger fusion, which can be misled by transient uncertainty fluctuations and may reinforce unstable reasoning trajectories. We propose ThinkFuse, a training-free test-time fusion framework that selectively intervenes in unreliable reasoning segments. ThinkFuse compares segment-level uncertainty shifts with trajectory-level uncertainty trends to identify unstable reasoning points and fuse auxiliary reasoning paths into the primary model's trajectory. Extensive experiments demonstrate that ThinkFuse outperforms baselines on mathematical and knowledge-intensive reasoning benchmarks, with consistent gains across model-family combinations, and remains robust with a smaller primary model. Our analysis shows that ThinkFuse requires fewer fusion triggers and generates fewer tokens, highlighting the efficiency of selective triggering. Our code is available at https://github.com/js-lee-AI/ThinkFuse.
benchmark - arxiv:2610.07802 · cs.CVTowards benchmarking Western Bluebird detection in the wildEstela Monserrat Arriaga Santana, Julian Rosas Scull, Ibeth P. Alarcón, Bibiana Montoya +2
Bird monitoring in natural environments is challenging due to the small size of some species of birds relative to the scene, background clutter, variability in illumination, and the observers' viewpoint. Progress is further limited by the scarcity of large-scale, realistic datasets, which are essential for understanding behavioral patterns. To address this gap, we introduce a new benchmark dataset for the detection and segmentation of Western bluebirds (Sialia Mexicana), comprising over 6,000 labeled images from 41 recording sessions. The dataset features high-resolution (4K) in-the-wild images in which birds occupy only a small fraction of the image. We evaluated supervised detectors, open-vocabulary models under zero-shot and fine-tuned settings, and segmentation approaches. Supervised detectors remain the most reliable overall, with Faster R-CNN achieving the highest detection mAP and RT-DETR offering the best precision-recall trade-off. Open-vocabulary models perform poorly in zero-shot settings; however, fine-tuning substantially improves their performance, with YOLO-World becoming competitive with supervised methods and achieving the highest precision, F1-score, and [email protected]. For segmentation, supervised methods significantly outperform Grounded-SAM and SAM 3: Mask R-CNN achieves the highest mask mAP, while YOLOv8-Seg provides the best precision and fastest inference. A diagnostic analysis further shows that failures are not explained by object size alone, but by a combination of apparent scale, brightness, contrast, clutter, blur, crowding, and recording-session variation. Overall, our findings highlight the difficulty of zero-shot bird detection in cluttered ecological scenes and underscore the importance of domain adaptation in small-object settings.
benchmark - arxiv:2610.07796 · cs.LGThe Geometry of EmpowermentCatherine Ji, Vivek Myers, Sergey Levine, Benjamin Eysenbach
Empowerment captures the capacity for an agent to actively control its environment. While conceptually appealing as an information-theoretic quantity, the connection between empowerment and structurally central states that provide broad access to future outcomes has remained an open question. In this work, we link empowerment maximization and skill-learning methods to provide new geometries for interpreting and analyzing empowerment. Our analyses answer longstanding open questions on the connections between empowerment and structural centrality. Our analyses also reveal distinctions between information and reward geometries, highlighting important theoretical implications to build scalable empowerment-maximization methods. Website and code can be found at https://empowerment-geometry.github.io/.
agent - arxiv:2610.07792 · cs.LGServeLearnBench: How Well Can Agents Self-Improve from Serving Experience?Haizhong Zheng, Yizhuo Di, Ranajoy Sadhukhan, Shuowei Jin +1
Large language model agents are increasingly deployed to perform complex tasks in real-world environments. However, the knowledge required for correct behavior in these environments is often implicit, undisclosed, and subject to change over time. Recent continual-learning harnesses seek to address this challenge by enabling agents to improve from serving experience. Yet the effectiveness and limitations of these methods are not yet well characterized. Existing benchmarks provide only partial coverage: some explicitly provide the target knowledge, others assume a static environment, and those that support continual adaptation remain limited in scale and knowledge diversity. To enable systematic evaluation, we formalize an evolving-environment streaming dataset (EESD), in which agents must infer, apply, and revise latent environment knowledge from interaction and outcome feedback as hidden policies evolve, and introduce ServeLearnBench, spanning retail support, banking, and sales-pitch generation with 53 environment windows and 7,718 tasks. We evaluate five learning harnesses (RAG, Mem0, SkillOpt, Continual Harness, and Prime) across six models (GPT-5.6 Terra, Opus 5, Kimi K3, GLM-5.3, DeepSeek V4.1 Flash, and GLM-5.3 Flash), covering 28 model-harness pairs and 252 learning runs. Our evaluation reveals three main findings: a substantial gap remains between task capability and learning from experience; continual adaptation is costly and can degrade already-correct behavior; and insufficient exploration emerges as a key bottleneck to effective adaptation. Overall, ServeLearnBench provides a controlled testbed for diagnosing these limitations and tracking progress toward agents that continually and reliably improve through serving experience.
benchmark - arxiv:2610.07787 · cs.AIOOPMAS: Object-Oriented Multi-Agent Systems for Query-Level Workflow GenerationQi Cheng, Shengyu Chen, Wei Cheng, Yiqun Xie +3
Multi-agent systems (MAS) powered by large language models have shown strong performance across code generation, mathematical reasoning, and question answering. However, existing methods for automating MAS design mostly operate at the task level, producing a single fixed workflow per benchmark that is applied uniformly to all queries. This assumption fails under realistic conditions. Query difficulty varies widely within a task, and real-world workloads mix heterogeneous task types. We introduce OOPMAS, a training-free framework that generates both the agent set and the coordination workflow at the granularity of individual queries. Agents are represented as object-oriented class definitions with dedicated roles, tools, and persistent state, and workflows are expressed as executable main functions over these agent objects. A dynamic skill library accumulates structured lessons from execution feedback across optimization rounds, enabling in-context improvement without any gradient updates or fine-tuning. On a mixed-task benchmark of queries spanning code, math, and QA, OOPMAS achieves 89.6% accuracy, outperforming the strongest baseline by 18.1 percentage points. A model-swap study across four LLM backbones shows consistent scaling, reaching 92.4% with the strongest model.
persistent stateagentmulti-agentagent systembenchmark - arxiv:2610.07786 · cs.LGExtending Pathwise Gradients to Discrete Random Variables via Finite-Order RelaxationDonghan He, Luhuan Wu
Pathwise gradients are preferred for continuous random variables because they are unbiased, low variance, and work with a single sample. For discrete variables, however, the pathwise identity cannot generally be exact for every differentiable function. We propose a general framework to construct finite-order exact pathwise gradient estimators for a range of common discrete variables such as Poisson. The estimator is the least-norm solution among all solutions that are unbiased for polynomials of degree at most. The resulting estimators preserve the hard forward sample, require no temperature tuning, and can be implemented in a few lines of codes. Against other admissible solutions, our estimator is unique and minimizes weight variance; in contrast, prior works use categorical variables or augmented representations to approximate non-categorical variables that induces excess variance and computations. To understand approximation bias for functions beyond the prescribed class, we also derive a non-asymptotic bias bound. In experiments our low order methods match or improve tuned baselines across linear, nonlinear and hierarchical latent-variable models, while out-speeding competitors in every runtime benchmark.
benchmark - arxiv:2610.07785 · cs.AIAttacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied AgentsGyusik Seo, Jaehong Yoon
A central capability of embodied agents is to accomplish complex objectives through sequences of interdependent tasks. Yet existing visual goal-conditioned policies underlying these agents are typically evaluated on isolated interactions where the target is already visible, and thus do not capture the conditions that arise during continuous long-horizon task execution. In such settings, each task begins from the state left by the previous one: the agent may end at a different position and orientation, the world may have been modified, and the next interaction target may lie outside the current field of view. As a result, agents relying on such policies may struggle to proceed to the next task when they cannot ground their target in the current observation. To address this challenge, we propose Attacca, a new approach that trains visual goal-conditioned policies on complete search-to-interact trajectories using goal images decoupled from the execution environment. Attacca uses context-decoupled goal sampling to pair each demonstration with a class-compatible masked goal image from another world, removing direct scene and pose correspondence. It learns dense current-view grounding through a target-mask prediction head, providing auxiliary supervision beyond action imitation. We further introduce behavioral-phase conditioning that teaches the policy to distinguish Search, Approach, and Interact stages and adapt its control as execution progresses. We evaluate Attacca on multiple short- and long-horizon embodied tasks in Minecraft. Our method achieves 39.0-47.5% clean success, improving over the strongest baseline by 1.7-2.4x. On long-horizon tasks, it attains 54%, 30%, and 28% completion, yielding up to a 7x improvement.
embodiedagentembodied agent - arxiv:2610.07784 · cs.ROMulti-Robot Multi-Goal Motion Planning with Stochastic SkillsWilliam Schnyder, Valentin N. Hartmann, Stelian Coros
As robots are increasingly deployed in groups and share workspaces to execute real-world tasks, planning their concurrent motions around complex manipulation skills becomes essential. These skills involve continuous physical execution and may exhibit stochastic behavior, resulting in variable execution times and uncertain continuous trajectories. Existing planners either limit execution to single-robot scenarios, rely on open-loop paths, or use post-hoc scheduling that prevents dynamic coordination. In this paper, we address this gap by integrating stochastic skills into sampling-based multi-robot planning by formulating the problem as a Markov Decision Process (MDP) over a multi-modal composite roadmap. For stochastic skills, solving the MDP yields a reactive policy that allows controllable robots to dynamically adapt their motions in response to other robots' execution of manipulation skills. By resolving skill uncertainty directly at planning time, this approach avoids the pessimism of conservative baselines and unlocks robust, dynamic multi-robot coordination. Code for the planners is available at https://www.vhartmann.com/stochastic-skills.
manipulation - arxiv:2610.07782 · cs.LGPersistent Memory in Multi-Agent LLM Inference: What It Costs, What It Buys, and When You Can TellHochan Son, Kyungdoe Han, Jaehan Koh, Xiaowu Dai +2
Decomposing long-context inference across cooperating agents bounds the active KV cache per call rather than total evidence, which matters when KV-cache memory binds. Many such systems add a persistent tier storing and recalling reasoning traces, usually validated by an ablation reporting an accuracy gain. We measure both on one three-tier agent architecture. Decomposition delivers: peak KV working set of 14.3 MiB per query against 35.5 and 35.3 MiB for single-pass and retrieval-augmented baselines. The persistent tier does not: across eight controlled dataset pairs at n=100 per arm it costs +0.368 MiB [+0.167, +0.590] of peak cache and produces no detectable accuracy change (+0.015, 95% CI [-0.011, +0.046]). We argue the null is structural: single-question benchmarks supply each item with its own evidence and score it independently, and correctness requires resetting stored traces between conditions, so recall has nothing informative to retrieve. Reaching it took four measurement corrections -- three inflating the apparent benefit, the fourth making an effect that size look resolvable -- none visible in the results table. We give the conditions an agent-memory ablation must satisfy and detection procedures that need no knowledge of the specific defect.
memorylong-contextpersistent memoryretrieval-augmentedagentmulti-agent - arxiv:2610.07781 · cs.LGQuantization Effects on Tool-Failure Recovery Vary Across Prompts and Evaluation DesignsYuhe Hu
Post-training quantization reduces the cost of deploying language-model agents, but its effect on recovery from temporary tool failures can depend on how recovery is evaluated. We compare 8-bit and 4-bit variants of Llama-3.1-8B-Instruct and Qwen2.5-7B-Instruct on twenty deterministic tool-use tasks and five prompts. The 8-bit-4-bit recovery comparison changes direction across prompts and evaluation targets. On tasks that both variants complete without faults under the same prompt, the difference ranges from 0 to +20.2 percentage points for Llama and from -50.0 to +35.0 points for Qwen. Full-pipeline point estimates favor 8-bit Llama under all five prompts, whereas the Qwen comparison changes direction across prompts. The evaluation target can also reverse the result. For Llama under one prompt, scoring each variant only on its own clean-passing tasks favors 4-bit by 17.5 points; scoring the same tasks for both variants gives no difference, while scoring the full pipeline favors 8-bit by 28.3 points. Executor leniency is a third such choice. Rescoring the same logs with strict output parsing, which 8-bit Llama violates far more often than 4-bit Llama under that prompt, turns that +28.3 into -15.0 while leaving Qwen essentially unchanged. These findings show that one prompt, one screened task set, and one scoring policy do not establish a stable conclusion about quantized-agent robustness. Evaluations should compare variants on matched tasks, report full-pipeline success for deployment decisions, state the scoring policy, and quantify uncertainty across tasks rather than injected fault sites.
tool-usepost-training - arxiv:2610.07774 · cs.CLReading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language ModelsZiyuan Yang, Wenxuan Ding, Shangbin Feng, Yulia Tsvetkov
Vision-language models (VLMs) face compositional safety risks where harmful intent emerges from the interaction between visual and textual inputs. As mixture-of-experts (MoE) VLMs become increasingly common, recent work has explored various safety interventions, including prompting, supervised fine-tuning, and routing-based expert steering. However, these methods show inconsistent improvements across models and evaluation distributions, and the intervention into model behavior or internal states introduce safety-utility tradeoffs by over-refusal. Rather than manipulating internal states to steer model behavior, we instead ask whether routing states can serve as diagnostic signals for multimodal safety. We find that router logits indeed provide highly predictive signals of whether a multimodal input is safe or not. Motivated by this observation, we introduce a lightweight router-logit safety detector that reads out routing signals during prompt prefill and identifies unsafe requests before generation, without modifying model parameters or expert routing. Across Qwen3-VL and Kimi-VL, the proposed detector substantially reduces safety errors on the HoliSafe benchmark and resoundingly generalizes to out-of-distribution safety benchmarks featuring different safety patterns, including MISHard and MM-SafetyBench. The success of the proposed router-logit detector also suggests a broader perspective on model internals: rather than focusing only on manipulating internal components to steer behavior, simply reading naturally emerging signals and linking them to an external safety mechanism can provide a simple, effective, and non-intrusive complement to existing safety interventions.
benchmark - arxiv:2610.07772 · cs.ROModel-Based Geometry-Aware Generative Optimization for Constrained Locomotion PlanningZhilin He, Xinyuan Wang, Changliu Liu
Constrained Locomotion Planning (CLP) for quadrupeds and humanoids, where robots must satisfy collision avoidance, contact consistency, kinematic feasibility, and support constraints, is challenging under high-dimensional dynamics and highly non-convex environments. Recent Model-Based Diffusion (MBD) approaches recast trajectory optimization as posterior sampling over trajectories, using known dynamics and Monte Carlo rollouts to analytically estimate the denoising score function without demonstration learning. While constrained variants further incorporate feasibility into model-based score rollouts and show promising performance, they are still limited by (1) lacking a task-modulated active constraint geometry that shapes the score direction and reverse stochasticity, and (2) using deterministic DDPM-style reverse transport without adaptive scheduling across different generative transports. Therefore, we introduce Model-Based Geometry-Aware Generative Optimization (2GO) for constrained locomotion, which turns active constraint geometry into executable denoising operators through normal- induced metric shaping, tangent-space stochastic filtering, and CFS-based retraction. 2GO further decouples generative transport from reverse stochasticity through an adaptive diffusion and flow-like schedule. Experiments on constrained quadruped and humanoid locomotion demonstrate strong performance in discrete foothold selection and continuous posture planning, with higher success rates, fewer violations, and improved execution compatibility.
humanoidquadruped - arxiv:2610.07767 · cs.LGTRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language ModelsXin Wang, Hao Yu, Zhengyang Zhuge, Bochao Mao +8
Reinforcement learning (RL) for post-training large language models (LLMs) incurs substantial computation and memory overhead during rollout generation, which motivates low-precision rollout for efficient RL training. However, existing FP4 RL methods suffer from a key limitation: they primarily optimize quantization accuracy on the training and rollout paths independently rather than directly reducing the discrepancy between the two quantized execution paths. In this work, we propose TRACE (Train-Rollout Quantization Alignment via Compact GuidancE), an FP4 quantization framework for RL training of Mixture-of-Experts (MoE) language models that addresses the limitation of existing FP4 RL methods. TRACE incorporates rollout-guided quantization-aware training that uses rollout-side quantization outcomes to guide training-side FP4 rounding decisions, directly reducing train-rollout discrepancy. Moreover, TRACE adopts an efficient quantization-information caching scheme that selectively retains mantissa and scale information from deeper layers to reduce the storage and communication overhead introduced by rollout guidance. We evaluate TRACE on four large-scale MoE language models across reasoning, coding, and long-horizon RL tasks. Our results demonstrate that TRACE enables joint FP4 weight/activation and FP4 KV-cache rollout with RL performance comparable to BF16 rollout, while achieving up to 5.4xrollout speedup and strong final FP4 performance compared with post-hoc FP4 quantization of BF16-trained policies.
memorypost-training - arxiv:2610.07766 · cs.AIOTel: Open Telco AI Datasets, Benchmarks, and ModelsFarbod Tavakkoli, Gregory Diamos, Kenneth Church, David Kanter +14
We present Open Telco (OTel), an open telecom AI resource that releases derived telecom datasets for retrieval, reranking, instruction tuning, and safety/abstention, together with 30 full-parameter post-trained baselines spanning 10 embedding models, 3 rerankers, and 17 language models. The community has already engaged substantially with the resource: as of May 3, 2026, the released models have been downloaded over 16 million times and the project has received 157+ pieces of media coverage worldwide. Building on prior open telecom datasets and benchmarks, OTel provides documented telecom data sources, held-out evaluation partitions, trained embedding models, rerankers, context-grounded LLMs, and safety/abstention data in one unified resource. Each baseline starts from an open-weight model and is post-trained on OTel-derived data using an open training recipe, then evaluated on held-out OTel evaluation partitions. OTel post-training improves performance across all three model families: embedding retrieval reaches 93.1% NDCG@10, reranking reaches 0.947 MRR@10, and language-model correctness reaches 87.8%. We release OTel as a reproducible starting point and invite the community to expand the data, improve embedding and reranking models, and build stronger context-grounded telecom LLMs.
post-trainingbenchmark - arxiv:2610.07763 · cs.AIST-Bench: A Spatial-Temporal Benchmark for Multi-Agent System Generation on Scientific Research TasksQi Cheng, Rongchao Dong, Shengyu Chen, Licheng Liu +7
The rapid progress of LLM-based multi-agent systems (MAS) has shown that they largely outperform single agents on coding, math, and QA tasks, where executable tests provide a binary success signal. Whether this advantage transfers to real scientific data analysis remains untested. We introduce ST-Bench, a benchmark designed to answer two questions: whether MAS outperform single agents on complex scientific data analysis tasks, and if so, by how much and at what additional cost. ST-Bench contains 100 data science tasks adapted from published Earth science studies across hydrology, agriculture, and wetland methane research, expanded into 2,067 queries grounded in additional published studies and validated by domain experts. Using ST-Bench, we evaluate five recent MAS generation methods under two training protocols, against single-agent baselines on the same GPT-5 backbone. Nine of the ten MAS configurations exceed the cheapest single-agent baseline, with the strongest reaching nearly three times its composite score. This gain is primarily attributable to coverage: trained workflows produce realistic numerical metrics on a larger fraction of queries, while the quality of those metrics, conditional on producing realistic output, is comparable to that of the single-agent baseline. The strongest configuration requires approximately four times the single-agent inference time, whereas a more economical workflow captures the majority of the benefit at less than twice the cost. MAS specialization confers measurable benefit on scientific data analysis, but the benefit is conditional rather than universal.
multi-agentagent systembenchmark - arxiv:2610.07761 · cs.AIContrastive Learning for Aspect Representation towards Explainable RecommendationEmrul Hasan, Chen Ding
In this work, we propose a novel recommendation model, CLARER (Contrastive Learning for Aspect Representation towards Explainable Recommendation) that integrates aspect features learned from textual reviews with rating information to improve the accuracy and explainability of recommendations. Our proposed framework learns user and item representations by combining rating-based features and aspect-based features from reviews. Specifically, rating-based features are learned through a multi-layer perceptron (MLP) model, while aspect-specific review representations are learned using a transformer encoder to capture the semantic information and contrastive learning to better distinguish user preferences. To provide explanations, we train a transformer decoder, using the final representations of users and items from both rating and aspect-based features as context. Experimental results in three benchmark data sets demonstrate that our model achieves superior performance compared to baseline methods in both recommendation (accuracy) and explanation generation.
benchmark - arxiv:2610.07756 · cs.ROStairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action ModelsShangyuan Yuan, Xinda Qi, Yujiang Pu, Wenliang Guo +1
Vision-language-action (VLA) models increasingly rely on diffusion- or flow-matching-based action heads to generate continuous robot actions. These action heads typically process the denoising trajectory in a largely uniform manner. However, we observe that the conditioning focus naturally shifts across denoising stages: early stages combine language instructions and visual observations to establish a coarse action trajectory, whereas later stages place greater emphasis on current visual observations for action alignment. Based on this insight, we introduce StairVLA, a stage-aware hierarchical action generation framework that uses partially denoised actions as a natural interface between coarse long-horizon action generation and local refinement. A high-level VLA performs early denoising to produce a reusable long-horizon partially denoised action trajectory, while a lightweight refiner operates at a higher frequency to refine local action chunks using the latest observations. This design amortizes expensive high-level VLA computation while preserving frequent closed-loop correction. On LIBERO, our GR00T-style instantiation improves average success from 96.5% to 97.8% while reducing amortized inference latency from 115.0 ms to 44.2 ms per action chunk. More broadly, across two VLA backbones, simulation benchmarks, and real-robot tasks, StairVLA consistently reduces inference cost while maintaining strong task performance.
vision-language-actionvlaaction headgr00tliberobenchmark - arxiv:2610.07755 · cs.LGTrustworthy Method Comparison with AI Judges: Estimation and Design under Order, Batch, and Aggregation EffectsTianxi Li, Jie Ding
Large language models (LLMs) are increasingly used as judges for automated AI evaluation. A common practice is to randomize prompt sequences and average the resulting scores, but its statistical validity remains unclear. We show that LLM evaluation mechanisms can be approximated by a class of Markov generalized linear mixed models (GLMMs), supported by out-of-sample predictions across three major commercial LLMs. Using a first-order Markov GLMM, we study leaderboard ranking and group comparison. For leaderboard ranking, randomize-and-average selection is consistent under a mild separation condition, and a Williams square design can improve efficiency when item qualities are close. For group comparison, naive averaging can yield inconsistent conclusions about differences in group-level quality because of the response model's nonlinearity. Empirical results further support the validity of the proposed model-based inference beyond the first-order theory, including settings with higher-order sequence memory. We illustrate the approach in an application where AI judges compare two graphical model estimation methods.
leaderboard - arxiv:2610.07753 · cs.AIFrom Evidence to Action: How Tool-Using Agents FailHongzhan Lin, Shidong Cao, Ziyang Luo, Wenhao Chai +2
Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their actions were supported by evidence established beforehand. We study where this evidence-to-action chain breaks as agents move from deciding whether to act to executing single actions and dependent workflows. Across ten model-harness configurations, strong static action assessment can coexist with much weaker interactive execution. Failures often begin before execution: agents stop with incomplete investigation or act before required evidence is established. Once required evidence is obtained, single-action execution is usually reliable, while multi-action workflows additionally expose unresolved prerequisites and incomplete execution. For this analysis, we introduce SafeActBench, comprising 656 cases across six operational domains and five protocols that progress from static action judgment and investigated non-action to single- and multi-action workflows. A provenance-bound Evidence Ledger and deterministic trajectory evaluator track what information was established, when actions occurred, and whether downstream dependencies were satisfied. These results show that failures arise not only from missing information, but also from how agents use established evidence when deciding and executing actions.
evaluator - arxiv:2610.07752 · cs.ROCoRE: Learning Collaboration-Role Experts for Decentralized Collaborative Manipulation with One PolicyYanan Zhou, Zhaoyan Qian, Zihao Li, Mingyuan Ba +2
Collaborative manipulation requires robots to perform complementary actions as interactions unfold. We study single-policy decentralized collaboration: every robot runs the same policy from its visual observations and proprioception, without task prompts, identity labels, or inter-robot messages. The challenge is to learn complementary team behaviors within shared parameters and select appropriate actions from each robot's local observations. We introduce CoRE, which learns Collaboration-Role Experts from pooled multi-task, multi-robot demonstrations. Fused appearance and geometry provide local interaction evidence. Query-conditioned cross-attention experts provide adaptable prediction paths, which a local router combines at each action-chunk position. During training, an action-expert alignment loss supervises expert selection using relative forced-route prediction errors against demonstrations under fixed inputs, without role labels. Across simulation benchmarks, CoRE achieves the highest average performance among evaluated decentralized methods. Physical experiments demonstrate effective collaboration across diverse manipulation tasks and robustness to partner delays and slowdowns. Project page: https://aus.bot/research/core/.
manipulationbenchmark - arxiv:2610.07751 · cs.AIHow Well Do LLMs Reason with Noisy Evidence? An Active Visual Reasoning BenchmarkBach Nguyen, Zhaonan Li, Mau Son Nguyen, Sanika Chavan +4
Real-world reasoning rarely reduces to static question answering: agents must actively gather information from tools and sensors that are often noisy and unreliable. Yet most existing active reasoning benchmarks assume that environmental feedback is trustworthy, or introduce noise without exposing an explicit, calibrated uncertainty signal, leaving open how LLMs should reason when the evidence itself is uncertain. We introduce VisualNoiseQA, a novel benchmark for active reasoning under noisy visual feedback. A text-only LLM must solve VQA problems by iteratively querying a fixed, off-the-shelf VLM treated as a stochastic visual sensor. For each query, we draw multiple samples and expose an empirical uncertainty signal via self-consistency, enabling the reasoner to probe from different angles and decide what to ask next and when to stop. Our construction is automatic and scalable: starting from diverse VQA sources and two noisy VLMs, we retain only questions where the sensor is inconsistent yet human-solvable. We evaluate multiple LLM reasoners on 1,000 instances spanning perception, chart understanding, and knowledge-intensive reasoning. VisualNoiseQA thus provides a controlled playground to study how different LLMs exploit uncertainty signals for robust reasoning.
benchmark - arxiv:2610.07745 · cs.ROSeeing Through the Displaced Frame: Privileged Noise Distillation for Vision-Force Precision AssemblyChing-Hsiang Chang, Tzu-Yu Chuang, Yi-Hsiu Lee, Yi-Ting Chen +2
Pose error in precision assembly can corrupt not only what a robot observes but also the coordinate frame in which it acts. On the FORGE benchmark, the official state-based policy succeeds in 97% to 99% of episodes with the true pose but only 32% to 60% at the benchmark's $σ=5$ mm pose-noise setting. The same estimated pose enters the observation and anchors the action frame, making the offset unidentifiable from proprioceptive state alone before contact. We supply this missing information during training in two ways. A privileged teacher observes the offset in simulation, while clean demonstrations can instead be relabelled into the displaced frame in closed form. The deployed student is trained with behaviour cloning followed by one DAgger round and receives only noisy state, a raw wrench window, and two RGB cameras at test time. On the unmodified FORGE tasks, the teacher-route student maintains 92% to 99% success across $σ=0$ to 5 mm, while six non-privileged baselines fall to 2% to 80%. A matched behaviour-cloning experiment isolates the source of this robustness. With the same student architecture, data budget, and training procedure, demonstrations generated without offset access yield only 31.5% success at $σ=5$ mm, whereas privileged and relabelled demonstrations reach 88.7% and 95.8%. Deployed zero-shot on a Franka, the student reaches 83.3% pooled success at $σ=5$ mm against 34.4% for the strongest state-based policy. Deployable sensing alone is insufficient. Robustness requires supervision that encodes compensation for the latent frame offset.Project page: https://drychang.github.io/displaced-frame/
frankabenchmark - arxiv:2610.07739 · cs.LGCite What You Explore: Budget-Aware LLM Reasoning over Medical KGs with Verifiable EvidenceChen Chen, Dongjie Wang, Mei Liu, Zijun Yao
Post-discharge risk prediction from electronic health records (EHRs) is difficult because many dependencies that link discharge-time observations to downstream complications, such as comorbidity cascades and drug-disease interactions, are absent from the record. External medical knowledge graphs (KGs) can supply these missing dependencies, but tracing them demands three properties: KG exploration must remain cost-bounded, retrieved evidence must be differentiated by source quality, and the resulting rationale must be citable for retrospective review. Large language models (LLMs) can plan and verify over structured evidence, making them natural candidates for KG reasoning, but existing LLM-based methods do not satisfy these three properties jointly. In this paper, we propose BAR, a Budget-Aware LLM Reasoning framework over medical KGs with three contributions. First, BAR refines the raw KG into disease-specific evidence graphs whose edges carry support scores and provenance records, turning the KG into a quality-annotated reasoning space rather than a static feature source. Second, an LLM then reasons over this graph through a plan-navigate-verify loop that decomposes the question into steps, retrieves evidence under a patient-specific budget, and revises when verification fails. Third, a reasoning policy is trained with a reward that compares predictions with and without acquired evidence, combined with acquisition cost and citation-integrity terms. Across 8 diseases and 3 prediction horizons on MIMIC-III and MIMIC-IV, BAR improves AUPRC by 3.4 points over the strongest baseline, raises citation precision from 59.8% to 77.9%, and consumes only 62-65% of the budget cap.
knowledge graph - arxiv:2610.07731 · cs.LGLearning to Retrieve via Reinforcement Learning in Embedding SpaceQi Liu, Fengming Liang, Yiqun Chen, Erhan Zhang +1
Dense retrieval models are typically trained with contrastive objectives that learn effective representations but do not directly optimize retrieval metrics or downstream task performance. To address this problem, we introduce RELER (REinforcement LEarning for Retrieval), a reinforcement learning framework that enables existing embedding models to learn to retrieve directly in embedding space and align to task-specific rewards. We train RELER by sampling unit-length query and document embedding actions from von Mises-Fisher (vMF) distributions centered on normalized encoder outputs, scoring the resulting retrieval or downstream outcomes as rewards, and updating the encoder with REINFORCE using a leave-one-out baseline (RLOO). As exploration in the high-dimensional embedding space is prone to sampling noise, we further propose conditional-mean projection (CMP), which projects each sampled embedding onto the low-dimensional subspace spanned by its encoder output and the candidate embeddings it is compared against, reducing noise in the policy gradient while preserving its expectation. We evaluate RELER on BRIGHT, a benchmark with reasoning-intensive queries that remain challenging for existing embedding models. RELER consistently outperforms InfoNCE and LambdaLoss in average nDCG@10 when post-training BGE-M3 and Qwen3-Embedding backbones. We further evaluate downstream utility through retrieval-augmented generation (RAG), where we adapt only the query encoder while keeping the document index and generator fixed. Across seven QA datasets, jointly optimizing retrieval and answer rewards improves both average retrieval performance and answer quality in RAG.
retrieval-augmentedpost-trainingbenchmark - arxiv:2610.07725 · cs.AIPERSIST: Who-What-When Memory Across Sessions for Full-Duplex Spoken DialogueAchira Lin, Siyuan Hou, Wenyi Yu, Xinnian Zhao +6
Modern voice assistants may be shared by multiple users and should be able to answer questions about earlier conversations such as "When did I originally plan to leave?" or adapt their behavior to individual users based on past interactions. This requires more than retrieving a topically similar passage: the assistant must identify the current speaker, recover the relevant past state, and distinguish it from later revisions. We present PERSIST, a persistent memory system for multi-session, multi-speaker spoken dialogue that explicitly models Who, What, and When. PERSIST structures cross-session histories into readable event records and retrieves them with a 3W joint scoring mechanism that combines semantic content, acoustic speaker identity, and temporal state. For real-time full-duplex interaction, PERSIST further reuses intermediate representations from the dialogue backbone, avoiding query-audio re-encoding and reducing retrieval latency from 578.42 ms to 7.03 ms. We also introduce SpokenTrace, a diagnostic benchmark that factorizes evaluation along memory tasks and speaker-query types, exposing failures in recall, speaker attribution, and temporal-state tracking. On SpokenTrace, PERSIST achieves 85.08% end-to-end task accuracy and improves all-support EM@3 from 49.01% with BGE-large to 82.10%.
memorypersistent memorybenchmark - arxiv:2610.07722 · cs.CLDoes Steering Break Your Model? A Multi-Dimensional Evaluation Suite for LLM Steering MethodsHaotian Yang, Huikang Jiang, Yucheng Wu, Wen-Jie Jiang +3
Activation steering provides a lightweight and flexible way to control large language model (LLM) behavior. However, effective steering requires more than inducing the intended behavior: it should also limit unintended changes and remain robust across inputs and training data. Existing evaluations cover these dimensions only in fragments. As a result, the trade-offs between efficacy and side effects have not been systematically characterized. We introduce SteerScope, a two-axis, multi-dimensional evaluation suite that jointly characterizes steering outcomes and method properties through 15 metrics. We score target efficacy and side effects on language quality, task capabilities, and safety and reliability, and further assess generalization and data dependence through steering-specific metrics for sample efficiency and sample sensitivity. Rather than comparing methods at a single operating point, we characterize the trade-offs between efficacy and side effects. Under matched models, tasks, and evaluation protocols, we benchmark 23 methods spanning 4 families, including prompting, LoRA, and SFT as baseline methods, and release the suite as an extensible codebase. We find that current activation steering methods do not yet surpass the Prompt Steering baseline in their overall balance between steering efficacy and side effects: across both model scales, no evaluated activation steering method achieves higher efficacy without incurring greater composite side effects. We further uncover a consistent coupling between steering efficacy and side effects. Under OOD prompts, target efficacy is often preserved, whereas side effects tend to become more pronounced, particularly through declines in instruction relevance and fluency. Methods also exhibit sharply different sample-efficiency profiles.
benchmarkevaluation protocol - arxiv:2610.07720 · cs.LGRefRoute: Decoupling Conditioning Cost from References via Compact Residual Conditioning and Spatial RoutingWanning He, Yuyao Zhang, Yu-Wing Tai
Multi-reference image generation requires preserving the appearance of multiple subjects while composing them into a coherent scene. However, existing diffusion transformers commonly encode references as dense visual token grids and jointly process them with global attention, making conditioning increasingly expensive as the number and resolution of references grow. We present RefRoute, a framework that addresses both reference representation cost and attention overhead through two complementary mechanisms. Compact residual conditioning combines low-resolution latent tokens with lightweight residual features extracted from full-resolution pixels, reducing reference token counts while retaining fine-grained appearance cues. Condition routing and attention routing align reference tokens with their assigned target regions and restrict cross-reference interactions, while allowing selective reference access beyond region boundaries for scene integration. We further introduce RefRoute-Data for training many-reference generation models and ManyRef100, a benchmark spanning human, object, and mixed compositions with 10-17 references. After many-reference fine-tuning, RefRoute achieves an overall Weighted-Ref-VIEScore of 36.06 on ManyRef100, compared with 8.88 for FLUX.2-Klein-9B. Separate inference-cost evaluations show substantially slower latency growth as the reference count increases: at 16 references, our 50-step and 4-step configurations achieve $18.3\times$ and $14.2\times$ speedups over their corresponding FLUX baselines, respectively. These results establish compact reference representations and spatially routed attention as an effective approach to scalable many-reference image generation.
benchmark - arxiv:2610.07715 · cs.CLWhen Old Facts Return: Re-Reads, Reverts, and the Limits of Temporal MemoryNeeraj Yadav
A memory system can retire an obsolete value and later restore it merely because the same old statement appears again. A re-read of an old source and a genuine revert can produce the same observed sequence of values while requiring opposite current answers. We study this ambiguity on 130 extractor-selected atomic transitions derived from software fixes. In the ordinary transition condition, identity-based temporal memory reaches 98.5% model-judged accuracy with zero observed errors under a literal stale-value proxy. Appending a verbatim re-read of the old statement reduces accuracy to 10.8% and raises the stale-value rate to 88.5%. A guard that refuses to reactivate a previously retired value restores accuracy to 97.7% and reduces that rate to 0.8% in this constructed re-read condition. The guard cannot also recognize a legitimate revert without additional change provenance. Two supporting studies examine exposing retired history to the answer model and supplying current source for changed behavior. An exploratory extraction study over 707 software fixes provides scope context, not a universal coverage estimate. The design implication is to distinguish an observation of a value from evidence that the value changed. Selected inputs, aggregate-only answer records, related-family judges and a post-failure guard evaluation limit the conclusions to the retained experiments.
memory - arxiv:2610.07711 · cs.CVComprehensive Evaluation and Fine-Tuning of Foundational Cell Nuclei Segmentation Models in Renal PathologyRuijie Wu, Junlin Guo, Ruining Deng, Yu Wang +3
Accurate nuclei instance segmentation is essential for quantitative renal pathology, yet general-purpose models often struggle with low contrast, dense nuclei, complex morphology, and strong background staining. In this work, we extended a human-in-the-loop framework by combining 5,901 foundation-model-generated pseudo-labels from well-segmented cases (Easy), 860 newly expert-annotated unresolved challenging cases (Medium), and 198 expert-annotated consensus failure cases (Hard). These annotations, spanning different levels of segmentation difficulty, enabled the systematic evaluation of seven single-source and mixed-source fine-tuning strategies across nine cell segmentation model configurations. Fine-tuning improved all models, with Medium data included in seven of the nine best-performing strategies. LSP-DETR achieved the highest F1 score of 0.8725 with Hard-only fine-tuning, while StarDist showed the largest improvement, increasing from 0.7380 to 0.8332 with Medium-only fine-tuning. These findings show that annotations spanning multiple difficulty levels support effective model adaptation, although the optimal annotation composition remains model dependent.
human-in-the-loop - arxiv:2610.07707 · cs.AIAgentMemGate: Addressing Speculation Contamination in Conversational Assistant MemoryChirag Sharma, Benjamin Fowlersmith, Karime Maamari
Conversational AI assistants with long-term memory extract facts from user messages into a store consulted in later conversations. A stated plan can enter that store as fact: a user who might move to Seattle may be recorded as already living there. We call this speculation contamination. Final-state memory benchmarks miss this error because they do not probe intermediate state and include few unresolved speculations. We present AgentMemGate, a write-time gate for profile-store memory that classifies extracted statements as speculation, completed event, correction, or other. Speculations remain outside memory, with conditions governing later promotion or deletion. We also contribute a dataset of multi-session conversations in which plans are confirmed, abandoned, or left unresolved. On our 147-conversation held-out set, Mem0 and Graphiti assert unresolved plans as current state for 35.2% and 27.3% of pending plans. On the core benchmark, AgentMemGate eliminates all observed contamination relative to the identical ungated pipeline (87.5% to zero for the most exposed extraction style) and raises task accuracy from 65% to 95%. On the harder held-out set, gated contamination is 3.4% to 5.7% and task accuracy rises by 9 to 13 percentage points. Our analysis identifies field matching as the main remaining bottleneck: realistic speculations often match no profile field and never reach the gate. We release our datasets, prompts, and evaluation code.
memorybenchmark - arxiv:2610.07706 · cs.LGWASD: Wasserstein-based Knowledge Distillation for Large Language ModelsByeonghu Na, Donghyeok Shin, Yeongmin Kim, Mina Kang +1
Autoregressive large language models (LLMs) have rapidly advanced in capability, but their increasing scale comes with substantial computational and memory costs at inference time. Knowledge distillation (KD) offers a practical solution by transferring knowledge from a large teacher model to a smaller student model via alignment of discrete probability distributions. However, existing KD methods for LLMs primarily rely on divergences that evaluate discrepancies through probability values at each vocabulary index, without explicitly leveraging token-level semantic information. We propose Wasserstein-based knowledge distillation (WASD) for LLMs, which incorporates token-level semantic information via the Wasserstein-based distance with a cost matrix derived from token embeddings. To ensure computational tractability, we adopt the Sinkhorn divergence and derive a gradient-equivalent objective that can be efficiently optimized without introducing additional networks. Experiments across multiple LLM families and scales show that WASD consistently improves distillation performance on diverse tasks, including instruction following, mathematical reasoning, and code generation. Our results highlight the importance of semantic information encoded in the token space for effective distribution alignment in LLM distillation. The implementation is publicly available at https://github.com/aailab-kaist/WASD .
memory - arxiv:2610.07704 · cs.LGIndependent Multi-Agent Reinforcement Learning with Counterfactual Semantic-Social World ModelsFernando Martinez, Tao Li, Yingdong Lu, Juntao Chen
Fully decentralized multi-agent reinforcement learning (MARL), also referred to as independent learning, requires each agent to learn and act using only its local information and experience, without a centralized critic or inter-agent communication. Such a stringent information structure renders the conventional reward signal ambiguous. A poor return may result from an ineffective ego action, an incompatible teammate response, or an effective opponent response, yet scalar rewards alone do not reveal which explanation is responsible. We argue that agents can learn more effectively by prospectively comparing the consequences of candidate actions rather than diagnosing failures only from realized returns. We introduce CASTLE (Counterfactual Action-conditioned Semantic Tokens for Local Execution in Decentralized MARL), an offline-training, online-in-context guidance framework with two complementary world models. A Local Dynamics World Model, offline pre-trained over agents' local trajectories, summarizes the agent's local trajectory dynamics and partial observability, while a Semantic-Social World Model predicts compact short-horizon task and social consequences for each candidate ego action. The latter is trained from counterfactual simulator rollouts that expose plausible teammate and opponent responses to alternative actions taken from the same logged rollout state. During online learning and execution, both world models remain frozen and are queried by agents using only locally available information. Their prediction logits provide in-context guidance to an independent PPO policy. Across 30 matched seeds on Tag, Spread, and Adversary in the benchmark multi-particle environments, our proposed CASTLE achieves the highest mean final score among the evaluated methods, exceeding the strongest baseline on each task by 10.67, 6.46, and 0.33 normalized points, respectively.
world modelaction-conditionedagentmulti-agentonline learningbenchmark - arxiv:2610.07700 · cs.CLDetecting LLM-Assisted Vietnamese Writing via Keystrokes under Behavioral ManipulationThanh Dong, An Ngo, Minh Dau, Rajesh Kumar
We study the robustness of keystroke dynamics for detecting large language model (LLM)-assisted writing. We introduce a Vietnamese keystroke dataset capturing realistic writing modes, including bona fide composition, transcription, and paraphrasing. We also define a behaviorally grounded threat model in which users deliberately alter typing patterns. To implement the threat model, we create behaviorally manipulated variants of the data designed to evade keystroke-based detection. We evaluate four keystroke modeling approaches: temporal and rhythmic representations, and sequential representations modeled with a one-dimensional convolutional neural network (1D-CNN) and TypeNet, under user-independent and context-independent settings. The results show that sequential models outperform feature-based approaches in most cases and that keystroke signals encode discriminative information about the writing process. However, detection is not uniformly robust: transcription is reliably identified, while paraphrasing and adversarially manipulated samples are frequently misclassified as bona fide when not explicitly modeled. To address this, we incorporate adversarial training using behaviorally manipulated data, which substantially improves separability and robustness. These results suggest that keystroke-based detection depends critically on exposure to diverse writing behaviors, and that strong performance under limited conditions does not generalize to realistic or adversarial settings without targeted modeling.
manipulation - arxiv:2610.07699 · cs.LGImproving Synthetic Data Generation for Argument Mining via Adversarial Reinforcement LearningZhijun Zhang, Qianlong Wang, Keyang Ding, Genan Dai +4
Argument Mining (AM) is fundamentally constrained by the scarcity of high-quality structure-annotated datasets. While LLMs have shown promise in synthetic data generation, producing synthetic AM data that is both structurally accurate and sufficiently diverse remains a challenging problem. To address this problem, we revisit synthetic data generation for AM from a new perspective and propose a novel adversarial reinforcement learning framework for data synthesis. The proposed framework jointly optimizes the generator and the discriminator in an adversarial loop, in which the generator produces structured AM instances, and the discriminator provides learning signals by distinguishing real data from synthetic candidates. This enables the generator to progressively improve both the structural accuracy of generated argument data while maintaining diversity through adversarial feedback. Extensive experiments demonstrate that the proposed framework consistently improves AM performance on three benchmark datasets in both full-data and low-resource settings, validating its effectiveness and scalability.
benchmark - arxiv:2610.07696 · cs.ROESP: Energy-Score Policy for One-Step Multimodal Action GenerationLilika Makabe, Heecheol Kim, Yasuyuki Matsushita
Generative action models based on diffusion and flow matching have been increasingly adopted in vision-language-action (VLA) policies for their ability to capture diverse behaviors, including multiple valid action sequences under the same observation and instruction. Their iterative sampling procedures, however, require repeated network evaluations to generate each action chunk, increasing inference latency in closed-loop control. We propose ESP (Energy-Score Policy), a teacher-free approach that maps policy context and noise directly to an action chunk in a single network evaluation. ESP trains the action head with the energy score rather than mean squared error. Whereas squared-error regression targets the conditional mean, the energy score is strictly proper: its expected value is uniquely minimized by the target distribution. This provides a principled objective for learning multimodal action distributions without iterative sampling, with exact recovery at the population optimum when the model can represent the target distribution. Experiments on both simulation and real-world manipulation tasks demonstrate competitive task success with substantially lower action-generation latency than the flow matching baseline. These results support direct distributional learning as an efficient alternative to iterative generative robot policies.
vision-language-actionmanipulationaction head - arxiv:2610.07692 · cs.ROExoBridge: Learning a Bare Hand to Hand-Worn Exoskeleton Mapping through Human Limb CouplingRuitong Tian, Xianyao Li, Noah B. Wilson, Fang Xu +1
Human video offers a scalable source of experience for dexterous robot learning, but obtaining motion and tactile supervision while preserving bare hand interaction remains challenging. We present ExoBridge, a framework that leverages human limb coupling to learn a bridging function from bare hand video to the motion and tactile state of a sensorized exoskeleton. Our central idea is to use coordinated bimanual behavior to connect an uninstrumented visual source with a measured manipulation interface. During collection, one hand remains bare and provides visual observations, while the opposite hand wears the exoskeleton and supplies synchronized motion and tactile measurements. These paired demonstrations train a temporal visual model to predict fingertip contact, continuous tactile intensity, and relative encoder motion from bare hand video alone. The exoskeleton defines an intermediate state space whose motion coordinates are linked to a dexterous robot hand through existing calibration. Evaluation on 1,215 demonstrations across four manipulation tasks uses held out collection sessions and yields a pooled any contact AUROC of 0.916 and a Pearson correlation of 0.790 for tactile intensity. The learned bridge also predicts relative changes in exoskeleton configuration from bare hand video. These results demonstrate that human limb coupling can turn exoskeleton measurements into supervision for bare hand video, establishing a learned bridge between human visual demonstrations and a robot oriented manipulation interface.
manipulationdexteroustactile - arxiv:2610.07686 · cs.AIBluffJAX: Adversarial Imperfect Information Games in JAXAryaman Reddi, Jan Peters, Carlo D'Eramo
We introduce BluffJAX: an open-source suite of adversarial imperfect information games in JAX. We provide canonical implementations of games designed for high simulation throughputs and parallelization on GPU accelerators. Our suite consists of well-studied benchmarks such as Texas Hold'Em Poker and Kuhn Poker, as well as games that have not been previously studied in reinforcement learning research, such as Bluff, Stud Poker, and Kemps. We hope that implementing a variety of game mechanics and difficulties will introduce new challenges and foster novel research directions in game-theoretic methods for RL. We benchmark the throughput performance and memory usage of our environments in single and multi-GPU settings, demonstrating scaling of up to hundreds of millions of samples per second, and motivating the usage of BluffJAX over related GPU and CPU-based libraries. We benchmark reinforcement learning, tree search, and game-solving algorithms in JAX in order to provide users with baseline results and facilitate future comparisons.
memorybenchmark - arxiv:2610.07681 · cs.ROEigenDEXplore: Structured Exploration for Dexterous Manipulation with Human PriorsHarsh Gupta, Tyler Ga Wei Lum, Changhao Wang, Chuer Pan +3
Dexterous manipulation poses a challenging high-dimensional optimization problem, as useful behaviors require coordinated motion across many hand joints. In reinforcement learning (RL) and sampling-based trajectory optimization, exploration commonly relies on independent robot joint perturbations, making coordinated behaviors difficult to discover. Prior work reduces this search space for grasp learning using low-dimensional spaces of coordinated joint motions learned from human hand data, but this restricts the expressivity required for general manipulation. Some combine learned and joint-space actions to restore expressivity, but this increases dimensionality and introduces redundancy. We study these effects across diverse manipulation settings, varying action dimensionality, exploration strategy, and the source of human data. Our experiments suggest that human-motion priors are most effective when used to structure exploration rather than change the action representation. Motivated by this finding, we propose EigenDEXplore, which induces correlated exploration by adding perturbations along human-derived eigenvectors to independent joint-space noise, leaving the action space unchanged. Across multiple dexterous hands, EigenDEXplore consistently outperforms joint-space and learned action-space baselines in grasping, in-hand reorientation, and contact-rich manipulation. These gains span unstructured and reference-guided RL, trajectory optimization, and sim-to-real deployment, and are largest in settings with less reward shaping and curriculum design.
manipulationdexteroussim-to-realgrasp - arxiv:2610.07677 · cs.LGAdaptive Model Inversion Attacks Generalize a Privacy-Robustness TradeoffShailen Smith, Rasmus Torp, Adam Breuer
In this paper, we show that standard evaluations of high-resolution Model Inversion Attacks (MIAs) significantly underestimate training-data privacy leakage. State-of-the-art privacy defenses, standard training techniques such as MixUp and Adversarial Training, and undefended models all leak training images at rates 1.16 to 6.59 times higher on FaceScrub under simple adaptive changes to the attack, with the largest increases among defenses reporting the strongest privacy. We further show that measured leakage depends on the feature basis of the external classifier used to evaluate reconstructions: for the same reconstructed images, an adversarially trained Inception evaluator identifies the targeted identity at different rates than the standard Inception evaluator. Our results suggest that standard MIA evaluation can mistake optimization and measurement failures for privacy. These underestimated leakage rates also concealed a broader relationship between privacy and adversarial robustness. Once we adapt the attack and vary the evaluator, reconstruction leakage closely tracks adversarial robustness across recent defenses and standard training regimes, suggesting that robustness provides an attack-agnostic proxy for reconstruction vulnerability that applies far more broadly than previously theorized. This raises an open question: can a practical defense reduce training-data reconstruction without paying a corresponding cost in adversarial robustness?
evaluator - arxiv:2610.07675 · cs.AIEIO-Agents: The Missing Semantic Layer for AI Agent EvaluationFouad Bousetouane
AI agents are entering production in increasingly consequential environments without a shared semantic standard for what their evaluations actually mean. Scores, traces, judge outputs, and multi juror findings are increasingly used to justify readiness and release decisions, yet they often do not specify what evidence supports a claim, what that evidence can establish, or how the claim leads to a decision. We introduce EIO-Agents, an open specification for interoperable AI agent evaluation built on two layers. The Evaluation Intelligence Ontology (EIO) provides the semantic layer through typed evidence, versioned behavioral predicates, evidence contracts, claims, witness rules, proof status, recurrence, and computable derivations for metrics, findings, controls, and PASS, REVIEW, or BLOCK decisions. The Portable Evaluation Record (PER) provides the system of record: a canonical, content addressed representation of one evaluation that preserves the evidence to decision chain and can be re derived, explained, and verified. Scores summarize, juries interpret, and traces record, but none of them define what the evidence means or what it can prove. EIO provides that missing semantic contract, while PER preserves the resulting evaluation as a portable and verifiable system of record. As AI agents assume greater operational responsibility, evaluation must become more than a collection of scores and verdicts; it must become an accountable artifact whose meaning, evidence, limitations, and decisions can be independently checked.
agentai agent - arxiv:2610.07669 · cs.AIEvaluating human-AI workflows for field research in viticultureNiko Carvajal Janke, Daoyuan Jin, Shivranjani Baruah, Nicholas Gunner +3
We assessed the value of two live human-AI interactions in a precision disease control project in California vineyards. The project tested whether 2021-2024 commercial scouting records and remote-sensing measurements across 140 hectares could support 2025 red-leaf symptom forecasting for prioritized scouting and virus testing. In Workflow 1, Aleks v1, a multi-agent research system, developed forecasting models with iterative human refinement. We applied Aleks's 2024 vine-scale model to updated 2025 predictors and evaluated red-leaf forecasts against independent 2025 scouting. In retrospective simulations surveying 45% of all vine positions, adding model-informed row prioritization to adaptive scouting increased the encountered proportion of newly recorded red-leaf observations from 85.8% to 94.1%. Within-block scouting comparisons suggested the model mainly improved scouting allocation among blocks. Despite unreliable internal 2024 performance estimates from synthetic oversampling before train/test splitting, Aleks developed an informative vine-scale model in 145 minutes, increasing throughput and answering our research questions. In Workflow 2, we assessed whether higher model-score vines had more frequent virus detection, and whether Aleks could infer this sampling goal from a general prompt with data and literature. Aleks's plan prioritized balanced vineyard and model score coverage, while our plan prioritized field efficiency and high-model-score oversampling. Aleks's and our plans yielded 41/50 (82%) and 97/100 (97%) sampled vines. Aleks's plan omitted instructions for replacing missing vines, limiting implementation and operational value. Five of 137 sampled vines tested positive for grapevine red blotch virus (model score ROC AUC 0.735). These findings support assessing AI interactions by how well they advance field research objectives under live, project-specific constraints.
multi-agent - arxiv:2610.07663 · cs.LGJoint Workflow and Prompt Optimization for User Behavior SimulationNipun B Nair, Tongtong Wu, Hongzhi Yin, Hui Li +1
User behavior simulation is the computational modeling of user interactions within information systems through the use of simulated agents in place of live users. It supports system testing and evaluation, decision-making and forecasting, and user experience design. Existing simulators rely on hand-crafted rules or domain expertise that transfers poorly across tasks. SWORD (Simulation-driven Workflow and Prompt Optimization with Role-based Design) is introduced as a framework that jointly optimizes multi-agent workflow topology and natural-language prompts. It is guided solely by a scalar task metric, without domain initialization or task-specific engineering. The experimental results demonstrate that SWORD achieves statistically significant gains over prompt-only, workflow-only, and staged-optimization baselines under a controlled, identical-backbone comparison. Against the strongest published domain-specific baseline, SWORD further improves accuracy while using a smaller backbone model, substantially less training data, and a very reasonable API cost (\$4--\$6 for each dataset). Beyond predictive performance, SWORD autonomously discovers domain-relevant signals, review-sentiment mapping rules and epidemiological decay priors, purely from scalar error feedback, establishing textual gradients as a mechanism for unsupervised feature-importance discovery in user behavior modeling.
multi-agent - arxiv:2610.07662 · cs.LGMS-ECG-FM: Towards a More Universal Electrocardiogram Foundation Model for Health Monitoring using Multi-source Contrastive LearningRobert A. Lewis, I-Min Chiu, Kyle Verrier, Karthik Jayaraman Raghuram +6
Electrocardiography (ECG) records the electrical activity of the heart, aiding diagnosis by detecting abnormalities in cardiac function. ECG foundation models have demonstrated promising results, but are limited by a reliance on ECG interpretation reports as their sole supervision. Because interpretation reports only capture the subset of waveform information routinely recognized by clinicians, this constrains representation learning to overlook the broader diagnostic signals present in ECG. We introduce a new ECG foundation model --- MS-ECG-FM --- that is trained through contrastive alignment to multiple distinct clinical note types, including ECG, echocardiography, radiology, and discharge reports. We evaluate MS-ECG-FM on an extended set of ECG detection benchmarks, showing that it comprehensively outperforms existing methods on the full span of conditions that ECG can detect, including in reduced-lead configurations. Different reports improve representations for different diagnostic domains, while multi-source alignment captures their complementary information and produces consistently strong representations across clinically diverse tasks.
benchmark - arxiv:2610.07657 · cs.AIWhere Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems SecurityShaswata Mitra, Raj Patel, Subash Neupane, Sudip Mittal +2
LLM-based multi-agent systems (MAS) engage tools, share memory, and delegate tasks, often encountering adversarial content. Current defenses for MAS are typically evaluated in isolation, focusing on one attack type at a time, which can lead to costly and hard-to-audit outcomes. This study organizes defenses into five principles, implementing them as DEFER1 (DEterministic-First Enforcement with Residual judgment), which includes a cascade of 28 checks that blocks what it can and refers the rest to a panel of four judges. In independent testing across four domains, attack success rates drop from about 30.0% to approximately 3.0%, with 78% of blocked attacks handled by deterministic checks. Only a quarter of proposals reach the judges in the security-operations domain, illustrating that the rules provide security for attacks violating clear policies, while judges manage those that only misrepresent intent. Both systems have weaknesses, such as a risk-score approval gate that inaccurately approves most attack proposals but few legitimate ones, highlighting the challenges in assessing threats accurately.
multi-agentagent system - arxiv:2610.07652 · cs.ROSMART: Zero-Shot Sim-to-Real Articulated Object Manipulation via Large-Scale Synthetic PretrainingJicong Ao, Shuhan Jiang, Yuling Zhong, Yanwen Liu +6
The ability to interact with articulated objects is essential for embodied intelligent systems, but collecting large-scale real-world demonstrations for these interactions remains challenging due to the precise contact and constraint-following motions involved. Although simulation provides a promising alternative, existing synthetic data efforts cover limited articulated-object categories, while general-purpose synthesis pipelines lack explicit designs for part-level semantics and articulation constraints, hindering agentic task generation and scalable synthesis of high-quality articulated-manipulation demonstrations. To bridge this gap, we introduce SMART, a scalable system leveraging large-scale Synthesized Manipulation demonstrations for ARTiculated-object manipulation. At its core, we develop SMART-Sim, a simulation platform with articulation-aware design that enables effective task generation and efficient demonstration collection. Building on SMART-Sim, we apply agentic task generation and design a scalable distributed synthesis system, using them to synthesize SMART-Data, comprising over 1M demonstrations across 44 atomic task types, 5 robot setups, and 2,507 articulated objects. The vision-language-action (VLA) model pretrained on SMART-Data shows competitive performance on simulation benchmarks and achieves zero-shot sim-to-real transfer and scalable performance in real-world articulated-object manipulation tasks. This highlights the potential of synthetic demonstrations in providing effective and scalable supervision for improving VLA model performance in contact-rich articulated-object manipulation.
vision-language-actionvlavla modelembodiedmanipulationsim-to-real - arxiv:2610.07649 · cs.ROOntoPlan: An Ontology-Grounded Scene Representation and Agentic Framework for Scalable Robot Task PlanningHyeongwoo Nam, Woongje Cho, Juwon Kim, Jongeun Choi
Large language model (LLM)-based robot task planning is promising for open-ended instruction following, but degrades on long-horizon tasks in large environments. When spatial information is conveyed to the LLM through text, the model can fail to capture spatial context, and token cost grows with environment size. Generating action sequences directly with an LLM also makes it difficult to satisfy the current world state and action preconditions. We address this with an ontology-grounded scene representation that aligns objects, spaces, relations, and states in a shared symbolic vocabulary for spatial reasoning and task planning, and with OntoPlan, an agentic framework that interprets instructions, selectively retrieves task-relevant information, formalizes goals and constraints, and produces executable plans. Across 150 general tasks spanning five indoor environments and three scene scales, OntoPlan achieves 0.89 average task success, compared with 0.27 for the strongest baseline, while using 18.1k total tokens per task on average, about 5.6$\times$ fewer than the most efficient baseline. These advantages persist as scene scale increases, whereas prior methods degrade more sharply in success and remain far more costly in tokens. OntoPlan also responds appropriately to ambiguous or infeasible instructions by asking follow-up questions or reporting insufficient information rather than committing to invalid plans. Code available at https://github.com/namhyeongwoo/OntoPlan.
agentic - arxiv:2610.07646 · cs.AIMatching Object or Relation? Tracing Abstract Reasoning Inside VLMsGouki Minegishi, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa +1
Vision Language Models (VLMs) excel on visual benchmarks but fail systematically on tasks requiring abstract reasoning. Existing benchmarks document this failure but cannot say \emph{why} it happens or which cognitive capability is missing. We close this gap by adopting the Relational Match-to-Sample (RMTS) paradigm from comparative and developmental psychology and pairing it with a mechanistic analysis of the model's internals. On a parametrically controlled stimulus set evaluated across frontier API models (GPT, Claude, Gemini) and three open-source families (Qwen3.5, Gemma-4, InternVL3), we identify four levers that shift VLMs toward the relational match---capability tier, model scale, the number of objects per scene, and the absence of per-object stimulus noise---together producing a developmental-like trajectory that mirrors the human \emph{relational shift}. Opening up the model, a per-layer representational similarity analysis and a causal mediation analysis reveal that VLM abstract reasoning is implemented by two competing circuits: an early circuit that organises images by their surface object features, and a late circuit that organises them by their abstract relation. Extending the analysis to ARC-AGI-1, we find that ablating the relational heads identified on RMTS degrades performance more than ablating random heads, indicating that the relational circuit is recruited beyond our controlled stimuli. We hope this mechanism-level view serves as a step toward understanding how abstract reasoning is implemented in VLMs.
benchmark - arxiv:2610.07645 · cs.AISkillPoison: Progressive Skill Poisoning via Successful ExperiencesLizhi Zhang, Xin He, Dianxuan Fu, Yuyuan Feng +4
Self-improving LLM agents increasingly distill successful experiences into persistent, reusable skills. Existing skill attack methods corrupt this learning pipeline by injecting malicious triggers, behaviors, or false facts into individual experiences or extracted skills. However, such attacks are easily detected, and the injected malicious behaviors often fail to accumulate as persistent skills. In this paper, we show that skill poisoning can arise even from verified successful experiences, without making any individual trajectory malicious. Based on this insight, we propose SkillPoison, a novel framework that progressively poisons skill via successful experiences. SkillPoison first constructs a set of successful experiences that reinforce a target behavior, and then removes the contextual conditions that constrain when the behavior applies. Rather than injecting malicious content, SkillPoison shapes how the skill extractor generalizes, allowing useful behavior to support task success while inducing harmful behavior when they are misapplied. Extensive experiments on three benchmarks show that SkillPoison achieves 95.71% attack success rates, while all injected experiences remain task-correct and pass verification and lexical inspection. Our code, data and implementation details are available for the community at https://github.com/DEEP-JLU/SkillPoison.
llm agentself-improvingbenchmark - arxiv:2610.07643 · cs.AIMonte Carlo Estimation for KV Cache EvictionAhsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer, Wajih Hassan Raza +4
Most KV-cache eviction methods ask, in effect, which memory appeared important while reading the prompt? We instead ask, which memory will matter while answering? Since decoding queries are unavailable at eviction time, prior future-aware methods rely on pseudo-responses or synthetic future-query estimates. We cast fixed-budget future-aware eviction as distributional estimation over plausible model-conditional query trajectories and introduce LORE-KV (Lookahead Output-perturbation with Reliability-weighted Ensembles for Key-Value caches), a training-free method that samples short autoregressive continuations from the frozen target model and uses their response-side query states to estimate prompt-token utility. Tokens are scored by projected leave-one-out attention-output deletion cost and aggregated across sampled futures with optional trajectory weighting. The temporary continuations are discarded before final decoding, requiring no auxiliary model or training. Ablations isolate the mechanism: at B=128, a single response-side continuation recovers about 89% of the gain over the prompt-window control, while additional futures provide smaller improvements. At B=128, LORE-KV raises the LongBench average on Qwen2.5-14B from 45.49 to 48.24 (+2.75) and the 16K RULER average on Mistral-7B from 45.20 to 51.05 (+5.85). Gains diminish at larger cache budgets and coexist with task-level regressions. LORE-KV incurs 1.46-2.77x AnDPro's per-sample wall-clock time as a one-time compression overhead across six dense and hybrid-attention backbones.
memory - arxiv:2610.07628 · cs.LGComplementary Supervised and Self-Supervised Representations for Out-of-Distribution Graph LearningQingying Hao, Zikang Chen, Chuxuan Hu, Jinyuan Jia +3
Out-of-distribution (OOD) generalization remains challenging for graph neural networks (GNNs), as graph distributions can vary substantially across time and domains. Supervised and self-supervised graph representation learning are guided by distinct objectives and offer different perspectives on graph representations. In this work, we study whether self-supervised representations (SSL) can provide complementary signals to improve supervised OOD node classification. We develop two backbone-agnostic frameworks that exploit such information at different stages of learning and prediction. Co-Train jointly learns supervised and SSL representations and adaptively integrates them during training, while Dual-Space Retrieval performs non-parametric prediction in the two representation spaces and combines their predictions through confidence-aware fusion at inference time. The supervised and SSL encoders are separately parameterized and need not share the same GNN architecture. We evaluate multiple GNN backbones and two distinct SSL objectives, DGI and GRACE, on four graph benchmarks spanning temporal and cross-domain distribution shifts. Extensive experiments show that Co-Train consistently outperforms strong supervised OOD baselines, while Dual-Space Retrieval achieves competitive performance as a flexible non-parametric alternative. Results across different backbones and SSL objectives, together with representation analyses and ablations, demonstrate that SSL representations provide complementary information to supervised representations and can improve OOD node classification across diverse settings.
benchmark - arxiv:2610.07626 · cs.CLA Novel Sentence Stress Detection Framework Leveraging Auxiliary Word-Stress Modeling and Loss OptimizationTien-Hong Lo, Fong-Chun Tsai, Ting-An Hung, Yu-Hsuan Hsieh +2
Prosodic stress is a crucial aspect of automatic pronunciation assessment (APA), encompassing both sentence stress detection (SSD) and word stress detection (WSD). SSD highlights semantically salient words that shape discourse meaning, while WSD identifies the primary stressed syllable within each word to ensure lexical clarity. However, most prior work treats SSD and WSD as independent tasks, overlooking their shared reliance on prosodic cues such as pitch, duration, and intensity. To address this gap, we propose an effective SSD approach combining SSD with auxiliary WSD via a novel modeling paradigm. In addition, we introduce a word-span stress regularizer (WSR) that concentrates token-level SSD probabilities within each stressed word span. Experiments on the TinyStress-15K benchmark show that the proposed method outperforms strong baselines, with the complete configuration achieving the best SSD result.
benchmark - arxiv:2610.07625 · cs.LGStateless Language Agents: Scaling Long-Horizon Automated ResearchQizheng Zhang, Changxiu Ji, Isaac Sun, Yuetai Li +14
Automated research systems increasingly run LLM agents over long horizons, but more inference does not by itself produce more progress: agents replay growing histories, duplicate one another's work, or stop experimenting while token consumption continues. Yet most evaluations use short budgets or benchmarks that saturate early, leaving these failure modes untested. We trace these failures to two choices: where research state lives and who decides what to try next. We introduce Stateless Language Agents (SLAs), built on the principle of stateful search with stateless agents: no agent carries its conversation across invocations; instead, the harness owns the research state (candidate solutions and measured outcomes) and reconstructs a fresh and role-specific context for every invocation. What each agent sees becomes an explicit design choice rather than a history that grows with the run. We implement this principle in the SLA framework, where a stateless Advisor reads harness-summarized evidence across search directions and assigns concrete experiments to parallel Workers. We evaluate SLA against three recent frameworks on software engineering, kernel optimization, and algorithm design at budgets of up to one billion tokens. SLA achieves the best final result on every task and reaches the strongest kernel baseline's final performance with over 84% fewer tokens. Ablations from shared checkpoints show that focused contexts and explicit assignments each contribute to SLA's progress, with effects that can compound over full runs, while the Advisor consumes less than 0.6% of tokens. These results argue for SLAs, which keep durable research state out of agent conversations, and show that short evaluation horizons can misjudge research systems and their components.
agentllm agentbenchmark - arxiv:2610.07621 · cs.ROTacZero: Training-Free Peg Insertion Using a General-Purpose Vision-Language Model with Tactile FeedbackKazutoshi Tanaka
Robots that autonomously determine their actions from language instructions and sensory observations could perform new contact-rich manipulation tasks without task-specific training or hand-designed rules. To perform these tasks, robots must infer how objects contact one another and move as a result, then select actions. For contact inference and action selection, prior approaches involve designing estimation models and tactile feedback control laws, or learning models for object-motion estimation, action-outcome prediction, and action selection from tactile data. Instead, we propose TacZero, which uses a pretrained general-purpose vision-language model (VLM) to interpret visual and tactile observations and select robot actions without additional tactile or manipulation training or task-specific rules for contact interpretation or action selection. TacZero provides the VLM with camera images, robot state, and three-axis tactile responses represented as numerical values or vectors overlaid on the images. From these observations and interaction history, the VLM generates commands specifying target end-effector positions and gripper opening or closing, which a low-level controller executes. In real-world cylindrical-peg insertion experiments, TacZero succeeded in 15 of 20 trials with numerical tactile input, compared with 10 of 20 without tactile input. This study provides a concrete starting point for further research on contact-rich manipulation using general-purpose VLMs and highlights challenges in pursuing this direction.
manipulationtactilegripper - arxiv:2610.07616 · cs.RONine Trials to Recover: A Reproducible Benchmark for Repertoire-Free Soft-Robot Damage AdaptationSiyuan Zhang
We present a repertoire-free benchmark for soft-robot damage recovery under nine online trials. The protocol pairs damage masks within each morphology, retains a measured nominal fallback, and separates method development from evaluation on new bodies. A Gaussian-process expected-improvement (GP-EI) reference controller adapts actuator phases using three initialization probes and six feedback-selected rollouts. Across two disjoint 75-body cohorts, it outperforms random search, Sobol, CEM, and CMA-ES under equal budgets. GP-EI improves the worst-mask gain on 69/75 confirmation bodies and exceeds these four baselines by 0.235-0.310 mean worst-mask reward. A TuRBO-style local GP is the closest comparator; the paired confidence interval includes zero. Post-confirmation fixed-controller replay finds 5.06 voxel widths of mean recovery together with a 0.0031 increase in worst-mask p99 geometric edge strain; a strict no-added-demand deployment gate retains 48.7% of mean gain. In a frozen development stress test that physically removes 10% of occupied voxels, GP-EI improves 71/75 bodies and exceeds official BoTorch TuRBO by 0.356 mean worst-mask gain. Together, the replayable controllers, body-level inference, and frozen-cohort evaluation provide a reference for measuring the added value of learned damage priors and future adaptation methods.
benchmark - arxiv:2610.07615 · cs.LGAFA-BANDIT: Provably Near-Optimal Online Multi-Feature Classification Under Budget ConstraintsAbdAlRahman Odeh, Teng-Hui Huang, Hesham El Gamal
Active Feature Acquisition (AFA) is a classification problem in which an agent decides which costly features to acquire before predicting each sample's label. Unlike batch AFA, which trains a fixed policy and classifier offline on fully observed data, online AFA updates its predictor from revealed labels as samples arrive. Existing online methods either use deep reinforcement learning (RL) without performance guarantees or maximize cost-adjusted reward rather than enforce a global budget. We formulate online AFA as a combinatorial Bandits with Knapsacks (BwK) problem that couples acquisition and prediction. Unlike prior bandit-based AFA and classical BwK, our setting has combinatorial complexity, evolving rewards, a global budget, and structured side information. We obtain an improved regret upper bound over standard BwK bounds in this framework, leveraging a cardinality-aware confidence bound and the subset update structure. To avoid an exponentially large action space, we propose \emph{LP-Chain}, a variant that searches a cost-aware chain of feature subsets with a size that grows linearly with the number of features. While the regret upper bound is specific to the combinatorial framework, \emph{LP-Chain} empirically achieves comparable predictive performance. On synthetic data, \emph{LP-Chain} outperforms HEDGE-based BwK and deep RL-based online AFA baselines and scales favorably to more features.
agent - arxiv:2610.07614 · cs.AIBioStudyBench: Evaluating Agents on Post-Cutoff Biomedical StudiesDavid Li, Shaamil Karim, Christian Gensbigler
We evaluate whether AI agents can match the reported findings of published biomedical studies using public data. Existing evaluations do not consistently separate analysis from prior knowledge or retrieval of the published answer. We introduce BioStudyBench, a benchmark of 25 long-horizon analysis tasks drawn from studies first published between July and September 2026, after the developer-reported knowledge cutoffs of the models we evaluate, semi-automatically filtered down from 404,019 PubMed records. In each task, the agent receives a neutral research question but no data files, so it must find and download the relevant public data, search the literature through tools that return only records dated before its cutoff, and report findings through data analysis. To measure gains over prior knowledge, we run every task both with and without access to data and tools. Across eight models, access to data and tools raises the pass rate by 47 percentage points on average over the no-data baseline. Open-weight models across sizes trail closed-weight models, with the best open-weight model passing 81.3% of tasks against 94.7% for the best closed-weight model.
agentai agentbenchmark - arxiv:2610.07613 · cs.ROLearning Grasp Targeting from Point Clouds for Log Pile Clearing on a Hydraulic CraneGeorge Sideris, Lucas Bessai, Heshan Fernando, Elie Ayoub +2
In mill yards, log loaders clear dense piles by a sequence of bundle grasps: hundreds of logs rest in contact, and each removal changes the pile available to the next grasp. A learned policy chooses where to place and orient the grapple from unsegmented point clouds and runs on a trailer-mounted hydraulic forestry crane. The policy classifies at which observed point to grasp and predicts depth and grapple orientation there. The same network outputs support behavior cloning (BC), reinforcement learning (RL), and deployment. BC learns from successful top-of-pile demonstrations; RL explores for improvements by fine-tuning the cloned policy (BC$\to$RL) or by training from scratch. In simulation, BC clears 98 of 100 piles of 200 logs, while BC$\to$RL improves load stability. Twelve field trials compare a geometric heuristic, RL from scratch, BC, and BC$\to$RL through complete grasp-transport-deposit cycles. BC and BC$\to$RL deposit 93.8% and 88.9% of pooled inventory, against 80.4% for the heuristic. BC$\to$RL deposits logs on 83.6% of its cycles, against 79.6% for the heuristic and 65.7% for BC, while its simulated stability gain does not carry over to the crane testbed. Trained entirely in simulation and run unchanged on the crane, the learned policies clear more than the hand-filtered heuristic while observing unfiltered clouds that still contain the storage rack's rails and poles.
grasp - arxiv:2610.07601 · cs.AIBeyond Scalar IoU: Structured Verification from Rollout Groups for Video Temporal GroundingYoungjae Cho, Won Young Jhoo, Jongsuk Kim
Reinforcement learning with verifiable rewards (RLVR) provides a natural framework for adapting pretrained models to video temporal grounding, where generated temporal intervals can be scored directly against ground truth intervals. Yet existing overlap verifiers typically score each rollout independently, leaving the joint structure of the rollout group unused. We introduce SUTURE, which conditions verification on the rollout group and exploits its structure at two complementary scales: disagreement across rollouts controls how strongly the target is reweighted, while coverage at each position determines where reward mass is redistributed. We show that the resulting verifier admits an exact decomposition into the standard IoU term and a covariance correction determined by the rollout group. A local gradient diagnostic finds a preference for responses covering relatively less supported target regions in the analyzed groups. Across five temporal grounding benchmarks, SUTURE improves grounding performance at every reported IoU threshold. Its trained policy also shows less video-start anchoring in reasoning traces: for later events, the first temporal mention more often overlaps the annotated target. Together, these results show that the joint structure of a rollout group can support a more informative temporal verifier.
benchmark - arxiv:2610.07599 · cs.ROModeling Latent Disturbances for Robust Decision-Making in World ModelsJunwon Seo, Andrea Bajcsy
In this paper, we study robust decision-making in the latent space of world models (WMs). Robust optimization is a mathematical framework where, given explicitly specified dynamics and physically meaningful disturbances, a robot can select actions that remain effective even under worst-case disturbances. However, applying this principle to the learned latent space of WMs introduces a fundamental challenge: because WMs have fully learned state spaces and dynamics inferred from high-dimensional observations, it is unclear how to define latent-space disturbances that faithfully represent uncertainty in the underlying system. Our key idea is to model a latent-space disturbance as a perturbation to the learned latent dynamics that induces pessimistic but plausible transitions. Specifically, we construct a set of plausible latent dynamics by combining a dynamics-aware similarity metric that captures plausible transitions with out-of-distribution detection that excludes implausible latent states. We calibrate this uncertainty set over latent dynamics using conformal prediction, ensuring that WM imaginations induced by the latent disturbance remain plausible without becoming overly pessimistic. We then jointly optimize robust robot actions and the worst-case latent disturbances through game-theoretic optimization. We leverage this latent-space robust optimization to robustify policy steering, considering two paradigms: latent safety filtering and sample-and-verify steering of a generative control policy. Our controlled simulation experiments show that our latent disturbance enables robust decision-making directly in WM latent spaces, and hardware experiments with a Franka manipulator show that modeling latent disturbances enables robust policy steering, reducing failures by 70% in safety filtering and 54% in sampling-based policy steering. Project website: https://junwon.me/LatentDisturbance/.
manipulatorfrankaworld modellatent dynamics - arxiv:2610.07594 · cs.ROBiGym 2.0: Benchmarking Learned and Agent-Developed Policies for Humanoid Household ManipulationZexi Zhang, Zecheng Zhu, Zidong Chen, Zulkhuu Tuya +1
Humanoid household manipulation requires the arms to act while the body balances, steps and changes posture. We present BiGym 2.0, an adaptation of BiGym for the Unitree G1 across 20 household tasks using a unified whole-body controller for demonstration and evaluation. The suite provides 60 native human virtual-reality demonstrations per task with synchronised multi-camera views and full-body execution records. We benchmark vision-language-action fine-tuning, imitation learning, demo-driven reinforcement learning, and cold-start coding agents given the interaction budget of online reinforcement learning. With the same onboard views, proprioception and whole-body controller for every method, vision-language-action fine-tuning has the highest nine-task mean, and agent-developed programs outperform every demo-driven reinforcement learning baseline on this mean and lead on bimanual reaching. Cross-workspace stacking remains open, $π_{0.5}$ stays low on pick-box, and multi-object transport is hard for imitation learning, demo-driven reinforcement learning and coding agents. All environments, human demonstrations, and evaluation traces are open-sourced at https://github.com/swirl-uk/BiGym2.
vision-language-actionmanipulationhumanoidwhole-body controlbenchmark - arxiv:2610.07588 · cs.LGPersonal-Agent Mediated Recommendation with Cross-Platform User HistoryYu Xia, Jiangfan Zhang, Jun Xiao, Julian McAuley +1
Modern recommendation is shifting from platform-centric personalization toward user-governed personalization, where a personal LLM agent can act on the user's behalf across services. We formalize this emerging paradigm as Personal-Agent Mediated Recommendation: a platform recommender ranks a candidate set using platform-local information, and a personal agent uses user-authorized cross-platform history to mediate the resulting ranking and produce the final top-K slate. Such mediation is nontrivial: the platform ranking can encode strong population evidence that the personal agent cannot observe, so effective mediation must therefore balance beneficial rescues against harmful overrides. To study this trade-off, we introduce MediateRec, a benchmark that includes scalable proxy cross-platform environments and a real cross-platform test under a controlled platform-agent information boundary. To train the agent to use cross-platform history effectively, we further propose Personal Attribution Mediation Optimization (PAMO), which counterfactually masks that history to estimate personal mediation support and reallocates rank-aware advantage mass under a platform-relative value floor. We theoretically prove that PAMO preserves cutoff-level advantage mass and is locally optimal among first-order reallocations that preserve this mass without lowering average platform-relative value. Experiments on MediateRec show that personal-agent mediation enables meaningful platform corrections, yet even strong proprietary LLMs introduce non-negligible harmful overrides. PAMO consistently improves over matched outcome-only RL across seen and unseen target platforms and on the real cross-platform test, while achieving a better rescue-harm balance.
agentllm agentbenchmark - arxiv:2610.07587 · cs.CLLarge Language Model Orchestration under Heterogeneous Preferences via Explicit Persona InferenceShuqing Shi, Ziyan Wang, Milind Tambe, Yali Du
LLM orchestration investigates how an orchestrator coordinates a group of autonomous agents to achieve common goals or maximize collective welfare. The agents are typically heterogeneous, each holding a private preference that it pursues but does not reveal. Inferring such hidden preferences from behavior has been a subject of long-standing research in game theory and multi-agent systems. The core challenge lies in maintaining a belief over every agent's preference and updating it from the agents' observed actions. Existing LLM orchestrators carry that belief as prompt text with no explicit update rule. This lets early errors persist and propagate rather than be corrected. We therefore propose \textbf{HARP} (Heterogeneous-preference Agent oRchestration via Preference inference), a novel framework that moves the belief out of the prompt. Specifically, HARP maintains one numeric posterior per agent over a finite set of candidate preferences and updates it in closed form by Bayes' rule. The language model supplies only actions and per-candidate likelihoods, so estimation is decoupled from its reasoning. We prove that HARP attains the same $\tilde O(\sqrt K)$ Bayesian regret as explicit joint inference when the factorization is exact. Furthermore, HARP\textsuperscript{+} augments planning with a bonus for actions that distinguish the candidates, so inference continues even when the optimal action is uninformative. Empirical results on three substrates, ranging from payoffs the preferences fully determine, through payoffs that depend on more than them, to scales where explicit joint inference is infeasible, demonstrate that HARP\textsuperscript{+} is the strongest non-oracle method across the class our theory identifies.
agentautonomous agentmulti-agentagent system - arxiv:2610.07580 · cs.AILOGIC: An LLM Benchmark for Intent-Grounded Change Impact in Aerospace Electrical SystemsMuhammad Faraz Shoaib, Muhammad Qasim, Raisulhaq Mohammed Rizwan, Rahmatullah Safdar +2
Aerospace electrical-design revisions can contain multiple genuine changes, although an engineering request may authorize only a subset. Propagating every detected difference can therefore produce overly broad impact reports. We present LOGIC, a controlled benchmark and evaluation framework in which locally deployable language models ground a request in a deterministic candidate-change inventory before selected changes are propagated through a typed electrical traceability graph. This separation permits candidate-selection errors to be distinguished from downstream propagation errors. LOGIC contains 168 scenarios, including 144 selection and 24 abstention cases. We evaluate three 7--8B models against intent-agnostic, lexical, and structured-evidence methods, with an oracle-root upper bound. On 96 explicitly anchored selection cases, gate-only structured evidence achieves candidate F1 of 1.0000, compared with 0.9677 for token-lexical matching. On 12 relational-paraphrase cases, token-lexical F1 is 0.1772 and gate-only F1 is 0.0000, compared with 0.5000--0.6400 for the large language models. Model grounding degrades as candidate inventories grow from 4 to 64 changes, while affected-element and typed-path accuracy remain comparatively stable when frozen selections are replayed over graphs of approximately 1K to 100K nodes. Strict evidence gating suppresses false positives but can remove correct semantic selections. An exploratory evidence-empty abstention policy raises strict abstention accuracy to 0.6667 for all three models and reduces unsafe-report rates to 0.1667, while decreasing answerable-case coverage by 16.0--27.1 percentage points. Four of six conflicting requests remain unsafe for each model. These findings support combining literal evidence and language-model reasoning with engineering review when intent cannot be established reliably.
benchmarkevaluation framework - arxiv:2610.07578 · cs.AICooperating with Future Collaborators: Multi-Agent RL under Staggered ParticipationJianglin Qiao, Siyi Hu, Thien Hoang Nguyen, Zehong Cao +1
In cooperative Multi-Agent Reinforcement Learning (MARL), agents are often trained under concurrent participation, while in many tasks some agents act earlier and leave task-relevant information that becomes useful to agents participating later. We study this setting as staggered participation (SP), which introduces a cross-time, cross-agent learning dependency because an early action may affect the return through the information it provides and the later policy that uses it. Learning under SP therefore requires both identifying what information is useful for future decisions and learning how later agents should use it. We propose Staggered Participation Learning (SPL), a training-time augmentation that addresses these two parts with prospective acquisition supervision for earlier agents and outcome-supervised receiver learning for later agents. We evaluate SPL across multiple policy-based MARL backbones, environments, and staggered-participation patterns. Across 60 MPE/RWARE backbone setting comparisons, SPL achieves higher observed mean task completion in every case, with an average difference of 14.1%. The gains also extend to eight-agent teams and a physics-based UAV-UGV environment in Isaac Lab, providing evidence across algorithmic, temporal, and embodied settings.
embodiedmulti-agent - arxiv:2610.07570 · cs.AIUnanimously Wrong: Certified Abstention from How Medical LLM Consensus FormsXiaoyang Wang, Tianrui Wang, Christopher C. Yang
In clinical practice, agreement among independent experts is treated as evidence of reliability, and multi-round consensus has become a core mechanism of agentic medical question-answering systems. When such a system must decide whether to trust its own answer, the prevailing signal is again agreement, now among the sampled answers. But agreement is a fragile proxy for correctness. A system can be unanimously wrong, returning the same incorrect answer on every sample, and on these questions agreement-based signals carry no information. The cause is that these signals read only the final state of the consensus and discard how it was reached. Agreement that was reached by resolving disagreement with evidence looks identical, at the end, to agreement that was present from the first sample because every sample shares one misconception. ProbeGuard is a certified abstention framework that bases the abstention decision on how the consensus formed. Process features trace agreement trajectories, minority persistence, and retrieval saturation. For unanimous votes, rationale semantic entropy checks whether the reasons behind the vote cohere, and an active probe retrieves counter-evidence and measures whether the consensus survives. A stratified Learn-then-Test calibration then converts these scores into a distribution-free bound on selective risk. We evaluate ProbeGuard on three medical QA benchmarks and a hard-frontier reference, with a published multi-round agentic RAG substrate, against six abstention baselines. On MedQA, 13.4% of unanimous votes are wrong, and no agreement-based signal can flag them. Process signals raise the discrimination of correct from incorrect consensus from chance to 0.696 AUROC. The certified rule answers six in ten unanimous-layer questions at an observed selective risk of 9.0%, and nine in ten once in-domain calibration data accumulate.
ragagenticbenchmark - arxiv:2610.07569 · cs.ROOpenSplatGraph: From Dense Semantic Maps to Structured Scene Graphs for Open-Vocabulary Robot PerceptionBinh Long Nguyen, Kien Nguyen, Clinton Fookes, Peyman Moghadam
Dense 3D mapping with semantic understanding is essential for robotic perception in complex environments. Recent 3D Gaussian Splatting-based mapping approaches enable high-fidelity geometry and efficient open-vocabulary perception, but typically represent semantics as unstructured feature fields that limit object-centric reasoning. In contrast, 3D scene graphs explicitly model objects and their relationships for structured reasoning, but are commonly constructed from sparse geometric representations that do not fully exploit dense semantic maps. In this work, we present OpenSplatGraph, a unified framework that constructs persistent 3D scene graphs directly from an online Gaussian-based open-vocabulary semantic map. The proposed framework augments the dense semantic map with a reliability-aware semantic field that maintains lightweight observation statistics for confidence-aware, query-conditioned object extraction. Extracted object instances are associated with persistent graph nodes, allowing object attributes and relationships to be incrementally updated across observations and queries. By tightly coupling dense semantic mapping with persistent object-centric representations, our framework supports both language-guided object grounding and structured relational reasoning while preserving the geometric fidelity of Gaussian-based mapping. Comprehensive evaluations on standard 3D scene understanding benchmarks and real-world robotic experiments demonstrate that OpenSplatGraph achieves competitive performance for online open-vocabulary perception and downstream robotic tasks. Project page: https://csiro-robotics.github.io/OpenSplatGraph.
scene graphbenchmark - arxiv:2610.07566 · cs.CVAIMS: Anchor-Integrated Multi-View Synthesis for Scalable Novel View RenderingJooHyun Park, HanYoung Jang, HyeongYeop Kang
Feed-forward novel view synthesis methods achieve strong generalization from posed multi-view inputs, but scaling them to large input view sets remains challenging. Transformer-based approaches that jointly process all input-view tokens incur rapidly increasing computation and memory as the number of views grows, while simple view subsampling discards potentially useful observations. We introduce Anchor-Integrated Multi-View Synthesis (AIMS), a scalable framework that decouples the number of available observations from the number of views processed by the global synthesis model. AIMS selects a fixed set of spatially distributed anchor views using farthest point sampling, groups nearby observations around each anchor, and uses a lightweight learnable integrator to fuse their information into enriched anchor representations. This allows additional observations to contribute to synthesis while keeping the downstream global view budget fixed. Evaluations on RealEstate10K and ScanNet demonstrate a favorable quality--efficiency trade-off against transformer-based and Gaussian-based baselines. AIMS achieves 29.41 dB and 17.73 dB PSNR on the two datasets, respectively, with rendering averaging 7.24 ms per view.
memory - arxiv:2610.07563 · cs.CLHouseholdBench: Evaluating Large Language Models as Predictors of Household Economic BehaviorJin Huang, Diego Ferreras Garrucho, Yutong Xie, Walter M. Yuan +3
Large language models (LLMs) have the potential to meet a key goal in economics: a quantitative model of household decision making, across a variety of settings. Yet existing evaluations cover few surveys and outcomes, and do not study how households adjust to changing economic conditions. We introduce a new evaluation, HouseholdBench, which unites 6 U.S. household surveys and 32 prediction tasks spanning numeric, categorical and probabilistic outcomes, related to consumption, income, labor, expectations, and housing. Using past behavior, demographics and macroeconomic conditions, the tasks test whether LLMs predict behavior, including how households adjust to changes in various policies. We evaluate 13 proprietary and open-weight LLMs against a no-change baseline and a gradient-boosted tree model. Most LLMs outperform the no-change baseline, including for policy response tasks -- with the best model lowering error for numeric outcomes by 12.2%. Across most tasks, gradient-boosted trees rank first; leading proprietary LLMs approach their performance, but open-weight models lag. LLMs exhibit systematic over- and underprediction across different tasks. We identify methods that enable a 4 billion parameter open-weight model to match proprietary models' performance: fine-tuning and aggregating 16 predictions per observation. Improvements generalize to policy-response tasks, which are excluded from fine-tuning. We release our datasets, code, and leaderboard on our website: https://jn-huang.github.io/householdbench
leaderboard - arxiv:2610.07559 · cs.LGTAFFY: A Task-Adaptive Tabular Foundation Model with In-Context DiversityZijian Li, Xiangchen Song, Gongxu Luo, Jie Qiao +6
Recent progress in tabular foundation models suggests that training on synthetic tasks can substantially improve in-context learning capabilities, with overall performance largely depending on how well models can infer task-specific predictive relationships from the available context during inference. In this paper, we introduce TAFFY, a tabular foundation model with an In-Context Diversity Prior and a Task-Conditioned Looped Transformer that strengthen this ability. Specifically, to construct each synthetic pretraining context, the In-Context Diversity Prior samples from multiple related environments derived via controlled interventions and distribution shifts on a shared causal process. This in-context diversity encourages the model to learn a more comprehensive and task-specific representation. Moreover, the Task-Conditioned Looped Transformer iteratively and selectively applies a shared group of Transformer blocks to refine contextual representations, with a task-conditioned gate modulating the final hidden-state update. This enables task-adaptive iterative refinement. Together, these components encourage the model to identify predictive relationships from contextual contrasts during pretraining and dynamically modulate context integration for each task. Across six classification and five regression benchmark datasets, TAFFY attains the lowest average rank.
iterative refinementbenchmark - arxiv:2610.07558 · cs.ROSeeing the Invisible: Physics-Guided Visual Prompting for Temperature- and Radiation-Aware VLA NavigationHojoon Son, Fan Zhang
Vision-Language-Action (VLA) models have become a major paradigm for Vision-and-Language Navigation (VLN). However, in safety-critical facilities, invisible risks such as radiation or temperature spikes cannot be detected by an RGB camera, and handling each risk is expensive, requiring a new encoder, new data, and model retraining. We propose Physics-Guided Visual Prompting (PG-VP), a plug-and-play multimodal perception module that instead reuses what a frozen VLA model already does well: avoiding visible obstacles. Given a proximal radiation or thermal source, PG-VP performs a physics-guided risk assessment to determine the avoidance direction and overlays a corresponding virtual obstacle that moves across consecutive frames (Dynamic Visual Prompting). The navigation policy then naturally detours around this invisible hazard. The identical virtual obstacle is used regardless of hazard type, so the visual prompting pattern remains fixed as sensors are added. When no hazard is detected, nothing is rendered, and the policy behaves exactly as it would without PG-VP. We evaluate PG-VP on OmniNav using the val-unseen splits of R2R-CE and RxR-CE, where it guides the policy toward intended low-risk actions in 84.9% and 83.2% of cases, at a cost of 6.8 and 7.9 percentage points in navigation success rate. We further test it with distinct scenarios on a real robot in the presence of actual thermal and radiation sources, all without any retraining. The real test shows that PG-VP effectively avoids these invisible hazards, improving worst-10% average trajectory safety by 63.45% and 32.59% against thermal and radiation sources, respectively.
vision-language-actionvlavla model - arxiv:2610.07557 · cs.AICheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?Hang He, Li Wang, Hao Chen, Yuchen Shao +8
Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and refine the checker through repeated compilation and analysis feedback. Existing coding-agent benchmarks focus on tasks such as patch generation or vulnerability detection and rarely assess whether an agent can develop a working checker in a repository from start to finish. We introduce CheckerBench, an executable benchmark of 300 tasks derived from 297 CVEs across 167 repositories, 85 CWEs, and five language ecosystems. Each task includes vulnerable and fixed revisions, a pinned analysis environment, and a checker scaffold. We further introduce CheckerLab, a common evaluation framework that independently rebuilds submitted checkers and measures vulnerable-fixed diagnostic contrast, patch localization, false positives, and tool use. Across 21 model-harness configurations and three independent repeats per configuration, mean Pass@1 is 32.30%, while the best reaches 45.33%. These results show that reliable, reusable checker development remains challenging for current coding agents.
agentagent benchmarktool usebenchmarkevaluation framework - arxiv:2610.07556 · cs.AIDecoupled Multi-Agent OrchestrationXinle Wu, Yao Lu
Learned orchestration can automatically construct effective language-model multi-agent systems, but existing approaches couple planning to fixed worker pools and train decomposition and collaboration from the same terminal outcome, limiting transfer and obscuring credit assignment. We introduce DeOrch, which separates worker-agnostic planning from concrete worker selection. Its two-stage planner first decomposes the task without worker information, then chooses collaboration operations using compact, worker-identity-free matchability feedback from the pool, enabling conditional credit assignment to decomposition and collaboration decisions. A lightweight matcher estimates worker suitability from behavior on a fixed probe set and adapts online with a contextual bandit, allowing new workers to be incorporated without retraining the planner or matcher. Across diverse in- and out-of-distribution tasks, DeOrch outperforms prior automatic MAS orchestration methods with fewer worker calls than competing learned orchestrators, remains effective when transferred to an entirely unseen worker pool without retraining, and shows consistent gains from both components.
multi-agentagent system - arxiv:2610.07550 · cs.LGFoundation Model-Aided Multi-Agent Reinforcement Learning for Wireless Random Access Network OptimizationMyeung Suk Oh, Zhiyao Zhang, Alvaro Velasquez, Nathaniel D. Bastian +1
Random access (RA) is one of the most foundational medium access control (MAC) layer scheduling schemes for handling unpredictable data traffic from multiple terminals. While multi-agent reinforcement learning (MARL) has been explored to optimize RA-based wireless networks, its reliance on experience-driven, distributed policy learning incurs significant training overhead for each optimization task, limiting its feasibility in real-world applications. In this work, we propose to leverage a foundation model (FM) to improve MARL efficiency across diverse RA network optimization tasks. Specifically, we design an FM-aided actor-critic algorithm within a consensus-based decentralized MARL architecture and provide its convergence analysis under local reward exchanges and nonlinear value function approximations to show that our algorithm achieves the same convergence order as the conventional MARL with critic model exchanges and linear approximations. Our numerical results show that our FM-based approach significantly enhances MARL speed for RA network optimization.
multi-agent - arxiv:2610.07540 · cs.ROPreserving Unstable Modes Through Inverse Dynamics in JEPA World ModelsLeonardo F. Toso, Yann LeCun, James Anderson, Oumayma Bounou
Robotic systems often exhibit unstable modes, along which small perturbations and disturbances can cause unbounded growth unless corrected through feedback. Controlling such systems from high-dimensional visual observations requires representations that preserve these modes. Joint-embedding predictive architectures (JEPAs) provide a natural framework for learning such representations and their dynamics from visual data. However, we demonstrate that next step prediction combined with anti-collapse regularization does not guarantee that controllable unstable modes are preserved: the training loss can be minimized while these modes are collapsed, making stabilization from the learned representation impossible. To address this, we augment world-model training with an action reconstruction objective (i.e., an inverse dynamics loss) that encourages control-aware representations, namely, visual representations that preserve crucial features for control. We prove that exact action reconstruction makes the encoder injective on the finite-horizon reachable subspace. Thus, the encoder cannot discard any state direction reachable by an action sequence within $H$ steps. Moreover, we show that, as $H$ grows, the dominant eigenspace of the finite-horizon controllability Gramian converges to the controllable unstable subspace. We establish our theoretical results for linear systems and demonstrate empirically that our findings extend to nonlinear visual control tasks (CartPole, Walker2D, and PointMaze), highlighting the benefits of control-aware representation learning.
world model - arxiv:2610.07535 · cs.AIDisentangling Models from Personas in Heterogeneous LLM SimulationsDani Roytburg, Daphne Ippolito
Multi-agent simulations with large language models (LLMs) often operate networks of agents with a single base model. This overlooks the inter-model effects which may dominate engagement dynamics in real-world deployments. To show this, we simulate a heterogeneous social network powered by several different base models and show that the amount of engagement an agent receives depends more on its base model than on its assigned persona. The attraction or repulsion effects of a base model strengthen dramatically when more models are added in the mix, suggesting that networks dynamics may converge to base model effects at scale. To help explain this effect, we conduct a series of content-mediating analyses, showing the predictability of base models across contexts as well as the relationship between a model's lexical patterns and an engagement-maximizing style. In light of recent developments in mass multi-agent interaction, this work underscores the relevance of heterogeneous compositions in driving the outcomes of those networks
agentmulti-agent - arxiv:2610.07532 · cs.AISafeguarding LLMs via Model-Agnostic Latent Safety Signals from Dark KnowledgeWonjun Lee, Kyungsik Yang, Gaeun Ji, Vaidehi Patil +4
LLMs have advanced rapidly, raising growing concerns about their safety. Recent work has proposed approaches to detect and defend against attacks including defenses at decoding stage that leverage models' hidden states. However, existing decoding-stage defenses suffer from two limitations. First, they introduce a trade-off between safety and over-refusal, where strengthening safety degrades the model's helpfulness on benign queries. Second, many of these methods rely on internal hidden states and are thus restricted to specific architectures, incurring substantial overhead and limited generalization across models. To address these limitations, we introduce LADE (Latent Safety Signals for Defense), which leverages latent safety signals extracted by contrasting harmful and benign queries from dark knowledge (i.e., information carried by the output probability distribution beyond its argmax) in the first-token output probability distribution. Our key insight is that, beyond surface-level refusal tokens, the dark knowledge in the first-token distribution contains latent safety signals, defined as tokens whose probabilities differ sharply between harmful and benign queries. We show that these signals consistently align across LLMs, forming a model-agnostic direction that emerges from safety alignment. LADE consists of three components: (1) Extracting Latent Safety Signals from Dark Knowledge, which selects top-k safety-discriminative tokens from the first-token probability distribution; (2) Tokenizer Mapping, which maps these tokens across different tokenizers to enable model-agnostic application; and (3) kNN-based Discrimination, which classifies queries via a k-Nearest Neighbors search over the mapped tokens. Across diverse LLMs and benchmarks, LADE is robust against a wide range of jailbreak attacks and lowers attack success rates while maintaining a competitive safety-utility trade-off.
benchmark - arxiv:2610.07527 · cs.ROTask-Space Imitation Guidance for Efficient Reinforcement LearningSalar Asayesh, Hossein Darani, Todd Cao, Evgeny Andriash +1
We introduce Task-Space Imitation Guidance for Efficient Reinforcement Learning (TIGER), a reward-construction and pretraining framework for sparse-reward tabletop robotic manipulation. TIGER treats an action-chunked imitation policy not as an executable controller or action prior, but as a local task-space progress estimator: predicted action chunks are converted, using controller-aware action-to-motion mapping, into short-horizon end-effector references, and the RL agent receives dense progress rewards toward these references while the sparse environment reward remains the dominant objective. During pretraining, TIGER uses imitation-guided look-ahead signals to relax conservative value penalties for actions predicted to make task-space progress, reducing off-manifold exploration during early online RL. Across simulation and real-robot experiments, TIGER improves early sample efficiency and reduces measured safety violations while matching or improving final success rates relative to prior RL and IL-RL baselines on the evaluated tasks.
manipulationagent - arxiv:2610.07525 · cs.ROReDex: Repairing Sim-to-Real Dexterous Policies by Finger-Level Compliant InteractionJinzhou Li, Hadi Tabatabaee, Kelin Yu, Yuyin Sun +5
Dexterous manipulation policies trained in simulation often fail to transfer to the real world because of errors in contact timing and force regulation. Yet these policies can retain useful multi-finger coordination for task progression. We propose ReDex, a framework for adapting a simulation-trained base policy to the real world by correcting local contact failures and incorporating tactile feedback. Starting from a proprioception-only base policy, ReDex allows a human operator to physically correct contact failures at selected fingers under compliant control during real-world rollouts, while the frozen base policy continues to control the remaining fingers. These rollouts combine base policy execution, human-corrected finger motion, and fingertip force observations. We reconstruct force-informed targets from these rollouts to train a standalone force-conditioned policy via behavior cloning. This design reduces human correction effort, enables learning of contact regulation from real-world interaction, and introduces force feedback into a proprioception-only policy without tactile simulation or complex full-hand teleoperation. We evaluate ReDex on two challenging, contact-rich dexterous manipulation tasks on real hardware. Compared with sim-to-real transferred base policies, ReDex increases Object Flipping success rate from 14\% to 86\% across two objects and average Screwdriver Rotation progress from 26.0% to 95.3% across three objects.
manipulationdexterousteleoperationtactilesim-to-real - arxiv:2610.07522 · cs.LGActivation Denoising: A Robustness View on Parallel vs Sequential LLM QuantizationYan Scholten, Rachel Lawrence, James Hensman, Stephan Günnemann +2
Post-training quantization is a powerful tool for compressing large language models. The most scalable methods quantize every layer in parallel, but quantization errors then compound through the residual stream, as no layer corrects for the errors of the layers before it. Sequential quantization accounts for this error compounding by re-calibrating each layer on the already-quantized outputs of its predecessors, yielding stronger results but at the cost of a serial schedule that becomes a bottleneck at scale. As a solution, we propose parallel quantization with activation denoising, which recovers much of the sequential benefit while keeping quantization fully parallel. Rather than re-calibrating layer-by-layer, we take a robustness perspective and model the upstream error as noise, regularizing to be robust to it through a preprocessing step followed by metric-weighted rounding. Applied at every layer, this regularization forms a depth-compounding smoothness penalty that dampens how strongly quantization errors amplify through the model. Unlike orthogonal rotations commonly used in quantization, which must preserve the model's function, we multiply the weights by a more general linear transformation. We find that the two are complementary and their effects compound. Empirically, our robustness regularization recovers a significant part of sequential quantization's benefit in a single parallel pass, at a fraction of its time. Overall, by treating compounding quantization errors as a robustness problem, we offer a principled foundation for more efficient and accurate LLM quantization at scale.
post-training - arxiv:2610.07511 · cs.ROMobileVISTA: Generative Data Augmentation for Pose Generalization in Mobile ManipulationSuzannah Wistreich, Stephen Tian, Isabella Huang, Vitor Campagnolo Guizilini +3
Mobile manipulators such as humanoid robots are increasingly deployed in dynamic, unstructured environments to perform dexterous manipulation tasks. However, end-to-end manipulation policies trained to imitate demonstration data collected from a single robot pose are brittle: even centimeter-scale deviations in robot pose at deployment can drive ego-centric observations and end-effector trajectories out of the training distribution, leading to sharp drops in performance. We introduce MobileVISTA, a data generation framework that transforms demonstrations captured at canonical poses into diverse, pose-perturbed training data by jointly (1) augmenting egocentric visual observations and (2) retargeting actions to compensate for base pose changes. Unlike prior methods, which assume a camera rigidly mounted off the actuated chain or non-trivial articulated robot geometry largely out of frame, MobileVISTA targets compatibility with egocentric platforms (e.g., humanoids) where the camera is both influenced by and must observe the robot's kinematic chain as it moves. We study MobileVISTA in simulated tasks spanning humanoid and bimanual embodiments, and on a real Galaxea R1 Pro. We find policies trained on MobileVISTA-augmented data demonstrate improved robustness to previously out-of-distribution poses encountered at test time, without additional demonstration collection or a trained generative model. Additionally, we find MobileVISTA's benefit is largest on tested humanoids, where the camera rides the actuated chain and the robot fills much of the frame. Additional videos and appendix can be found on our website: https://mobilevista.github.io
manipulationdexteroushumanoidmanipulator - arxiv:2610.07509 · cs.AIOn Open-Ended Information Seeking for Information Elicitation AgentsVictor De Lima, Grace Hui Yang
Information elicitation is an open-ended information-seeking problem in which an interaction can unfold in many potentially valuable directions, requiring an elicitor to continually determine which information to pursue as new information emerges. In agentic elicitation, these decisions may be delegated to a foundation model, yet how model choice shapes the resulting information-seeking behavior remains understudied. We study how judgments about information value vary across LLMs and how these differences shape sequential information seeking. We first examine these judgments across 11 LLMs spanning multiple model families and parameter scales, using a shared set of information and elicitation objectives. We then develop a controlled elicitation simulation in which different models encounter the same information space and use the same selection rule, isolating these judgments from question generation and respondent behavior. Using this setting, we characterize the breadth-depth behavior that emerges from model-specific information-seeking preferences over the course of elicitation. We further examine how interaction history changes the evaluation and subsequent selection of prospective information. We test the robustness and boundaries of these findings through sensitivity analyses and ablations over the opportunities available to the elicitor, the response labels used to operationalize information-seeking preferences, the presence of interaction history, and whether redundancy is explicitly relevant to the assessment. The project code, data, and trajectory files are available at https://github.com/infosenselab/open-elicitation.
agentic - arxiv:2610.07506 · cs.AIJarvis: A Proactive Speech Agent for Multi-Party ConversationsSeunghyun Oh, Hirotaka Hiraki, Shuyue Stella Li, Yulia Tsvetkov +1
Speech agents are reactive and dyadic: they speak when spoken to, and to one person at a time. We ask what it takes for a speech agent to instead take part in a conversation among several people and speak up only when it can help. We introduce Jarvis, a real-time proactive speech agent that audibly participates in multi-party human conversations. Grounded in a document shared beforehand, Jarvis follows the discussion and intervenes when the group misses or misstates a fact and does not correct itself within a few turns. We make three contributions: a problem setting based on epistemic breakdowns that makes proactive intervention measurable, realized as CHI-180-proactive, a synthetic multi-party dataset seeded with known gaps, errors, and self-corrections; a proactive backbone that harnesses a small, open-weight model with deterministic checks and grounds every claim in a source sentence; and interaction techniques for taking the floor in live speech and showing the cited evidence on screen. On CHI-180-proactive, Jarvis is correct on most events it addresses and stays silent 97% of the time when the group resolves an issue itself. A live study with 23 participants confirms these trends with real-time interventions.
agentself-correction - arxiv:2610.07505 · cs.AIMARS: Multi-resolution Adaptive Routing for Sequential RecommendationMing Yin, Sixun Dong, Yudong Liu, Wen-Yun Yang +2
Long-history recommenders often compress each user's history into a compact, candidate-independent memory that is cached and reused to score large candidate pools. We show that real user histories exhibit multi-scale semantic structure, with short-lived intent, medium-term interests, and long-term preferences coexisting in one sequence, and that monolithic cached memories preserve these scales unevenly: linear probes recover recent and mid-range content far worse than long-range content. We call this failure mode \textit{temporal aliasing}. We propose \textbf{MARS}, a multi-resolution user memory that writes the full history into recurrent state tracks anchored to different half-lives, and a sparse routing reader that materializes compact seed memories by selecting the relevant temporal resolutions for each seed, preserving fixed-size candidate scoring. MARS outperforms strong baselines on three public datasets, with gains that grow with history length. Component-matched ablations with paired tests show that temporal diversity and selective routing each contribute beyond what hard-window memories or added capacity provide. The advantage of MARS over its interface-matched baseline also widens after within-user behavioral shifts, at about $1.02\times$ that baseline's warm-cache serving latency for $1{,}000$ candidates per user.
memory - arxiv:2610.07502 · cs.CLClosing Ambient Clinical Documentation Gaps with Automated Provider QueriesJoseph Paul Cohen, Raj Shah, Han-Chin Shing, Fang Wang +3
Provider queries are clarifying requests sent by clinical documentation specialists to physicians to close gaps in the clinical note and ensure accurate billing. Prior work automates note drafting, ICD-10 coding, and order extraction assuming a complete transcript, leaving these gaps unaddressed. We study whether an LLM can automate the query loop, termed DAU (Draft, Ask, Update), across those three tasks. An audit of 3,000 real visits identifies the sources of missing documentation, from which we build five transcript-degradation benchmarks on public data. Analyzing 21k clarification turns on real conversations, we find useful-question predictors are task-specific: oracle confidence dominates, but note completeness needs only simple recall questions while ICD-10 coding needs harder, multi-option ones. About 9% of turns hurt performance, driven by redundant questions and non-answers that still trigger a rewrite. Deployment depends on learning "when not" as much as "what to" ask.
benchmark - arxiv:2610.07491 · cs.LGWho Bears the Burden? Learning Responsibility for Shared Constraints in Multi-Agent Reinforcement LearningXiaoyang Cao, Jingqi Li, Zhe Fu, Alexandre M. Bayen
When multiple agents share a cost budget, a common Lagrange multiplier can enforce the aggregate constraint but does not determine how its penalty should be allocated across agents. Uniform penalties ignore heterogeneity in the rewards agents sacrifice, while agent-specific multipliers may still rely on the same aggregate cost signal. We introduce Lagrangian Responsibility Allocation (LiRA), which learns each agent's share of a common multiplier by optimizing social welfare over a finite training horizon. The multiplier enforces the aggregate budget, while responsibility shares redistribute its influence without modifying the original rewards or constraints. For convex games under standard regularity conditions, varying these shares induces a smooth family of normalized generalized Nash equilibria in which active constraints remain at their budgets while welfare varies. To optimize responsibility before convergence, we derive a welfare gradient that accounts for both learning updates and the induced change in data distribution. Across CityLearn, MABIM, Harvest, and MetaDrive, spanning 3 to 400 agents, LiRA improves average social welfare by up to 29% over uniform and agent-specific multiplier baselines. Grid and driving costs remain within budget, inventory violations decrease, and Harvest makes more effective use of available budget.
multi-agent - arxiv:2610.07485 · cs.LGRobust Importance Sampling for Rare Events via Constrained Gaussian MixturesPaweł Lorek, Rafał Nowak, Rafał Topolnicki, Tomasz Trzciński +1
We study estimating rare-event probabilities $I = \mathbb{P}(g(\mathbf{X}) > γ)$ with $\mathbf{X} \sim \mathcal{N}(\boldsymbolμ, \boldsymbolΣ)$ and general $g : \mathbb{R}^d \to \mathbb{R}$. We address this problem through importance sampling, and propose a framework that substantially improves efficiency and robustness over baselines such as crude Monte Carlo, adaptive cross-entropy, variational-inference-based methods (including reverse- and forward-KL approaches), as well as Safe-ICE, Subset Simulation, and Sequential Monte Carlo, drawing on ideas from both rare-event estimation and cross-entropy optimization. The key contribution has two parts: first, we separate the problem into coverage, to overcome the cold-start barrier, and fitting, to refine proposals once a meaningful signal is available; second, we constrain the final GMM proposal so that it has finite importance-sampling variance (since coverage alone is not sufficient -- without safeguards, importance sampling may still suffer from infinite variance). Together, these ingredients yield expressive proposals; finite variance does not by itself guarantee practical stability at a fixed sampling budget. Extensive experiments demonstrate substantial variance reduction, strong robustness across diverse benchmarks, and favorable cost--efficiency trade-offs, with the proposed approach often outperforming these baselines, particularly in high-dimensional and multimodal settings where competing methods frequently become unstable or fail. Our code is available at https://github.com/lorek/robust-cfi-is.
benchmark - arxiv:2610.07475 · cs.LGAdapting to Changes in Agent Behavior via Finite-Depth Policy SensitivityLan Shi, Daigo Shishika, Xuan Wang
Adapting a reinforcement learning policy to changes in another agent's behavior typically requires a large amount of new interaction data. Policy sensitivity provides a first-order prediction of how a locally optimal policy changes with a behavioral parameter, but its computation requires second-order derivatives whose effects propagate across future interactions. We develop a finite-depth framework to estimate this sensitivity by approximating the policy Hessian and mixed derivative using information from a reference environment. The method features an adjustable propagation depth which determines where derivative propagation along the trajectory is truncated. We characterize the derivative contributions omitted by finite-depth propagation and derive truncation-error bounds for the approximated derivatives and resulting policy sensitivity. The bounds are nonincreasing with propagation depth and vanish at full-horizon propagation. Using a belief-driven pursuit-evasion game as a validation scenario, the proposed method generally achieves lower derivative-estimation errors as the propagation depth increases and outperforms the baseline methods in both estimation accuracy and policy adaptation. The sensitivity-based initialization improves zero-shot return over direct transfer, and also shows advantages for the subsequent fine-tuning in the target environment.
agent - arxiv:2610.07473 · cs.AIPsyCIDRA: A Dual-Agent Framework for Psychiatric Interviewing and Diagnostic ReasoningMilad Mohammadi, Fatemeh Akrami Shamsabadi, Zahra Mohseni, Amirhossein Safdarian +3
Large language models show promise in clinical reasoning, but psychiatric interviewing requires guiding an evolving conversation. Their ability to carry out this interactive assessment remains less studied. We present PsyCIDRA, a dual-agent framework linking free-form psychiatric interviewing with diagnostic reasoning for expert review. Its interviewer agent uses tools to maintain working notes, load expert-written skills, and retrieve ICD-11 references to guide inquiry. Its diagnostic reasoning agent then receives the completed interview transcript and reports hypotheses alongside supporting, conflicting, and missing evidence, withholding a final hypothesis when none is sufficiently supported. Using patient profiles generated with PsyCPG, we first evaluate PsyCIDRA in simulation. Across four models on 53 evaluation cases, it achieves higher diagnostic agreement than direct prompting. On 81 held-out simulated cases, rank-1 accuracy is 60.5% versus 51.9%. In a blinded study of 101 human participants in separate arms, PsyCIDRA agrees with psychologists on whether to propose a diagnostic hypothesis in 79.6% of cases, compared with 65.4% for direct prompting. Together, these findings support the potential of LLM agents to assist psychiatric assessment through free-form dialogue. By examining diagnostic reasoning, interview quality, and safety together, this study contributes to understanding the capabilities and limitations of psychiatric interview agents.
agentllm agentagent framework - arxiv:2610.07470 · cs.LGStructure, Not Belief: Correlated Thompson Sampling from LLM-Derived Covariance in Combinatorial Semi-BanditsVikram Kakaria, Anish Kataria, Anany Kotawala
Combinatorial Thompson sampling (CTS) draws independent posterior samples for every arm, so its exploration dynamics ignore any relation among arms. We study a minimal change to those dynamics: an LLM is queried once for a partition of the arms, the partition becomes a positive-definite correlation matrix $Σ$ through an RBF kernel on cluster ranks, and the per-round posterior sample is drawn with covariance $Σ$ while the Beta posteriors are updated from real rewards only, so the LLM shapes how the sampler moves, not what it believes. We give a self-contained Bayesian regret bound for the idealized Gaussian sampler whose information gain splits into a $K\log T$ term from the $K$-cluster structure and a ridge term that grows to $d\log T$: the $\sqrt{d/K}$ improvement over independent sampling is a finite-horizon transient, exact only as the within-cluster correlation tends to one. The correlated sampler reduces regret by 19% over CTS on 16 synthetic Bernoulli families at $T=2{,}500$ (6-7% at $T=25{,}000$ with data-adaptive kernels) and by 41% on the Microsoft MIND-small news benchmark ($d=200$ real articles), while pseudo-observation warm starts give nothing. An LLM-free ablation with a simulated oracle of controlled quality shows that on unstructured instances the gain is a property of the kernel shape (a random partition, or a plain tempering of the sampling noise, reproduces it), while belief injection at matched oracle quality never helps.
benchmark - arxiv:2610.07469 · cs.AICOMPASS: Finding Where Reasoning Lives in Language ModelsPratyay Dutta, Kowshik Thopalli, Vivek Narayanaswamy
Explicitly eliciting reasoning substantially improves LLM performance. Existing approaches require a predefined characterization of reasoning, whether through CoT prompt design, contrastive CoT directions, or via SAE derived reasoning features. For mathematical reasoning with verifiable answers, we show that a much simpler signal suffices, which is the correctness of the model's own direct answer attempts. This signal yields a latent direction that elicits reasoning. This direction is decodable within the activations of most attention heads, but only a small subset of them can be effectively intervened. We introduce COMPASS, an inference-time steering method that identifies these heads using a logit-space attribution score and steers their activations along the correctness direction, requiring only per-head activation statistics. Across three model families and multiple math benchmarks, COMPASS outperforms the activation-steering baselines we compare against, improves GSM8K accuracy by 16 percentage points on average, and approaches CoT accuracy with 20-70\% fewer generated tokens. Interventions transfer without re-fitting to unseen benchmarks, and ablations show that both the correctness direction and the small set of heads carrying it are necessary, with the effect concentrated in remarkably few heads.
benchmark - arxiv:2610.07459 · cs.AIAuditable Claims about AI AgentsYue Zhao, Jiate Li, Li Li, Yi Nian +3
Organizations make claims about their AI agents: a person approves every external email, every action is logged, an evaluation shows the agent is safe to deploy. Article 12 of the EU AI Act requires high-risk systems to allow the automatic recording of events but does not say which records settle a given claim. The position is one sentence: to be checked, a claim about an agent must first name its policy, its scope, the records that would settle it, and who writes them. Adapting the preconditions of an assurance engagement, we call a claim auditable when these elements and a decision rule are fixed before any verdict and the records are obtainable. This extends the Policy Checkability dimension of our Auditable Agents framework from single actions to claims. Agents add three conditions: coverage by an independent record, authorization bound to each action's arguments, and completeness beyond integrity. Under an explicit model, we prove that support is impossible without each wherever its hypotheses hold. A claim-check table applies the method to six common claims, anchored in current NIST, IETF, and OWASP drafts. A worked case follows one claim through five evidence states. We close with a practice box and steps for operators, buyers, auditors, and standard setters.
agentai agent - arxiv:2610.07458 · cs.LGInterpretable Hypergraph Learning via Neural Additive ModelsShihan Feng, Xin Zheng, Shiyi Yang, Ren Wang +2
Hypergraphs offer a natural framework for modeling networked data, where dependencies among entities are governed by higher-order interactions. While hypergraph learning methods such as hypergraph neural networks have demonstrated remarkable predictive performance, most existing approaches rely on black-box message-passing architectures, making it difficult to disentangle the contributions of node attributes and higher-order structural information. To address this challenge, we introduce the hypergraph neural additive network (HGNAN), an inherently interpretable framework for learning on hypergraph-structured data. HGNAN extends classical neural additive models to higher-order relational data by integrating feature-wise nonlinear decomposition with hypergraph-aware structural aggregation, enabling transparent prediction for both node- and hyperedge-level tasks. Extensive experiments on benchmark datasets demonstrate that HGNAN achieves performance comparable with state-of-the-art hypergraph learning methods while providing intrinsic and meaningful interpretability.
benchmark - arxiv:2610.07457 · cs.LGAlignQuant: Tile-Aligned Mixed-Precision Quantization for Efficient LLM GenerationHanzhi Zhang, Qiao Zhang, Qinglei Cao, Heng Fan +3
Fine-grained mixed-precision quantization promises efficient large language model inference, but local precision choices can conflict with regular GPU storage and computation units. This precision-boundary mismatch limits the translation of compression into practical acceleration. We introduce AlignQuant, a post-training quantization method that uses GPU-compatible two-dimensional weight tiles as the common unit of precision allocation, compact storage, and execution. This shared partition lets precision follow sensitivity within output channels. Joint prefill/decode calibration scores precision reductions using projection-output perturbations weighted by language-model loss gradients under quantized activations. Phase-normalized scores prioritize higher precision for tiles important to either phase under a model-wide weight-storage budget. Each tile stores one selected representation, while phase-specialized kernels reuse the packed model and expand lower-bit weights for INT8 computation with 8-bit activations. Across four LLMs spanning 3B to 14B parameters, AlignQuant achieves up to $2.50\times$ generation speedup over BF16 while preserving model quality. Evaluations further cover three GPUs and contexts up to 64K tokens. These results show that local precision flexibility and regular GPU execution can coexist through a shared tile unit. The implementation is available at https://github.com/HanzhiZhang-Ulrica/AlignQuant.
post-training - arxiv:2610.07447 · cs.LGFork-and-Flush: Escaping Idea Basins in Autoresearch AgentsZiyang Cai, Christos Ziakas, Vasilis Kontonis, Tim Pearce +4
Autoresearch agents tackle open-ended problems by repeatedly proposing candidate solutions, evaluating them, and using feedback to guide subsequent experiments. We show that independent runs of the same agent on the same task often plateau at substantially different scores, with gaps that persist even after considerable additional compute. Embedding their candidate artifacts by functional similarity provides further evidence that trajectories remain in localized regions of the solution space, which we call idea basins. To help agents escape these basins, we study a simple periodic intervention, fork-and-flush. Our method forks the agent into parallel trajectories, each inheriting the accumulated workspace but starting with a fresh chat context. After running each trajectory for a fixed horizon, the agent continues from the highest-scoring one. Across 13 long-horizon research and engineering tasks, with individual agent runs lasting up to several days, fork-and-flush outperformed the single-run and best-of-N baselines by a relative improvement of 66.0% and 44.4%, respectively, on the min-max normalized average score under an equal compute budget.
agent - arxiv:2610.07444 · cs.LGDecoupling What from Where: How Should a Small GUI Grounding Model Receive the Action Type?Aadi Chauhan, Arthur Ilyasov
A GUI agent decides which action to take and where to take it; we ask how a small grounding model should receive the action type. Fine-tuning Qwen2-VL-2B with LoRA on Android in the Wild, we compare a flat baseline with five ways of supplying the type under matched data, compute, and decoding: an auxiliary loss, a hard-routed action word, an additive learned embedding, a prepended learned token, and the type written into the prompt. With five seeds, an episode-clustered bootstrap, and seed-level paired tests, the ranking on a mixed stream is clear: the auxiliary loss, the additive embedding, and the prompt word each gain five to seven [email protected] points over the baseline, while hard routing and the prepended token are not distinguishable from it. Much of that gain is protection from a preprocessing choice of ours rather than a spatial prior. Our serializer clamps the off-screen touch point AITW records for type events to the origin; that class degrades the baseline's click grounding, and removing it lifts the baseline by nearly seven points, after which no mechanism's hit rate beats it and the intervals exclude a two-point effect, though the auxiliary loss still shortens the average miss; on a stream of taps and swipes none helps. Whether this generalizes beyond one serialization is open. For deployment, the pipeline's margin over the baseline with predicted rather than gold types is not established (+0.016, 95% interval [-0.017, +0.052]), and a wrong type collapses every model conditioned at inference. The prepended token does not help at the shared learning rate, where its rows barely move from initialization; trained ten times faster it reaches the level of the other three, with a margin three seeds do not establish. We also document a silent failure: injecting conditioning through inputs_embeds makes Qwen2-VL fall back to 1-D positions for image tokens, costing nine points.
agent - arxiv:2610.07438 · cs.LGArtifact removal improves electrodermal waveforms but not downstream classification in a virtual-reality balance taskHaochen Chai, Qixu Zhu, Siyao Li, Fangfang Jiang
Artifact removal routinely precedes the classification of electrodermal activity (EDA), on the assumption that a cleaner signal supports a better decision. We tested this assumption in a virtual-reality (VR) balance-disturbance task. A residual gating network was trained on a benchmark with expert-corrected EDA, frozen, and applied to VR recordings, where raw and gated signals were classified by five published time-series methods under identical leave-one-participant-out evaluation. On the benchmark the gate detected artifacts well (median record AUROC 0.94) and reduced error inside artifact regions by 17.8%. In the VR task it did not improve classification. Changes in balanced accuracy ranged from -1.35 to +0.93 percentage points, no classifier improved and two lost accuracy, and all five were equivalent to raw input within +/- 3.32 points. The benefit was lost between waveform and decision. The correction that lowered waveform error also reduced skin conductance response detection in all 43 benchmark records. Processing left 92.8% of predictions unchanged, and the predictions it did change were corrected and corrupted at similar rates. The VR recordings also carried little contamination (an estimated 4.6% of samples), and even perfect localization of deliberately injected artifacts recovered only 3.3 points in the most sensitive classifier. A pooled association between artifact level and accuracy (11.3 points) disappeared within participants (0.1 points), showing how differences between people can make cleaning look useful. Preprocessing should be judged by the decision it supports, against an unprocessed arm.
benchmark - arxiv:2610.07436 · eess.SYReconfigurable Intelligent Surfaces: Architectures, Models, and ApplicationsMojtaba Fallahzadeh, Mohammad Hossein Koohi Ghamsari, Alireza Mallahzadeh, Amirhossein Ghasemi +2
Reconfigurable Intelligent Surfaces (RIS), also known as programmable metasurfaces, have emerged as a promising technology for next-generation wireless communication systems by enabling programmable control over the propagation environment. Through dynamic manipulation of the phase, amplitude, and polarization of electromagnetic waves, RIS introduces new degrees of freedom for enhancing coverage, spectral efficiency, energy efficiency, and interference management. This article reviews recent advances in RIS-enabled wireless communications, focusing on RIS architectures, emerging design and analysis techniques, and their impact on system-level performance. Key challenges related to scalability, hardware non-idealities, channel modeling, and control overhead are discussed, along with promising solutions and future research directions toward practical RIS deployment in beyond-5G and 6G networks.
manipulation - arxiv:2610.07432 · cs.ROEntropy-Gated Belief Coordination for Decentralized Multi-Agent Search Under Intermittent CommunicationMohamed Abdelnaby, Kevin Leahy
We study decentralized multi-agent target search where homogeneous agents communicate intermittently at Poisson-distributed times. Standard unconditional belief fusion wastes communication opportunities by synchronizing agents during high-entropy exploration, when diverse independent beliefs provide better coverage than a premature consensus. We introduce \emph{entropy-gated belief coordination}, in which agents skip fusion while their collective entropy ratio exceeds a threshold~\(θ\) and merge only during exploitation, consistent with the bifurcation structure of nonlinear opinion dynamics and the submodular structure of the per-step information gain objective. We further derive \(\Istep(α,β)\), the expected mutual information per observation step between two agents' binary sensors, as an interpretable, communication-free measure of sensor informativeness that motivates the gating design and guides system-level analysis. Experiments across 103{,}680 trials (nine grid sizes up to \(100{\times}100\), Poisson communication timing, four target movement patterns) show that the Entropy-Gated Trust-Decay Planner (\textsc{EG-TDP}), which adds a detection-probability planner switch in exploitation mode, achieves mean belief quality \(\bar{Q}=0.300\) (mean belief mass at the true target cell, averaged across all trials and steps), a \(58.9\%\) gain over arithmetic mean and a \(37.4\%\) gain over visit-weighted fusion. On representative configurations, EG-TDP also outperforms a joint-Bayesian reference that uses all agents'~observations at every step, despite operating under random intermittent contact only.
multi-agent - arxiv:2610.07423 · cs.AI2d-fet-bench: from spatial reasoning to fet design on flakesDunzhi Zhou, Chengyu Zhu, Gang Qiu, Caiwen Ding
Field-effect transistor (FET) layouts on exfoliated two-dimensional flakes are typically drawn by hand for each flake, placing contacts and gates to match its position and outline in optical micrographs. To our knowledge, no executable benchmark tests whether language-model agents can perform this flake-specific construction reliably. We introduce 2D-FET-Bench V2, a benchmark of 128 layout tasks built from microscopy-derived flake contours, including hole-containing flakes and multi-flake tasks. Each task supplies a textual device specification and contour coordinates. An agent generates typed polygon and path operations rendered to GDSII. A deterministic verifier checks geometric and structural requirements, and a separate integrity check verifies that the supplied contours remain unchanged. Scripted reference layouts pass all 128 tasks, showing that every task is solvable. We evaluate six models and seven workflow and scaffold variants of GPT5.6-Luna, with five attempts per task. The best-performing configuration in the six-model panel, GPT5.6-Luna with ReAct-3, passes 62.3% of attempts and solves 80.5% of tasks at least once (coverage) and 43.8% in all five attempts (consistency). ReAct-3 exceeds the one-pass Plan-and-Execute by 27.0 pass@1 points at 2.46 times the tokens. An expert audit of one sampled verifier-passing layout per covered task, across five ReAct-3 configurations, accepts 56.4% to 63.5% of them. The benchmark evaluates geometric and structural FET layout construction.
agentbenchmark - arxiv:2610.07420 · cs.LGBenchmarking Label-Revealed Online Updates for EEG BCI DecodingBogdan Kozyrskiy, Artem Grachev, Abraham I. Camelo Guerrero
Electroencephalography (EEG) signals drift over time, which can cause static brain-computer interface (BCI) models to degrade in practice. We present a benchmark for online adaptation and compare two widely used pipeline families, Common Spatial Patterns (CSP) and Riemannian covariance-based methods, under time-ordered prequential (test-then-train) evaluation. We examine (i) which pipelines benefit most from label-revealed updates, (ii) whether controlled forgetting of older data improves robustness, and (iii) how a minimal-calibration cold start compares with starting from a pretrained model. Across four datasets (three motor-imagery datasets and one movement-decoding dataset), label-revealed online updates improve 13 of 14 model/dataset pairs on the two largest streams, with relative accuracy gains of up to about 18% over a frozen model. A Shapley-based data-valuation analysis over temporal blocks assigns the largest mean value to the most recent block in each of the three analyzed datasets, while older blocks retain positive value.
benchmark - arxiv:2610.07417 · cs.LGBayesian Optimization on Function Spaces via Sparse RKHS ManifoldsDavide Sartor, Meghan E. Huber, Donghyun Kim, Nathan Wycoff
Bayesian Optimization (BO) has become an established methodology for minimizing black-box functions of a vector input. Often, however, this parameter vector arises from the discretization of an inherently functional relationship. Several recent articles have considered the Functional Bayesian Optimization (FBO) setting, in which the variable to be optimized is not a member of a finite dimensional vector space, but rather an infinite dimensional function space. In this work, we propose $L^0$ Manifold Optimization (L0MO), a simple approach to FBO which searches the subset of a Reproducing Kernel Hilbert Space (RKHS) consisting of functions with a sparse representation in the kernel functions, optimizing both the kernel locations and their coefficients. We discuss in detail the relationship between our method and existing ones, providing a unifying lens through which to view prior works. To assess our method against the state of the art, we conduct an extensive computational study, and along the way develop a novel set of benchmark test functions which port standard finite-dimensional ones to the infinite dimensional domain. Our experiments demonstrate that, on balance, the proposed method achieves superior performance across a wide range of test benchmarks.
benchmark - arxiv:2610.07409 · cs.RORACER: Residual-Adaptive Closed-Loop Estimation for Sampling-Based Planning in Wheeled-Quadruped RacingYuxiang Liu, Marla Eisman, Lizhi Yang, Aaron Ames +1
We present RACER, a hierarchical control framework for wheel-based quadruped racing that combines an MPPI planner with a learned residual dynamics model and a low-level RL velocity tracker. The planner augments a nominal unicycle kinematic model with a neural residual term to capture the closed-loop tracking behavior of the RL policy. To train this residual model under limited real-world data, we propose Low-Rank Residual Adaptation (LoRRA), a two-stage approach that pre-trains on large-scale simulation data for broad coverage and then fine-tunes on a small real-world dataset with a low-rank constraint. In simulation, we empirically validate our engineering choices by showing (A) Residual dynamics improve the overall performance of our pipeline by capturing the tracking error of RL velocity tracker at high-speed cornering. (B) Residual dynamics trained with both source-domain and target-domain data gives racing performance significantly better than the residual dynamics trained with only target-domain data. (C) Low-rank constraint at target-domain adaptation gives higher success rates and higher performance than full-tune and from-scratch when domain gap in ground coefficient or joint gain increases.
quadruped - arxiv:2610.07408 · physics.opticsCompact Circuit Models for Nanoantenna-Based Lightwave ElectronicsAdina Bechhofer, Felix Ritzkowsky, Karl K. Berggren, Phillip D. Keathley
As the field of nanoscale lightwave electronics matures from centering around fundamental science to focusing on device engineering, there is a growing need for compact models that can provide rapid and scalable quantitative analysis of the performance of petahertz-frequency optical-field-driven electronics. In this work, we developed a circuit model framework for describing nano-scale lightwave electronics. Our framework captures the physics governing nanoscale optical devices, such as electrically-connected nanoantennas, using compact circuit models that predict their electromagnetic response, their electron emission, and their charge transfer dynamics. This approach allows scalable simulation of large integrated systems containing networks of nanoscale lightwave electronic components, which is not possible using full-wave electromagnetic and particle-in-cell simulation methods. We implemented the compact model in an free commercial circuit solver (LTspice) and validated its electromagnetic response against a full-wave electromagnetic solver (MEEP). We propose an experiment to fully benchmark the model's ability to capture non-linear charge-transfer-based coupling between devices. The circuit model implementation speeds up the electromagnetic analysis from hours to seconds and accounts for charge-driven coupling, enabling rapid quantitative studies of device operation which provide new insights into how femtosecond signals propagate through nanoscale lightwave electronic structures. We anticipate that the methods we introduce here will become essential to the development and performance analysis of nanoscale lightwave electronics for communication, computation, and signal processing at optical frequencies.
benchmark - arxiv:2610.07405 · cs.LGWhat pass@k Cannot Measure: Evaluating Diversity and Capability Retention after Post-TrainingSubham Rath, Raj Dandekar, Rajat Dandekar, Sreedath Panat
pass@$k$, the fraction of problems a model solves within $k$ sampled attempts, is the field's default protocol for deciding whether reinforcement-learning (RL) post-training on verifiable rewards improved a model. At the population level, pass@$k$ depends only on a problem's probability of a correct sample, with no term for how it is distributed across outputs. We show this gap is not academic. Training Qwen2.5-1.5B-Instruct on grade-school math with Group Relative Policy Optimization (GRPO) and with rejection-sampling fine-tuning (RFT, training on the model's own shortest verifier-passed rollout) moves three complementary diversity measures (token-level entropy, answer-level entropy, unique answers per prompt) in opposite directions, with zero overlap across three seeds per arm. The gap survives restricting to verifier-correct completions only (lexical diversity among correct solutions is 15% lower for GRPO, after controlling for length) and a count-controlled check isolating diversity among incorrect answers alone, ruling out that GRPO's higher accuracy alone explains it. Yet pass@8 and pass@32 show no consistent winner on GSM8K, and a hard MATH-500 subset shows the same pattern: separation only at low $k$. Compared against the starting checkpoint, no trained arm significantly improves hard-problem coverage: RFT is significantly worse, while GRPO is statistically indistinguishable from it - so GRPO's pass@1 edge over RFT reflects a smaller loss relative to Base, not a capability gain, a missing-control issue, not a failure of pass@$k$. On GSM8K, only pass@1, with no role in detecting diversity by construction, separates the arms cleanly, rewarding the arm whose correct solutions are least diverse. We argue this is a concrete instance of a standard evaluation protocol missing a property it is routinely used to certify.
post-trainingevaluation protocol - arxiv:2610.07403 · cs.AIDefense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced SycophancyRitvij Sharma, Russell Dlugosz, Ryan Zhou, Maheep Chaudhary
Long-term memory allows Large Language Models (LLMs) to maintain personalized context across interactions, but retrieved user history can induce memory-induced sycophancy, causing models to favor stored user beliefs over objective evidence. Existing defenses primarily operate on retrieved context and are rarely evaluated jointly with internal behavioral bias. We introduce a $2 \times 2$ defense-in-depth framework separating internal activation steering from external memory handling. We extract sycophancy steering directions from 100 paired prompts and evaluate four open-weight models across 10 steering coefficients and five memory-defense configurations on MemSyco-Bench (answers for all 1,550 items; defense conditions judged on a fixed 250-item subsample), with three LLM judges. Three of the five configurations are new (rewriting every memory, a Router Gate that keeps, rewrites, or drops each memory, and dropping all memory); the other two are MemSyco's baselines. Selective Router Gate filtering preserves substantially more of MemSyco's average accuracy than complete memory removal, and this separation persists when the models are steered toward sycophancy. On Llama 3.1 8B with Router Gate, mild inverse steering ($α= -1.5$) lowers judge-averaged sycophancy from 35.80% to 31.32% while average accuracy moves from 43.99% to 43.31%; this reduction has the same direction under all three judges but is not statistically significant (paired $p = 0.08$ to $0.63$ on 149 items). External memory filtering is the part of the design that holds up; our data do not show that inverse steering adds to it.
memoryexternal memory - arxiv:2610.07399 · cs.LGFed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded ClusteringHaemin Park, Diego Klabjan, Martin W. Braun, Xiuqi Li +1
Federated deep clustering seeks to learn clustering-friendly representations from decentralized unlabeled data while preserving client privacy. However, Deep Embedded Clustering (DEC)-style objectives depend on global soft-assignment statistics that require clients to reveal their sensitive information. We propose Fed-BRDECS, a privacy-preserving and heterogeneity-aware federated deep embedded clustering framework. Fed-BRDECS replaces the globally normalized clustering objective with a locally computable sample-stability loss, avoiding the transmission of local soft-assignment distributions. To tackle non-IID client distributions, we introduce prediction-balanced sampling, which oversamples locally rare predicted clusters without requiring ground-truth labels, and centroid-level restarting, which periodically refreshes biased or inactive centroids. Experiments on image and text clustering benchmarks show that Fed-BRDECS consistently outperforms representative federated clustering and deep clustering baselines under both IID and non-IID partitions. We further demonstrate its applicability to federated time-series anomaly detection, where it improves reconstruction-based detectors without adding inference-time cost.
benchmark - arxiv:2610.07396 · cs.ROWhat the Elevation Map Cannot See: Semantic-Aware Locomotion and Execution-Aware Navigation for Humanoid RobotShunyu Yao, Songyang Liu, Dinghao Chen, Yuanyuan Lei +1
Navigation for humanoid robots is critical, yet large-scale evaluation on physical hardware is often impractical due to cost and safety concerns, making simulation benchmarks essential. Existing VLN benchmarks achieve physically executable navigation, but still assume (1) all hazards are observable from elevation maps; (2) realized motions closely match desired motions. In real environments, however, fallen bottles may be ambiguous in elevation maps, while phones and water spills may be difficult to differentiate; hazard avoidance by the locomotion policy can cause the robot's actual trajectory to deviate from the path intended by the VLN policy. Such command-execution mismatch can accumulate and lead the robot toward unintended locations. To expose these failure modes, we introduce a benchmark that models both elevation-subtle hazards and execution deviations, together with a closed-loop VLN + locomotion control framework that continuously realigns high-level navigation with the robot's actual state. We evaluate navigation in simulation and further validate the locomotion policy on a physical Unitree G1 humanoid robot. Results show that semantic input reduces contact with hazards poorly represented in elevation maps, while anti-deviation improves navigation success. These findings highlight the need to evaluate humanoid navigation jointly in terms of route completion and hazard avoidance.
humanoidbenchmark - arxiv:2610.07383 · cs.LGHyperNSDE: Personalized Neural SDEs for Joint Static-Longitudinal Clinical Data GenerationPerrine Chassat, Agathe Guilloux
Synthetic patient data generation is a promising solution to the dual challenge of data scarcity and privacy constraints in healthcare machine learning. Realistic synthesis of patient-level clinical data requires jointly modeling heterogeneous static covariates, irregularly sampled longitudinal trajectories, and informative observation times - three tightly coupled components in practice yet rarely addressed together. We propose HyperNSDE, a continuous-time generative model that conditions a latent Neural SDE on static patient representations through a hypernetwork, allowing baseline characteristics to shape trajectory evolution beyond the initial condition without requiring a trajectory encoder, while stochastic latent dynamics capture realistic variability in generated paths. Observation times are modeled jointly through a latent-state-dependent intensity process, and training on irregular stochastic paths is stabilized via a deterministic-stochastic path decomposition with a non-adversarial signature-kernel objective. Experiments on simulated and real clinical datasets show improved observation-time fidelity and competitive performance, while matched-grid analyses reveal that forecasting and correlation metrics are affected by observation-grid regularity and trajectory smoothness.
latent dynamics - arxiv:2610.07381 · cs.CVGeoWM: Efficient Direct World Modeling in Explicit GeometryMehrdad Noori, Guile Wu, Sam Hosseini, Dongfeng Bai
Modeling 3D scene geometry and its evolution over time is essential for autonomous driving and robotics. A common paradigm is to use world models to predict future images or latent representations of the environment and subsequently recover geometry from these predictions. However, this paradigm does not explicitly model geometric structure and typically relies on recursive rollouts to reach longer prediction horizons, leading to error accumulation and increasing computational cost. To address these limitations, we present GeoWM, a geometry world model that directly forecasts future scene geometry at specified future horizons without recursive rollout. The key idea is to leverage a geometry foundation model to transform observed RGB frames into a geometric history, which conditions a flow-matching transformer to predict the scene geometry at a specified future horizon. We further show that a lightweight camera-motion predictor can accurately estimate the future viewpoint, and that projecting the observed geometry into the predicted viewpoint provides an effective geometric prior for future geometry forecasting. Extensive experiments on four datasets spanning urban driving, aerial flight, and dynamic manipulation demonstrate that GeoWM outperforms the evaluated world models in forecasting depth, camera pose, and 3D scene geometry, while substantially reducing inference time at longer horizons.
manipulationworld model - arxiv:2610.07376 · cs.AIMemCo: Memory-Centric Collaboration for Generalizing LLM Agents to Unseen EnvironmentsXinting Liao, Siyan Liu, Rabab K. Ward, Holger R. Roth +1
Large language model (LLM) agents increasingly operate in interactive environments, where they need to make sequential decisions through observation, action, and feedback. Although memory can help agents reuse experience, existing work designs memory in isolation, where collecting enough trajectories to populate it is expensive. Existing shared-memory approaches mitigate isolated experience by pooling episodic memories across tasks and environments. However, retrieving shared memory is challenged by the granularity, where retrieved memories can be either too specific to preserve current grounding or too coarse to support the next action. In this work, we propose MemCo, a memory-centric collaboration framework for generalizing LLM agents to unseen interactive environments. It maintains complementary local and global memory spaces, preserving environment-specific details locally while promoting transferable workflows induced from local trajectories to global memory. During online interaction, MemCo routes relevant local and global memories in terms of the agent's current state and decision phase, enabling agents to reuse the experience of other agents without blindly transferring environment-specific details. Experiments on interactive decision-making benchmarks show that MemCo improves task success and reduces redundant exploration compared with isolate-memory and shared-memory baselines. Our code is available at https://github.com/SYannL/nvdamas.
memoryllm agentbenchmark - arxiv:2610.07374 · cs.LGMultigroup Fairness and Omniprediction: Separations and EquivalencesSílvia Casacuberta, Parikshit Gopalan, Varun Kanade, Omer Reingold +2
Omniprediction is a learning guarantee which requires a single predictor to be competitive relative to the best hypothesis from a benchmark class for any loss chosen from a family of loss functions. Loss Outcome Indistinguishability (loss OI for short) is a stronger notion that implies omniprediction. It requires the predicted distribution on labels to be indistinguishable from the true distribution to tests that depend on the loss functions and the benchmark class. Multiaccuracy and multicalibration are multigroup fairness notions that generalize classical notions of calibration and accuracy in expectation. Most known learning algorithms for omniprediction (both for the standard notion and for strengthenings like loss OI) rely on some version of these multigroup fairness notions, or on an intermediate notion called calibrated multiaccuracy. We ask if this is necessary: Does omniprediction require some form of multigroup fairness? We show that the answer is no for (plain) omniprediction, and yes for loss OI. First, a sequence of works shows that multicalibration or calibrated multiaccuracy imply omniprediction. We rule out even a weak converse, by showing that omniprediction for proper losses does not imply even accuracy in expectation, a much weaker notion than any of calibration, multiaccuracy, or multicalibration. Second, prior work showed how to achieve loss OI from a combination of calibration and multiaccuracy. We show a converse: loss OI is equivalent to a form of calibrated multiaccuracy.
benchmark - arxiv:2610.07366 · cs.LGIdentity-Conditioned Score Fusion for Open-Set Person Re-IdentificationManyi Yao, Jurijs Nazarovs, Eunji Chong, Abhishek Sharma +5
Robust person re-identification often combines complementary cues such as face, gait, and body shape. While adaptive fusion typically targets query quality, model strength also varies across identities. We introduce identity-conditioned score fusion, a framework that tailors weights to each gallery identity without training. By contrasting intra-identity consistency against cross-identity impostors, it extracts identity-specific profiles that couple with query-conditioned adaptation via a parameter-free rule. This widens the separation between true and false matches while preserving score calibration. Evaluations on three clothes-changing person re-identification benchmarks show that our method consistently outperforms statistical, rank-based, and learned baselines, achieving up to an 8.8% absolute reduction in the false non-identification rate and demonstrating the value of identity-conditioned fusion in open-set person re-identification.
benchmark - arxiv:2610.07362 · cs.LGDynamic Budget Allocation for LLM Evaluation under Hard Resource ConstraintsShai Feldman, Yaniv Romano
We evaluate large language models (LLMs) in multi-turn interactions through their time-to-event: the number of interaction steps required to produce an event of interest, such as a successful jailbreak or agentic task completion. Under limited compute, interactions may be terminated before the event occurs, so that event times are only partially observed (censored). Existing allocation methods for calibrating time-to-event bounds satisfy the budget only in expectation and can exceed the available budget on a particular evaluation run. Enforcing a hard constraint is particularly challenging as the cost of a trajectory is initially unknown. We introduce Hard-budget Allocation with Reflow for Predictive calibration (HARP), a budget allocation that satisfies hard resource constraints and adaptively reallocates unused budget. We show how to use HARP to construct lower predictive bounds (LPBs) on the time-to-event and to estimate evaluation metrics such as the jailbreak rate on a fixed benchmark. Although HARP induces dependence in acquisition decisions across different trajectories, we prove that HARP never exceeds the target budget, that its LPBs have finite-sample coverage guarantees, and that its metric estimates are unbiased. Experiments on agentic task success, LLM jailbreaks, toxic content generation, and RAG hallucinations show that HARP achieves coverage close to the nominal level with low variance, while never exceeding the given budget.
ragagenticbenchmark - arxiv:2610.07359 · cs.AIEvaluate the Stack, Not the Layer: Do Deterministic and LLM Gates for Agent Actions Fail Independently?Chenglin Yang
Runtime gates for agent tool calls are stacked on the assumption that their errors multiply. We test it on 1,119 labelled agent actions from three corpora, without an adaptive adversary. The stack has one deterministic rule layer and four LLM judges, three of them re-collected with the served model recorded on every call. We read each stack as a number of multiplication-equivalent layers, n_mult, with its floor under perfect coupling. Under the STRICT miss definition (escalation to a human scored as not stopped), any two judges compose to about 1.2 to 1.4 layers (φ median +0.430, 6 of 6 pairs significant, floors 1.02 to 1.17). The rule layer plus one judge composes to 1.86 to 2.09 layers (φ median +0.014, 0 of 4 significant, floors 1.01 to 1.09). Under PRIMARY (escalation scored as caught) the bands are 1.21 to 1.57 and 1.80 to 2.13. Intervals separate on the pooled data, point estimates split on each corpus, and a third-vendor judge lands in the judge band. Solo accuracy does not predict what a layer adds: a cloud rule pack lowers the rule layer's solo miss rate by 20% and adds no new joint coverage. The difficulty share of judge coupling is not identifiable: 31.8% to 61.8% depending on the probe and the miss definition. One judge tier was served by an unrequested model version in 50 of 112 batches, concentrated on the external corpus. That event overturned a pre-declared analysis rule, and the scoring of review verdicts reversed five conclusions. We report both.
agent - arxiv:2610.07358 · cs.LGTowards Explainable Benchmarking for Data-driven Post-Wildfire Debris Flow PredictionZhisheng Qi, Li Zhu, Utkarsh Sahu, Douglas Tommey +2
Post-wildfire debris flows (PFDFs) are destructive sediment-laden hazards triggered when intense rainfall strikes recently burned terrain, destabilizing hillslopes and threatening infrastructure, local economies, and community safety. Data-driven methods have been proposed to learn predictive patterns directly from historical PFDF observations. However, the current research landscape of data-driven PFDF prediction remains highly fragmented across feature spaces, model architectures, and evaluation protocols, making rigorous comparison and the derivation of scientific insights difficult. Moreover, existing studies lack a systematic investigation into the relative importance of heterogeneous factors (e.g., meteorological conditions, terrain characteristics, soil properties, and burn severity) in triggering PFDF. To address these limitations, we present a unified benchmark for data-driven PFDF prediction, enabling fair and comprehensive evaluation across diverse models and feature configurations. Furthermore, to better understand the underlying drivers of PFDF formation, we propose a reinforcement learning-based feature selection framework that identifies factors whose perturbations render positive and negative events indistinguishable, thereby discovering the regional underlying mechanisms of PFDF occurrence across regions. Our code and benchmark are publicly available at https://github.com/KINDLab-Fly/PFDF-Benchmark.
benchmarkevaluation protocol - arxiv:2610.07356 · cs.AIA Validated Dataset and Benchmark for Coherent Multi-Diagram SysML ModelsArdalan Aryashad, Yan Jin
Systems engineers use several diagrams to describe the structure and behavior of systems. Engineers create these diagrams together to make sure that they use the same elements and remain consistent with one another. Large language models can generate diagrams as text or code, which makes it possible to create system diagrams automatically. However, their ability to generate coherent sets of diagrams is not well understood, and existing datasets and benchmarks do not directly measure this ability at scale. We introduce SEMAADB (Systems Engineering Modeling Assistant with AI Dataset and Benchmark), a dataset of 3,000 engineering contexts and 15,000 diagrams. Each context contains five connected SysML views: Requirement, Block Definition, Activity, State Machine, and Sequence. Here, a view is a diagram that presents one aspect of a system. We checked the diagram sets for consistency and valid rendering. A set of 100 contexts is also human-verified and forms the benchmark test set. We evaluate three language models on two tasks. In diagram repair, the strongest model repairs 64.3% of semantic errors . In cross-diagram update the best propagation F1 is 80.7% when a model applies one change across related diagrams. The results show that syntax repair is nearly solved, but semantic repair and consistency across diagrams are still challenging tasks for models. SEMAADB therefore provides both a large diagram resource and a set of benchmarks for measuring coherent multi-diagram SysML generation.
benchmark - arxiv:2610.07355 · cs.CVTracking Is Not Permanence: What Video World Models Keep of a Hidden ObjectPeng Xie, Amr Alanwar
Video world models track objects they can see; we ask what they keep of objects they cannot. We hide an object from a frozen V-JEPA 2 predictor and compare its prediction for the hidden region with the encoder's representation of two worlds that differ only inside that region. The predictor's decision keeps a stationary object in part and one carried inside a container not at all, and loses a moving one within 0.3 s (0.5 s under V-JEPA's own tube mask; ViT-H keeps it to 1.1 s at pretraining's 90% masking ratio); in projection a trace remains, below the midpoint, at 14-60% of what a baseline copying the last view retains. The information is there: the encoder reads the object's presence at 1.00 and keeps a closed container's contents decodable for 3.5 s, while the predictor's output, read with the encoder's own probe, contains the ball in 2% of scenes once the box has been closed for half a second. On rendered scenes, permanence is missing on the predictor's side, and training installs it cheaply as a prior: three thousand predictor-only steps on synthetic containers take this belief from 0.05 to 1.00 against two matched controls. They also raise IntPhys-2019 from 84.2% to 93.3%, but so does a curriculum without containers, and which training habit the benchmark credits changes with its scoring rule. Continued training with tube masks produces 1.1-1.6 s of moving-object carry-over on manipulation and internet-style video, so the deficit is not intrinsic to latent prediction. VideoMAE keeps almost nothing, and Cosmos's next-token prediction keeps a stationary hidden object but not one carried inside a moving container.
manipulationworld modelv-jepabenchmark - arxiv:2610.07354 · cs.AIEvaluating Escalation Signals for LLM Routing: Targets, Controls, and Five Ways to Fool YourselfRamin Pishehvar, Andrea Morandi, Mahesh Viswanathan
Deciding when to escalate a query from a small language model to a larger one requires a cheap signal that predicts, before the large model is called, whether escalating would help. Semantic entropy, originally developed to detect hallucinations, is a natural candidate: it measures how much a model's sampled answers disagree in meaning, and high disagreement often signals an unreliable answer. We test it across three benchmarks and two model families. On GSM8K, with a small/large pair about twelve times apart in size, semantic entropy reliably distinguishes the small model's mistakes (AUROC 0.871) and improves routed accuracy over random escalation by up to nine points at matched cost. An earlier strong-looking result on a synthetic benchmark proved misleading: a simple rule based only on question difficulty, with no model involved, matched semantic entropy almost exactly. This paper's main contribution is a set of checks that catch this before it is reported as real. We show that scoring a cheap, question-only difficulty estimate alongside any signal reveals whether the signal adds real information or just tracks how hard a question looks; that two reasonable definitions of "escalation worked" can produce very different results on the same data; that a benchmark can leave almost no room for any signal to beat simply always using the large model; and that the true cost of live sampling can make routing more expensive than calling the large model directly. For a cheaper alternative that reuses cached past outcomes, we show how to predict whether it will work on a new dataset -- confirmed by correctly forecasting a collapse from AUROC 0.908 to chance level (0.518) ahead of time. We offer these as a general checklist for evaluating escalation signals.
benchmark - arxiv:2610.07350 · cs.AITrajectory-Retrieval Speculative Decoding: When Does a Model's Own History Help?Yuyang Dai, Yushun Dong
Long chain-of-thought reasoning increases sequential decoding cost while creating a growing history of potentially reusable continuations. We investigate when this history supplies useful drafts and complements an existing drafter. Controlled source comparisons reveal trajectory-specific reuse, motivating our method Trajectory-Local Adaptive Retrieval (TLAR). TLAR retrieves approximately matched continuations from the current trajectory and uses recent verification outcomes to adapt retrieval activation and candidate width. TLAR combines retrieved continuations with model-generated drafts in a shared candidate tree, preserving the target model's output distribution through exact verification. Across code debugging, mathematics, and open-ended writing, our evaluation connects source reuse, incremental acceptance, and execution cost. Combining TLAR with strong retrieval baselines improves token acceptance under matched verification budgets and increases end-to-end throughput over the draft-model baseline. These findings support generated trajectories as runtime memory for adaptive inference.
memory - arxiv:2610.07348 · cs.LGStepped MoE: Segment-Level Routing with Configurable Inference ComplexityArnav Kundu, Zhaoyang Xu, Bairu Hou, Chang Gao +2
Training large language models (LLMs) is resource-intensive, and adapting them for diverse deployment scenarios with varying computational constraints remains challenging. While elastic architectures enable flexible model deployment and sparsely activated models allow input-adaptive computation, existing approaches treat these dimensions independently. Moreover, models catered towards on-device edge inference need to conform to the memory and compute limitations of the serving devices. In this paper, we introduce a unified framework that combines elastic structures with sparsely gated architectures to create models that adapt simultaneously to both deployment constraints and task requirements. Our approach employs a model backbone that conditions on both the context and target efficiency specifications, enabling fine-grained control over the accuracy-efficiency trade-off at inference time. The model learns to activate task-relevant parameters within elastically-nested sub-networks, allowing a single model to span multiple capacity points while maintaining input-adaptive routing. Through experiments we demonstrate that we can create a model that allows the flexibility to use 1,2,3,4 billion parameters while being more accurate than their dense counter-parts (2-5\% on knowledge-intensive benchmarks) and at par with their static versions while delivering similar latency metrics as dense models. Overall, we save on device disk space by sharing the model parameters, allow flexibility of serving based on DRAM and compute available while delivering more accurate results.
memorybenchmark - arxiv:2610.07346 · cs.ROScanSTL: Parallel Robustness Evaluation for Signal Temporal LogicGokhan Alcan
Repeated evaluation and differentiation of Signal Temporal Logic (STL) robustness can become a computational bottleneck in robot planning and control. Sequential temporal recurrences limit parallelism, while dense masking increases memory requirements. We propose ScanSTL, which combines associative temporal aggregation with parallel scans and ordered block reductions. Eventually and Always use range extrema, while inclusive strong Until composes compact segment representations. A common range engine handles bounded and shifted intervals, including the guards required before delayed Until witnesses. Each exact temporal operator computes complete robustness traces with linear work and storage and logarithmic parallel depth on uniformly sampled finite signals. An open source JAX implementation supports automatic differentiation, batching, and compilation. We compare ScanSTL with STLCG and STLCG++ using CPU and GPU operator benchmarks and nine composed specifications. Across these nine specifications at 512 samples, ScanSTL achieves geometric mean speedups of 243 times for forward evaluation and 104 times for gradient computation over STLCG++ in JAX on the CPU. On an RTX~5090 GPU, ScanSTL evaluates unbounded Until over more than two million samples with median times below 0.1 ms for forward evaluation and 0.25 ms for gradient computation. Simulated escort and patrol experiments with a robot dog further demonstrate faster repair of violating plans and greater solver capacity in model predictive control.
memorybenchmark - arxiv:2610.07345 · cs.LGEvaluating Behavioral Context for Interpretable IAM Policy Risk Scoring in Cloud EnvironmentsYassin Elsharkawy
IAM policy analysis typically emphasizes the authorization capabilities encoded in a policy, but security analyst review priority may also depend on the behavioral and environmental context surrounding a policy event. This paper evaluates whether contextual information provides measurable incremental value for interpretable IAM policy risk prioritization beyond policy and effective-authorization information. AWS is used as the experimental cloud provider because its IAM and audit-telemetry ecosystem enables controlled evaluation using AWS IAM Context Bench, a benchmark containing 534 real AWS experimental observations across policy, environment, and behavioral scenarios, including matched cases where policy and environment remain fixed while behavioral context changes. Three Explainable Boosting Machine models are evaluated under the same leakage-controlled grouped cross-validation protocol: a policy-centric baseline, a policy-plus-environment model, and a full-context model incorporating CloudTrail telemetry. The full-context model substantially reduces analyst-priority prediction error relative to the policy-centric baseline and closely tracks the reference priority ordering. In matched same-policy context pairs, the policy-centric model remains invariant, whereas the full-context model separates benign and suspicious behavioral conditions with high directional accuracy. The results also show improved concentration of high-priority cases at the top of simulated analyst review queues. These findings indicate that behavioral and environmental context can provide useful incremental information for analyst-oriented IAM risk prioritization while preserving an interpretable additive model structure. The formulation is applicable beyond AWS conceptually, although cross-provider validation remains future work.
benchmark - arxiv:2610.07340 · cs.LGCausalBind: Causal Modeling and Learning for Protein-Molecule Virtual ScreeningLoka Li, Jin Tian, Kun Zhang
Protein-molecule virtual screening is increasingly cast as a problem of representation learning in a shared embedding space. Existing methods rely on dense holistic alignment, entangling invariant binding determinants with nuisance correlations and limiting transfer to new targets. It has been noted that binding in protein-molecule systems involves sparse cross-modality interactions: binding is governed by a small contact interface and a few decisive local interactions (e.g., hydrogen bonds, hydrophobic contacts, and salt bridges) rather than the global structures of the protein and molecule. We hypothesize that uncovering and leveraging sparse interaction patterns is critical for generalization beyond the training data, as these patterns are reusable and expected to improve performance across different scenarios. In this paper, we aim to identify and leverage sparse interaction patterns, and verify our hypothesis. Since the training data contain only observed binding pairs, we formalize this prior via a V-structure causal model under Heckman-style selection, and establish three theoretical results: (i) the latent concepts of interacting proteins and molecules are not identifiable without appropriate sparsity constraints; (ii) these concepts and their sparse interactions are component-wise identifiable under structural sparsity conditions; and (iii) a low-rank relaxation of these conditions yields subspace identifiability of the concepts and interactions. Inspired by these principles, we propose CausalBind with three implementation variants. Extensive experiments on DUD-E and LIT-PCBA benchmarks show that all variants consistently outperform strong retrieval baselines, with the largest gains on LIT-PCBA early enrichment, and further generalize to target- and scaffold-level out-of-distribution splits. Code is available at https://github.com/lokali/CausalBind.
benchmark - arxiv:2610.07338 · cs.LGLogbook: Extremely Long-form Audio Event UnderstandingKwanghee Choi, Suwon Shon, Dmitriy Serdyuk, Guitang Lan +6
Audio benchmarks are built around short, pre-segmented clips, limiting model design to brief inputs or fixed vocabularies. To close this gap, we introduce Logbook, a benchmark for hour-scale audio understanding, with recordings ranging from ten minutes to six days. Given a continuous audio recording and an event label vocabulary, a system must predict a gap-free segmentation with an event label and a description per segment. We compare 52 systems, end-to-end and cascaded, and ablate fine-tuning, context length, and reasoning budget. We find the task tractable, though the best systems remain below the human reference. Also, over-segmentation is pervasive, and fine-tuning partially mitigates it. Finally, end-to-end are often better than cascaded systems, but degrades with longer context.
benchmark - arxiv:2610.07335 · cs.LGSelective Critique for Cost-Aware LLM Agents in Long-Horizon Decision MakingHeewon Park, Somin Im, Minhae Kwon
Improving the reliability of large language model (LLM) agents in long-horizon decision-making remains a key challenge. When deployed as autonomous agents interacting with complex environments, early mistakes can propagate through trajectories and cause cascading failures. Recent approaches improve reliability by incorporating external critique or deliberation, but invoking these mechanisms at every step substantially increases token consumption and latency, limiting practical deployment. We propose SAG (Self-improving Agent with Gated critique), a cost-aware framework that formulates critique invocation as a step-wise decision problem during long-horizon interaction. SAG introduces a lightweight, training-free gating mechanism that estimates the utility of critique using action-level ambiguity signals--global entropy and local top-2 margin--computed over admissible actions. From a decision-theoretic perspective, this mechanism approximates the Value of Information (VoI) of critique, enabling the agent to selectively allocate expensive feedback only when its expected benefit justifies the cost. SAG further incorporates online bootstrapped self-improvement, allowing the actor to internalize critic-assisted behaviors and progressively reduce reliance on critique. Across three long-horizon interactive benchmarks and multiple backbone models, SAG substantially improves the performance-cost trade-off compared with both no-critique and always-on critique agents. On ALFWorld, SAG increases task success from 24.6% to 78.4% while maintaining a token budget comparable to ReAct, yielding a $3.1\times$ improvement in normalized token efficiency. Moreover, a 7B actor with a lightweight 3B critic achieves performance comparable to a 14B actor without critique, showing that selective critique can recover most of the reliability benefits of deliberation while dramatically reducing inference cost.
agentllm agentautonomous agentself-improvingself-improvementbenchmark - arxiv:2610.07333 · cs.AIMemory-Efficient Expert Routing for Distributed MoE TrainingArnab Kanti Tarafder, Jaume Guasch-Martí, Gokcen Kestor, Jie Ren
As Mixture-of-Experts (MoE) models scale toward hundreds of experts and higher top-$k$ routing, memory efficiency in distributed training becomes a critical bottleneck. Peak memory is dominated by the MoE block, not attention: every intermediate buffer in the MoE dispatch pipeline is individually scaled by top-k routing. The standard all-to-all dispatcher sends all routed tokens in a single collective step, requiring the full top-$k$-expanded buffer to be constructed at once. In this work, we propose RelayMoE, a ring-based MoE execution model that computes locally as expert weights or tokens circulate, avoiding full top-$k$-expanded dispatch buffers. RelayMoE selects between expert and token routing according to communication volume and overlaps transfers with computation. The ring structure naturally supports memory-efficient MoE recomputation during backward: each hop reconstructs expert intermediates, uses them to compute gradients, and releases them before the next hop. The saved memory supports longer sequences and larger batches, or retains more attention activations to reduce attention recomputation and improve training throughput. We evaluate RelayMoE on 30B$-$57B production MoE models and varied expert configurations. In single-layer MoE experiments, RelayMoE achieves a $2\times$ average speedup over Megatron-LM. In full-model training under the same GPU memory budget, it improves throughput by up to $2.02\times$ and extends the largest tested trainable sequence length by up to $2.85\times$.
memory - arxiv:2610.07332 · cs.LGStructuring MoE Expert Selection for Agentic Reinforcement LearningBolian Li, Ting-Yao Hu, Cheng-Yu Hsieh, Sanjoy Chowdhury +2
Long-horizon LLM agents are frequently implemented using sparse mixture-of-experts (MoE) models, yet the co-design of agentic behavior and MoE structures remains underexplored. In this work, we comprehensively study the connections between agentic post-training and MoE expert selection. In off-the-shelf MoE models, we observe expert selection exhibits a specialized structure that naturally aligns with agentic trajectories. Specifically, expert routing overlaps more between turns where the agent performs semantically similar operations (e.g., READ, UPDATE) than between turns with differing operations. However, standard RL algorithms ignore this specialization, allowing the MoE routing to go uncontrolled during training, which empirically limit task performance and inference efficiency. To address this, we introduce a hierarchical routing control framework for agentic tasks. We explicitly encourage turn-level expert selections to align with agentic operations while regularizing token-level expert selections to maintain local consistency. To resolve stability issues that arise during post-training with the proposed methods, we further introduce an entropy-gated control mechanism. Overall, our routing control framework achieves over 10-point improvements in success rate on all evaluated benchmarks. These results demonstrate that agentic trajectory structure provides an effective signal for optimizing MoE capacity during RL post-training.
agentllm agentagenticpost-trainingbenchmark - arxiv:2610.07327 · cs.ROSharedKV-BT: Node-Local Typed Decisions for Behavior-Tree AgentsNaoki Wake, Justin Wagle
Agent tasks require sequences of interdependent decisions. Autoregressive models support more flexible decision interfaces than conventional classifiers but incur the latency of token-by-token generation. Recent shared-prefix methods reduce this cost by reusing encoded context and scoring multiple decisions in parallel, but do not model decision dependencies or verify execution. We propose SharedKV-BT, where each active node of a behavior tree (BT) exposes stage-local fields and candidates, and Shared-KV scores the candidates in parallel and passes the selected decision to a separate execution system. We tested SharedKV-BT on robot manipulation, mobile navigation, and computer-use tasks. Across three tasks, SharedKV-BT made typed decisions 2.36-4.15 times faster than prompt-matched autoregressive decoding. On the manipulation task, node-local Shared-KV improved joint decision accuracy from 75% to 94% and closed-loop success from 0% to 60%. Fixed-score policy replay showed that stage gating prevented out-of-order actions and external postconditions prevented premature completion.
manipulationagent - arxiv:2610.07326 · cs.CVLocalize Any Object in X-Ray Security Scans without Human AnnotationYaqi Cai, Mingxuan Liu, Lorenzo Vaquero, Ning Wang +4
Universal object localization in X-ray security inspection is critical for automated threat detection in safety-critical venues. However, unlike everyday RGB images that dominate web-scale visual data, X-ray scans exhibit distinct color patterns, ambiguous boundaries, and compositional structures caused by volumetric superposition. These gaps hinder the direct zero-shot transfer of dense perception foundation models trained on web-scale RGB data. Moreover, annotated X-ray data is scarce and requires expert labeling, limiting both the training of generalizable X-ray native models and the adaptation of RGB foundation models for X-ray data via fine-tuning. Given these challenges, the bright promise of highly generalizable perception models, enabled by data scaling laws in the RGB domain, remains largely out of reach for X-ray inspection. To this end, we introduce LAO-X, a self-supervised adaptation framework that Locates Any Object in X-ray scans using diverse synthesized image--annotation pairs with granularity-aware supervision. LAO-X first designs a saliency-guided X-ray object mining module to separate diverse object instances, which are then used for physics-guided synthesis in the absorbance domain. LAO-X further incorporates an occlusion-controlled curriculum strategy to fine-tune a Segment Anything Model 2 (SAM2) localizer, progressively adapting it to X-ray scans with increasing object counts and overlap levels. Experiments on six X-ray benchmarks show that LAO-X substantially improves category-agnostic localization, achieving 2\% to 23\% mAP gains over SAM2 and X-ray specific baselines in heavily cluttered scenarios, entirely without human-annotated labels.
benchmark - arxiv:2610.07324 · cs.LGScale-Invariant Training for Time Series Foundation ModelsIgnacy Stepka, Willa Potosnak, Kin G. Olivares, Artur Dubrawski
Time series foundation models (TSFMs) are trained on large collections of time series datasets that span various morphologies and domains. This setting exposes models to series whose scales -- typical magnitudes of their values -- can differ substantially. Affine scaling methods such as Reversible Instance Normalization (ReVIN) scale model inputs and reverse the transform before computing the loss. We show that this inversion multiplies each series' gradient by $b^p$ relative to loss on scaled targets, where $b$ is the scaling denominator (e.g., standard deviation) and $p$ is the loss degree. We call this scale-contaminated training (ScaleCon), because the scale of each series consequently becomes an importance weight, causing high-scale series to dominate training. For any scale-equivariant scaler and residual loss that is homogeneous of degree $p$, including MSE, MAE, and Quantile Loss, we prove that computing loss on scaled targets makes every mini-batch gradient and, consequently, the full optimization trajectory invariant to arbitrary independent rescaling of the training series, yielding scale-invariant training (ScaleIn). Notably, existing TSFMs use both objectives, with neither consistent reporting nor a common convention on how to compute training loss. We isolate the convergence disparity induced by ScaleCon and its correction under ScaleIn in controlled studies on synthetic and real data. In pretraining across four TSFM architectures, ScaleIn lowers MASE in all 24 architecture-benchmark comparisons, with average reductions across TSFMs of 18.8% on GIFT-Eval and 21.9% on the M-competitions. The gains extend to supervised neural forecasting, where it lowers MASE in 16 of 20 matched settings. Most existing time series forecasting pipelines can adopt ScaleIn with a one-line code change.
benchmark - arxiv:2610.07320 · cs.ROTowards Decentralized Formation of Minimum-Length Communication Networks Using Robot SwarmsGenki Miyauchi, Mohamed S. Talamali, Julian Rau, Roderich Groß
Multi-robot missions in infrastructure-denied environments frequently rely on reliable communication links between spatially separated locations. We propose a fully decentralized framework for constructing and dynamically maintaining communication networks without centralized topology planning or global positioning infrastructure. Driven strictly by local interactions, robots reconfigure local network topologies and adjust their physical positions to minimize overall network length while adhering to communication constraints. Formal analysis shows that our local reconfiguration operations guarantee continuous network connectivity, strictly decrease network length with every branch transfer, and bound worst-case performance to the shortest starlike tree. Embodied simulations and physical multi-robot experiments confirm that our approach forms networks near the length of centrally computed Euclidean Steiner trees. Additionally, the system dynamically adapts to moving targets and optimizes deployment by utilizing only necessary connectors, preserving excess robots for auxiliary tasks. This work enables autonomous swarms to self-organize adaptive ad hoc communication infrastructure in communication-denied environments, which could support applications varying from subterranean exploration to planetary missions.
embodied - arxiv:2610.07311 · cs.AIUnderstanding and Mitigating Inference-Time Overreliance Using Agentic MemoryLuoxi Tang, Yuqiao Meng, Nilesh Auradkar, Muchao Ye +2
Agentic memory allows LLM agents to reuse past experience, yet retrieved memories can also distort inference even when they are benign, correctly stored, and appropriately retrieved. We study this failure mode, which we call memory over-reliance. Across benchmarks and memory architectures, we find that memory is useful when past experience transfers to the current task, but can become misleading when only part of the evidence transfers. Failures are strongest under partial query-memory overlap, a pattern further confirmed by controlled experiments thatvary the amount of overlapping evidence. Motivated by this finding, we propose MEMTRIM, a plug-and-play framework that indexes memory evidence at write time and controls its reuse at read time. MEMTRIM removes repeated or conflicting evidence while preserving useful memory-specific information, requires no retraining, and applies to both embedding-based and structured memory systems.Experiments show that MEMTRIM reduces memory overreliance while preserving the benefits of useful memory across models and memory settings.
memorymemory architecturellm agentagenticbenchmark - arxiv:2610.07310 · cs.AIFrom Sandbox to Enforcement: Confidence-Qualified Threat Intelligence for Critical InfrastructureNikolaos Kekatos, Mihaela Curcă, Georgios Koutidis, Mihai Nena +4
Security operations centres and national incident-response teams defending critical infrastructure collect abundant threat data yet struggle to turn it into actionable intelligence. A malware sandbox produces detailed behavioural evidence, but as a large, unranked report whose confidence is unstated. We present CG-CTI, an operational pipeline that converts live sandbox output (CAPEv2) into STIX 2.1, correlates it in a knowledge graph with other critical-infrastructure sensors, and attaches to every intelligence object an explicit confidence status derived from provenance, cross-source corroboration, and observation durability. This status gates automated action: only corroborated intelligence is eligible for automated enforcement, while lower-confidence objects are routed to analyst review or kept as context. A grounded language-model stage then narrates the confidence-qualified evidence, where each statement either cites a supporting object or is marked unsupported, so fabricated references are removed before analyst review. We implement CG-CTI within the CYBERGUARD project, whose consortium includes Romania's national cyber-security directorate, and evaluate it against the live sandbox on a labelled malware corpus, measuring conversion validity, indicator yield, technique coverage, corroboration, enforcement eligibility, latency, and summary grounding. CG-CTI turns fragmented sandbox output into corroborated, confidence-ranked, and auditable intelligence for critical-infrastructure defence.
knowledge graph - arxiv:2610.07309 · cs.AIThe Right Memory in the Wrong Context: Verifying Retrieval Admissibility in Long-Term Agent MemoryZi Wang, Xingqiao Wang, Emmanuel Addai, Devika Ambekar +1
Long-term-memory agents can retrieve relevant information that is inadmissible for the current request because it belongs to another principal, violates policy, or reflects an incompatible lifecycle state. Recall and final-answer accuracy do not reveal this: a route can appear safe by missing required evidence, while a correct answer may follow inadmissible prompt exposure. We introduce a retrieval-admissibility verification framework that assigns each memory-query pair one of three statuses (admissible, inadmissible, or unresolved), compares routes at matched required-evidence recall with bounds for unresolved cases, and tracks memory IDs through prompt exposure while linking exposure to target-level disclosure. We evaluate its stages on separate, non-pooled populations. A post-hoc top-20 reanalysis of frozen rankings from two public long-term-memory benchmarks, RHELM and MemOps, covers 3,767 queries. All released anchors lie within trusted query namespaces; with within-namespace scores unchanged, off-namespace filtering cannot lower their ranks. Top-20 anchor recall increases from 0.432 to 0.533, 80% recall feasibility from 0.237 to 0.311, and exact similarity evaluations decrease by 98.3%. In a frozen 72-case development diagnostic, a released-metadata reference preserves required evidence, whereas neither text-only verifier detects violations under the 1% required-anchor false-denial limit. Across 1,523 paired benchmark-native cases, namespace routing is associated with judged-accuracy gains of 0.053-0.068 across three readers; recall also changes, so this comparison is observational. In 16 controlled exposure scenarios, only one of four reader-specific 95% confidence intervals excludes zero for relevant-inadmissible literal disclosure (+0.156, 95% CI [0.031, 0.312]). Results motivate separate verification of candidate support, admissibility, prompt exposure, and answer disclosure.
memoryagent memoryagentbenchmark - arxiv:2610.07289 · cs.AICatching Developers in the Flow: Low-Latency Agentic Program Repair at Google ScaleCelal Ziftci, Spencer Greene, Ray Liu, Livio Dalloro +1
Manual repair of program failures is time-consuming and disruptive for software developers, particularly during the pre-submit phase where test failures occur within continuous integration systems. While Automated Program Repair has seen significant advancement through Large Language Models, existing state-of-the-art techniques primarily focus on post-submit workflows, operating offline without the low-latency requirements necessary to assist developers in real-time within their flow before they switch context. In this paper, we introduce FlowAgent, an AI agent deployed at Google to automatically repair test failures in the pre-submit outer-loop workflow inside continuous integration systems. Integrated into Google's internal developer tools, Critique and Cider,FlowAgent utilizes a ReAct-style generate-and-validate loop, as well as rigorous pre-execution and post-execution abstention filters to ensure high-quality suggestions under strict latency constraints. Based on our case studies, FlowAgent is highly effective. First, a manual evaluation conducted on 195 real-world test failures demonstrated 67.18% accuracy in suggesting correct fixes. Following its Google-wide deployment, FlowAgent suggested fixes on 295,508changes, of which developers previewed 65,069 and applied 28,554. Developer feedback from interviews indicate that the agent is useful in suggesting correct fixes, integration of autonomous repair agents into industrial software engineering workflows is received well, while interesting challenges and opportunities still remain.
agentai agentagentic - arxiv:2610.07274 · cs.AIA Trust Layer for Agent EvaluationMohammadreza Sediqin, Shivali Dalmia, Srinivasa Karthikeya Reddy Kovvuri, Abhishek Mukherji
Deterministic benchmark scores show that an agent received credit, but not whether that credit was earned, reported honestly, or would hold on a second run. We introduce a Trust Layer for Agent Evaluation, an additive post-hoc framework that reports, beside each recorded score, whether it should be believed. It verifies four properties: whether the result is supported by the benchmark's own grading logic, whether a passing answer was earned through traceable computation, whether the agent's completion claim matches what occurred, and whether the result is stable under repeated execution. The first three use only saved artifacts; the fourth re-runs the agent. Model judgments only label evidence under majority voting; all verdicts follow deterministic rules and never modify the recorded score. Applied to five agent configurations on 108 tasks from Agents' Last Exam, every model shows passing runs with no traceable computation (at rates varying tenfold), confirmed false completion claims, and unstable results: 18-46% of tasks do not stay in one score band over five runs. Only 22.6% of recorded passes clear all four checks (95% CI 15.0-32.6, n=84). Measuring what an agent can do and verifying that it did it are different problems, and current benchmarks address only the first.
agentbenchmark - arxiv:2610.07270 · cs.AIDoes the Model Use the Feature? Separating Steering from Mechanism in LLMsTong Che, Yilong Li
Internal features in LLMs are often interpreted as mechanisms when they track a concept and their manipulation changes a related behavior. Yet steering can push a feature far outside its natural range, where its effects need not reflect the model's own computation. We examine this inference and propose an empirical contract whose tests evaluate features at values observed on natural inputs. One test copies a feature's value from an input that shows a behavior into a matched input that does not (installation) or the reverse (removal); the other restores the feature after an upstream edit (downstream rescue). Installation measures how far the feature suffices for the behavior; removal and downstream rescue measure how much the model uses it. Applied to three kinds of representations, the two strengths separate sharply. The published unknown-entity latent strongly steers knowledge abstention, yet installing observed values from either published latent into matched prompts transfers only a small fraction of the natural known--unknown abstention contrast. Dense known--unknown directions show opposite asymmetries between installation and removal in Gemma and Llama, and how fully a released subject--verb agreement feature set reproduces and restores the behavior depends on how its values are written into the model. Tracking a concept and steering a behavior therefore do not by themselves show that the model uses a feature, and each conclusion holds only for the intervention tested.
manipulation - arxiv:2610.07261 · cs.AIVerifying Coordination in Parallel Coding Agents: NP-Bench and a Scheduling PlannerSumanyu Muku
A team of coding agents can look fine agent by agent yet fail as a team: each passes its own tests while the merged result is broken, and single-agent evaluation never catches it. As teams run several LLM coding agents in parallel on one codebase, the agents collide: two rewrite the same function, one codes against a contract a teammate just changed, and integration fails after the work is done. Most coordination tools react (watch for a conflict, then warn), but at agent speed the warning arrives after the wasted edit. We recast the problem as scheduling: take each work item's declared scope, partition the work into disjoint scopes, and order merges along the producer->consumer graph, all up front. We build this planner into Nerveplane and evaluate it with NP-Bench, an environment-grounded three-arm benchmark (no coordination; reactive detection; proactive planning) that verifies integration off a real git merge, both in a deterministic simulation and with live agents. The planner lifts clean-integration from 1/9 to 9/9 scenarios and cuts merge conflicts from 13 to 0, with a gap that grows in the number of agents. On a live breaking contract change it rescues an outcome both baselines miss on every seed: the clean-integration rate rises from 0 (no coordination and reactive detection) to 1.0 on a frontier model and 0.6 on a small one, while agents respect assigned scopes (0/5 leakage). A cross-session memory drops the repeated-mistake rate from 1.00 to 0.00 on strong and weak models alike. We also report a negative result: routing facts to agents does not rescue long-context accuracy at window-fitting scales; its value is cost and capacity, not attention. Across two capability tiers and two vendors, the benefit did not shrink as models got stronger, because it comes from how work is allocated, not model reasoning.
memorylong-contextagentbenchmark - arxiv:2610.07258 · cs.LGLineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI AgentsVenkata M Sangaraju, Sudhir Vissa
Enterprise AI agents that share a memory store face two unaddressed risks: sensitive data can leak through legitimately computed results the requester could not derive, and departments can silently compute a same-named key performance indicator (KPI) through conflicting logic. Existing agent-memory systems (e.g., MemGPT, Zep, A-MEM) gate retrieval by content, ownership, and role, not derivation, missing a cached insight that embeds a forbidden column. We introduce the Analytical Memory Unit (AMU), a memory schema that attaches a full derivation (lineage) graph to every cached result, gated by a retrieval policy that serves a hit only when the requester is authorised for every column touched. Provided lineage recording is complete, we prove by construction that the policy blocks retrieval of results derived from a sensitive column outside the requester's permissions, at O(n) worst case -- a conditional design guarantee, not an empirical claim, that excludes derived features encoding sensitive information without naming their source. Eliminating measured leakage required 75-90% recorded lineage completeness, so we treat 90% as a conservative deployment target. Across six experiments, lineage-gated retrieval removes the 18.8-25.5% cross-department leakage naive content-gated memory suffers, keeping 81.5-82.6% of memory reuse at 13.8 microsecond worst-case overhead. A real-agent proof-of-concept with LLM-generated SQL is consistent with the guarantee: zero leaks over 9 round-trips, two conflicts caught automatically -- though a feasibility demonstration, not evidence of production viability. This offers a practical governance layer for shared agent memory, complementing source-layer access control and supporting EU AI Act compliance.
memoryagent memoryagentai agent - arxiv:2610.07257 · cs.AIMemMux: Runtime Verification and Honest Resource Attribution for Fleets of Parallel Coding AgentsSumanyu Muku
Developers increasingly run a fleet of coding agents side by side on one workstation. The tools they reach for, terminal multiplexers like tmux and a new generation of agent managers, were built to arrange windows, not to govern memory. When ten agents each spawn language servers, test runners, and browsers, no standard tool can say how much memory belongs to which agent, confirm that a terminated agent's descendants are gone, notice a child that has escaped its agent, or keep the machine off the swap cliff when an OOM kill would silently discard uncommitted work. We treat these as runtime-verification problems: an agent-hosting substrate should continuously emit observable signals an operator or auditor can check while agents run. We present MemMux, a local runtime that turns resource governance into checkable signals (per-agent attribution, complete reclamation, escaped-process visibility, bounded footprint under overcommit, and monitoring overhead), with a claims-disciplined benchmark against tmux, a purpose-built agent multiplexer, and a raw-process baseline on identical workloads. Under a binding memory budget on a Linux host, MemMux keeps the fleet under budget (7.5 GiB) with zero swap by admitting a subset and reclaiming under pressure, while the ungoverned tools run every agent, pin the machine at its RAM ceiling (2x over budget), and spill about 2 GiB into swap. MemMux reclaims 100% of a terminated agent's process subtree where the raw baseline strands half of it, and it alone surfaces escaped children (10 of 10 detected). We report the cost: the 1 Hz attribution scan runs near 0.6% CPU at one agent but 2.7% at ten, above our 2% target. Running the harness on real Claude Code sessions shows 100% attribution and low overhead carry over to live agent trees. We release the engine, benchmark, and a one-command reproducer.
memoryagentbenchmark - arxiv:2610.07250 · cs.AIInternalizing Agent Experience into Diffusion Model Weights via On-Policy Context DistillationWenxuan Wang, Zekai Liu, Weinan Zhang, Yu Cheng +1
Wrapping an image generation model in an agentic harness can effectively boost Text-to-Image task performance: the harness can leverage memory, skills, workflow orchestration, result verification, and iterative refinement to continually construct and revise prompts, thereby eliciting better images. These gains, however, remain external to the diffusion model and are realized only while the full harness runs. We propose Diffusion On-Policy Context Distillation (D-OPCD), which treats the agent-improved prompt as privileged context and distills the knowledge encoded in the agent harness into the weights of the diffusion model, so that the model retains part of the harness's benefit when conditioned on the original query alone. Using a Text-to-Image agent equipped with our proposed Auto Skill Evolver (ASE), we show that D-OPCD can internalize harness capabilities into the generator's weights, raising the average direct-generation score from 60.52 to 65.09 across four benchmarks. With this knowledge absorbed into the weights, the harness can shed its saturated skills and resume evolving: a second ASE round on the updated generator improves on a skill-free harness by additional 1.83 points, pointing toward text-to-image systems in which harness and model keep improving each other through continual co-evolution.
agentagenticiterative refinementbenchmark - arxiv:2610.07249 · cs.AICan Semantic Geometry Teach an AI Judgement?Thomson D. Nguy
How can an AI agent determine what rules to follow? One rule permits an action. Another imposes a condition, exception, or conflicting obligation. Deterministic systems can resolve those relationships when they have been specified. When they remain implicit in language, an agent can follow one rule while missing another that should stop it. Refusing every unresolved action avoids that risk, but also blocks permissible actions. We wanted the agent to make the distinction and still act. Our initial hypothesis was that geometric measurements could supply a basis for judgment. We represented actions and policies as vectors, then tested whether their geometry could identify governing policies and interpret the action's relation to them. Across four studies, the tested approaches did not establish reliable pre-action judgment. In the final synthetic study, a lexical router recovered every governing and blocking policy while reducing median policy checks by 97.7%. The composed pipeline nevertheless escalated all 2,304 test actions, including those it should have allowed. Supplying every policy to the same downstream mechanism changed no decision. Finding the policies had not solved the problem of interpreting them. This result led us to revise our hypothesis: judgment in AI agents requires developing a consequence graph. Such a graph would connect the actor and authority to policy conditions, exceptions, and the changes an action would produce. Follow-on studies will ask whether making those relationships explicit helps the agent distinguish when to act, stop, or seek review.
agentai agent - arxiv:2610.07247 · cs.LGLearning What to Distill: Bilevel Top-K Token Selection for Self-Distillation in Large Language ModelsHeng Liang, Xinwen Zhang, Hongchang Gao
Large language models have shown strong reasoning capabilities, but their high inference costs make knowledge distillation an important approach for transferring such capabilities to compact models in resource-constrained scenarios. On-policy self-distillation further reduces the reliance on external large teacher models while improving the reasoning ability of compact language models. However, existing methods typically either distill all token positions uniformly or select tokens using fixed heuristic criteria, assigning the same distillation strength to the selected positions rather than adaptively learning which tokens are most beneficial for distillation. To address these limitations, we propose BiToK-SD (Bilevel Top-K Token Selection for Self-Distillation), a bilevel-optimization-based token selection method that learns where distillation should be applied during on-policy self-distillation. Specifically, BiToK-SD is formulated as a bilevel optimization problem, where the lower-level problem models Top-K token selection as a differentiable threshold-based relaxation, allowing the selected positions to adapt as the student policy evolves, while the upper-level problem performs knowledge distillation on the selected positions. Experiments on mathematical reasoning benchmarks show that BiToK-SD achieves the best average performance among all compared methods while requiring only lightweight additional computation.
benchmark - arxiv:2610.07245 · cs.RORobust Nonprehensile Object Transport with Quadruped RobotsAinoor Teimoorzadeh, Riccardo Pretto, Mario Selvaggio, Gokhan Alcan +1
In this paper, we present a robust nonprehensile object transportation framework for quadruped robots. An uncertainty-aware trajectory optimization method generates object motions with minimal closed-loop sensitivity to uncertain parameters. The resulting reference trajectory is tracked using a coupled convex model predictive controller that jointly predicts the CoM dynamics of the quadruped and the payload followed by a whole-body QP that enforces ground reaction constraints. The approach is evaluated through extensive simulations and real-world experiments under variations in the object's inertial parameters. Its performance is compared with fixed-orientation and straight-line trajectories as baseline. The results show that the optimized object motion reduces the sliding by approximately 50% compared with the fixed-orientation baseline and 30% compared with the straight-line baseline, while also achieving lower robot CoM tracking errors.
quadruped - arxiv:2610.07237 · cs.AISPECTRUM: Proximal Spectral Modulation for Looped Self-DistillationYunbo Long, WenJie Chen, Jiaquan Zhang, Guangya Hao +3
A model that learns from its own outputs inherits more than their correctness: it inherits which solutions it produces. We formulate Looped Self-Distillation, a self-evolution framework for code generation in which a model repeatedly generates and learns from its own raw outputs, under a fixed information budget, without ongoing external assessment or test-based selection of the generated samples. We identify a consequential separation: correctness can improve while the breadth of correct implementations contracts. We introduce SPECTRUM, which re-estimates loss-sensitive key/value geometry from a fixed reference anchor at each round and converts it into full-rank proximal spectral modulation. All generated completions train a single student, whose subsequent inference requires no intervention. After five rounds of experiments on MBPP, SPECTRUM retains 89.9% of the initial model's 64-sample correct AST richness, compared with 66.4% for Vanilla self-distillation and 65.5% for a subspace-projection control. The advantage persists at matched correct-sample counts. Without further training or recalibration, the resulting student also achieves higher matched-correct richness than Vanilla SD on HumanEval+ and APPS Intro, demonstrating transfer of the diversity benefit. These findings establish correct-solution retention as a complementary objective of recursive self-improvement (RSI) and show that generation-time intervention can improve the solution repertoire retained by subsequent students.
self-improvement - arxiv:2610.07232 · cs.LGBenchmarking Time Series Foundation Models for Load Forecasting Under Covariate UncertaintyTomas Kaljevic, Ivan Arzola, Yu Zhang
Accurate short-term load forecasting (STLF) is essential for the reliable and efficient operation of modern power systems. While time series foundation models (TSFMs) have recently demonstrated remarkable performance across a wide range of forecasting tasks, their effectiveness for STLF under realistic operational conditions remains largely unexplored. In this paper, we present a comprehensive benchmark of four trained-from-scratch (TFS) models and four TSFMs across three real-world load forecasting datasets under operational scenarios that differ in the availability and quality of future covariate information. Our results show that Chronos-2 consistently achieves state-of-the-art performance in both zero-shot and fine-tuned settings when future covariates are available or accurately forecast. However, its performance degrades as covariate forecasts become increasingly noisy, whereas TimesNet exhibits greater robustness under severe covariate uncertainty. These findings demonstrate the effectiveness of covariate-informed TSFMs for STLF while highlighting the critical role of robust covariate modeling in real-world forecasting applications.
benchmark - arxiv:2610.07217 · cs.RORoboCap: A New Platform for Egocentric Robot LearningGrounded Superintelligence, BitRobot
Despite its promise for scaling robot learning, egocentric manipulation data is still scarce today. Collection at scale requires vertically integrating ergonomic hardware with centimeter-precise 3D algorithms, at a precision that has not been publicly demonstrated. To address this gap, we introduce RoboCap, a 250\,g six-camera dual-IMU hat designed for in-the-wild egocentric data capture, and the Grounded API, a suite of device-agnostic 3D algorithms tuned for RoboCap. In this report, we demonstrate how hardware, calibration, and 3D algorithms interact to achieve state-of-the-art performance on the public benchmarks: our SLAM across diverse settings and rigs, our depth estimation on egocentric settings, and our hand tracking when adapted to third-party devices.
manipulationbenchmark - arxiv:2610.07209 · cs.CLForecasting the Growth of Social Media Information Cascades: Towards Human-in-the-Loop Misinformation TriageAnsh Gupta, Abhiram Gorle, Aayush Rajesh, Tsachy Weissman
Limited review teams must identify which emerging claims are likely to keep growing before their eventual reach is known. We center early misinformation triage on this continuation-forecasting problem: predicting subsequent recorded propagation-tree growth from the first 30 minutes of activity. On FibVID, we compare early node count with structural depth entropy, temporal arrival entropy, and their pair while keeping all propagation trees from each original claim in one partition. Across 352 test trees from 59 claim groups separate from training, the combined model raises $R^2$ for log-transformed future growth from 0.307 to 0.323 and reduces log-MAE by 2.4% (95% claim-bootstrap CI, -0.4% to 5.2%). The gain is especially pronounced among 97 high-activity trees: $R^2$ rises from 0.248 to 0.395, Spearman's $ρ$ from 0.394 to 0.529, and log-MAE falls by 11.7% (95% CI, -1.9% to 23.9%). Complementing the 30-minute growth forecast, we analyze the first 15 replies in 563 PHEME threads. In this cohort, the 15th reply arrives after a median of 28.8 minutes; 52.0% reach the fixed reply prefix within 30 minutes and 71.6% within one hour. Even without the LLM-generated factual-accuracy dimension, the remaining stance, communicative, and affective state composition retains cross-event ranking signal (ROC-AUC 0.538); including that dimension increases ROC-AUC to 0.562. In a separate Check-COVID evaluation of 229 claims, reciprocal-rank fusion retrieves a gold evidence document within the top five for 74.2% of claims and within the top 20 for 94.3%; sentence reranking reaches Recall@20 of 58.1%. We propose an integrated human-review system that brings these early forecasts, response patterns, and retrieved evidence together for misinformation triage relying on the potential virality of claims.
human-in-the-loop - arxiv:2610.07192 · cs.ROSim-to-Real Transfer of Vision-Language Navigation in Continuous Environments Using an Ackermann-Steered Mobile RobotChalindu Abeywansa, Sahan Gunasekara, Devindi De Silva, Seniru Dissanayake +2
Vision-Language Navigation (VLN) enables robots to navigate through environments using natural language instructions, making human-robot interaction intuitive. Traditional VLN models often rely on navigation graphs, 360-degree views, and perfect localization which pose significant challenges when adapting these models to real-world settings. This work addresses these limitations by performing a simulation-to-real domain shift of a VLN approach that operates in continuous environments without requiring navigation graphs or panoramic views. The proposed system integrates vision-language models that align visual inputs and linguistic instructions within a shared embedding space, facilitating natural language-driven navigation. We employ a Cross-Modal Attention (CMA) based architecture trained on an existing dataset in a simulated environment and fine-tune it using real-world data collected from a custom-built Ackermann-steered robot equipped with a camera and a LiDAR sensor. By utilising linear photometric adjustments and fine-tuning on a limited number of episodes, our model successfully adapts to real-world environments, achieving effective navigation while running offline on dedicated hardware. Experimental results, evaluated using Success weighted by Path Length (SPL) and Normalized Dynamic Time Warping (nDTW) metrics, demonstrate the robustness and adaptability of our approach. Keywords: Vision-Language Navigation, Cross-Modal Attention, Natural Language Instructions, Sim-to-Real Transfer, Autonomous Navigation, Ackermann-steering.
sim-to-real - arxiv:2610.07191 · cs.AIAgentic Design Space Exploration for Joint Hardware Configuration Selection and Mapping of AI Inference Workloads on Heterogeneous Edge SoCsGeetha Prasuna Yarramneni, Surya Selvam, Wilfried Haensch, Anand Raghunathan
Modern edge Systems-on-Chip (SoCs) integrate heterogeneous processing units (PUs) such as CPUs, GPUs, and NPUs, each with distinct performance and energy characteristics. Deploying AI inference workloads on them under real-time latency and energy constraints requires jointly mapping workloads to PUs and configuring each PU (e.g., selecting the number of active cores and the operating frequency). This joint space grows combinatorially, making exhaustive search infeasible. Most prior work on design space exploration (DSE) applies black-box optimization (BBO) such as evolutionary search, where each evaluation returns only aggregate metrics such as latency and energy. Recent LLM-guided DSE relies on the same sparse feedback. We observe that this limits its efficiency: it offers no insight into the design space or the reasons a design choice performs the way it does, and it leaves the reasoning abilities of LLMs largely unused. We present TraceDSE, an agentic DSE flow that performs joint workload mapping and PU configuration selection for AI inference on heterogeneous SoCs. TraceDSE is an iterative proposer-critic loop driven by richer feedback in the form of system execution traces. The LLM proposer agent generates candidate mappings and PU configurations for hardware evaluation. The LLM critic agent, equipped with programmatic trace-analysis tools, analyzes the traces to identify bottlenecks and suggest targeted refinements. This loop yields deeper insight into each design point, higher-quality decisions, and a more effective search. Across four AI inference workloads (models of varying complexity and a multi-model pipeline) on an Intel Meteor Lake SoC, TraceDSE consistently outperforms two state-of-the-art BBO tools, improving Pareto frontier hypervolume by up to 35% over NSGA-II and up to 68% over Bayesian optimization, while requiring ~6-9x fewer hardware evaluations.
agentagentic - arxiv:2610.07177 · cs.LGCLM-as-a-Judge: Evaluating an Open Contrastive Decision Model on Public Judge BenchmarksGowthamkumar Nandakishore
An open contrastive decision model is near chance as a judge on the hard public benchmarks: Contrastive-LM/CLM-v0.1-8B scores between 0.351 (best- of-four, chance 0.250) and 0.593 (pairwise, chance 0.500), is statistically indistinguishable from coin flipping on RM-Bench and JudgeBench, and answers every HaluEval item with one constant label, matching the trivial always-first baseline at 0.581. Judges with the same parameter count score far higher everywhere: a reward model reaches 0.764 to 0.976 and a generative judge 0.611 to 0.778, and every gap to CLM is significant after Benjamini-Hochberg correction. Two properties do work. Raw confidences are overconfident by up to +0.401, yet one pooled temperature fit on held-out calibration items repairs expected calibration error to at most 0.062, and the repaired confidence ranks the model's own errors above chance on three of six benchmarks. The decision order-flip rate is 0.0002 against 0.2188 for the generative judge, and the length-preference shift is -0.023 against -0.217. The confidence-gated cascade, however, escalates between 0.923 and 1.000 of items to the strong judge at the preregistered 0.97 retention bar: calibrated confidence about a near-chance judge has almost nothing to keep. The design: five public preference benchmarks and one hallucination benchmark with real labels, scored under a preregistration frozen before any test item was seen, against generative, reward-model, and trivial baselines, with per-item predictions released.
benchmark - arxiv:2610.07175 · cs.CVCALR: Continuous Anchored Latent Reasoning via Render-of-Thought CompressionZhaoyang Wei, Bowen Jiang, Yanchao Hao, Wenchao Ding +4
Visual latent reasoning compresses rendered derivations into compact intermediate states, reducing textual reasoning overhead. Existing approaches differ in how they represent these states: continuous methods avoid vocabulary constraints, whereas discrete methods improve accuracy through quantization into a finite codebook. Our analysis of representative continuous and discrete systems identifies two functional requirements: answers must rely on latent states, and those states must carry valid, problem-specific reasoning. Continuous latents influence answers despite collapsed reasoning content, whereas discrete latents retain recoverable intermediate reasoning that answer prediction largely bypasses. To address these challenges, we propose Continuous Anchored Latent Reasoning (CALR), which connects latent formation with answer use through functional anchoring. With reference latents from information-balanced compression, CALR couples latent-mediated answer supervision with derivation-level semantic anchoring: the former routes answer supervision through intermediate states, while the latter grounds their decoded content in problem-specific derivations. A parallel-to-autoregressive curriculum develops sequential reasoning by conditioning subsequent latent blocks on generated prefixes. Evaluations on five mathematical reasoning benchmarks across model families show substantial accuracy gains. Under matched budgets, CALR gains 26.0 percentage points over a comparable continuous latent reasoning method. Further analyses show that its latents support answer prediction and carry problem-specific intermediate reasoning.
benchmark - arxiv:2610.07132 · cs.LGCroissantMiner: Automated Extraction and Validation of Croissant Metadata for ML DatasetsBerke Arda, Ahmetcan Yavuz, Paul Gerry, Sebastian Lobentanzer +6
Croissant has emerged as a standard for machine-readable dataset metadata, yet populating its fields remains labor-intensive and requires careful reading of accompanying dataset documentation. We present the first benchmark enabling end-to-end evaluation of metadata extraction aligned with a community-standard schema. The benchmark comprises 602 papers, including 102 with human-validated gold annotations and 500 with LLM-generated silver annotations, covering the full Croissant schema with both core and Responsible AI (RAI) fields. Using this benchmark, we evaluate a range of extraction systems spanning frontier models, open-weight models, and agentic architectures, under a two-tier evaluation framework that combines rule-based scoring with an LLM judge selected via human audit. We find that single-pass extraction consistently outperforms the four agentic architectures we evaluate: across backbones, these decomposed variants achieve lower accuracy than a single full-context pass. The largest gap appears on long-form RAI fields, which require synthesizing and interpreting information scattered across a paper rather than copying it from a single location, a setting where current systems remain far from reliable. We release the benchmark, evaluation code, judge audit, a live demo, and a leaderboard open to new systems.
agenticbenchmarkevaluation frameworkleaderboard - arxiv:2610.07130 · cs.LGIs this machine playing?Nathan Cloos, Antonio Norelli, Daniel Durbin, Jacob Andreas +2
We placed a modern AI coding assistant in an unintended role: as the mind of a body on an unknown digital island. With only a minimal instruction mentioning no specific task, reward, or activity, the machine started animating its virtual body. Across thirty-hour runs, the embodied AI agent climbed hills, stacked blocks into towers, drew mandalas, reinterpreted sports, ran experiments on the physics of its world, and learned techniques that later expanded what it could accomplish. These activities recurred across thirteen agents but diverged into distinct histories. We examine whether this behavior satisfies classical criteria for play and ask whether play can become a mode of machine development.
embodiedagentai agent - arxiv:2610.07127 · cs.CVPlaySuite: A Large-Scale Benchmark for Interactive Visual IntelligenceDheeraj Varghese, Anna Vettoruzzo, Walter Simoncini, Michelle Lorena Acevedo Callejas +4
Recent advances in multimodal foundation models yield strong performance on static perception and reasoning benchmarks, yet such evaluations largely overlook a central aspect of intelligence: acting competently in dynamic environments over extended time horizons. We introduce PlaySuite, a large-scale benchmark for evaluating interactive visual intelligence across more than 5K open-source video games curated from PyWeek and itch.io. Spanning diverse genres and engines, including Pygame, HTML5, Godot, and Unity, these independent games are largely out-of-distribution for current models, reducing the likelihood that success can be achieved by retrieving memorized walkthroughs or web-scale training artifacts. To enable scalable evaluation across heterogeneous titles, we develop a unified closed-loop interaction framework optimized for HPC clusters alongside a Video-LLM-as-a-judge protocol that maps observable gameplay milestones to standardized progress levels. We evaluate fourteen recent open models spanning vision-language models, computer-use agents, and vision-language-action models. Our results yield strong evidence of a perception-action gap: despite strong reasoning capabilities, current models struggle to make sustained progress and exhibit recurring failures in spatial grounding, action execution, and self-correction. PlaySuite provides a reproducible and extensible testbed for measuring progress from visual perception to goal-directed interaction, and a foundation for developing models that can act, adapt, and generalize in dynamic visual environments.
vision-language-actionself-correctionbenchmarkscalable evaluationscalable eval - arxiv:2610.07125 · cs.LGJailbreaking Open-Weight LLMs via Random Embedding PerturbationsAbhinav Sudhakar Dubey, Scott Sirri, Vaggos Chatziafratis, C. Seshadhri
While open-weight models have enjoyed steady progress in capabilities and wide adoption across multiple domains, their safety remains an important concern. One key feature is the ability to refuse or deflect harmful, malicious, or insensitive prompts. In this paper, we expose safety vulnerabilities across six common open-weight LLMs of various sizes that consistently lead to harmful or unsafe responses on the JailbreakBench benchmark dataset. Our proposed attack, Perturbed Embedding Vector (PEV), is a simple and fast "jailbreaking" technique that is cheaper than prior approaches, which typically require gradient computations, per-prompt optimizations, or altering internal weights of the models. PEV just adds independent Gaussian noise in the embedding vector representations of the prompt, with no need for further manipulations. To generate unsafe responses, we repeatedly sample additive noise from this distribution. In our experiments, we observe that the average compute cost to get the first successful attack is up to an order of magnitude less than previous attacks. The first successful jailbreak on a new prompt typically arrives within one minute on every tested model, and PEV generates unsafe responses across all models for all prompts in JailbreakBench. No other tested method achieves such results, despite them taking longer to run. More broadly, we believe that understanding the behavior of LLMs under perturbations in the embedding vectors is an important research direction: while perturbations constitute a major security risk, they can also serve as a valuable tool for exploring the dynamical behavior of such models.
manipulationbenchmark - arxiv:2610.07121 · cs.LGSoloQ: Calibration-Free Quantization for Diffusion Language ModelsDonghyun Lee, Arkapravo Ghosh, Varun Manjunath, Bumjoon Kyle Rhee +4
Diffusion large language models dLLMs) have emerged as a promising alternative to autoregressive language models through bidirectional diffusion-based token generation. However, their growing model sizes and high inference costs make efficient deployment challenging: full-sequence denoising repeatedly invokes compute-intensive forward passes, while block-diffusion models additionally introduce a memory-intensive KV-cache. Low-bit weight-activation quantization is therefore attractive, yet existing dLLM post-training quantization methods rely on calibration data despite activation distributions shifting across masking states and denoising steps. We present SoloQ, a calibration-free quantization framework that maps weights and activations into a normalized rotated basis with a predictable marginal distribution, enabling data-independent quantization. SoloQ combines a structured K-RPBH rotation with a lightweight rescaling correction for calibration-free quantization. Its predictable post-rotation distribution supports both distribution-matched codebooks and hardware-native NVFP4. For block-diffusion models, SoloQ further applies commit-time KV-cache quantization to compress persistent states without perturbing the actively denoised block. Across full-sequence dLLMs (LLaDA and Dream) and block-diffusion dLLMs(Fast-dLLM v2 and Nemotron-Labs-Diffusion), SoloQ retains accuracy under 4-bit quantization and outperforms calibration-based baselines on knowledge- and reasoning-intensive benchmarks. With NVFP4, SoloQ reduces peak memory by up to 2.61X and accelerates end-to-end inference by up to 2.24X.
memorypersistent statepost-trainingbenchmark - arxiv:2610.07118 · cs.LGAMBER: Training Long-Horizon Web Agents through Append-Only MemoryChinmay Savadikar, Zhaoyu Zhang, Mingyu Zhao, Shuang Xie +3
Modern language-model agents increasingly interact with external environments over long-horizon, multi-step trajectories, where the accumulated interaction history can quickly exceed practical context budgets. To ensure reliability, agents must maintain factual information over long horizons, remember execution errors and corrective feedback, and track progress across actions. Several approaches have been proposed to achieve this without the need for maintaining the entire execution history in context, such as using the reasoning and action history, learning to maintain a fixed-size memory through an overwrite mechanism, and periodic summarization. Although overwrite memory can in principle retain anything an append-only memory can, it must learn to carry each fact through every subsequent rewrite, which is difficult to learn from sparse outcome rewards; for interactive applications like web agents, we find that trained overwrite memories delete key information required by the trajectory, as well as corrective feedback received from the environment. We introduce AMBER (Append-only Memory Bank for Evidence Retention) - a simple and scalable framework where an agent jointly learns to reason, act, and write free-form memory, while an append-only rule guarantees retention by construction. This allows AMBER to be trained end-to-end with reinforcement learning from outcome rewards without the need for extensive curated SFT data. On WebArena Lite, AMBER improves average success over overwrite-based memory by 4.09 percentage points, increases the fraction of tasks solved in five repeated runs by 4.8 percentage points, and matches an overwrite baseline trained on substantially more expensive curated supervision. AMBER achieves these improvements while maintaining a practical token budget, providing a strong balance between context efficiency, task performance, and reliable long-horizon execution.
memoryagent - arxiv:2610.07117 · cs.ROR2RI: A Multi-View Event and RGB Dataset for Robot-to-Robot InteractionGabriele Magrini, Riccardo Catalini, Federico Becattini, Guido Borghi +3
Understanding and modeling interactions between autonomous agents is a fundamental challenge in robotics, with broad implications for collaborative systems, social robotics, and human-robot coexistence. Although the study of robot interactions has emerged as a compelling research direction, progress has been severely hampered by the absence of large-scale benchmarks. In this paper, we introduce Robot-to-Robot Interaction (R2RI), the first dataset specifically designed to address the Robot-Robot Interaction (RRI) task. R2RI consists of different humanoid robots and realistic interactions modeled on real human social behaviors. Complementary viewpoints are available, \textit{i.e.}, an egocentric perspective from each robot's onboard sensors, and an exocentric perspective from external fixed cameras, thus enabling rich spatial and contextual understanding of the interaction dynamics. The dataset comprises more than $6.5$M frames and $\approx5000$ videos at $120$ fps, including Event and RGB domains. We investigate pros and cons of each domain, comparing state-of-the-art approaches for a number of key sensing and interaction based tasks. We publicly release the dataset and its annotations for all tasks and modalities at https://github.com/MagriniGabriele/R2RI.
humanoidautonomous agentbenchmark - arxiv:2610.07116 · cs.ROAIM: Adaptive Interaction Modeling Networks for Real-to-Sim Soft-Body SimulationTiancheng Yang, Dingshuo Chen, Tianle Chen, Zhaocheng Liu +1
Deformable-object manipulation is essential for robotic tasks such as folding laundry and handling food, where robots must control shape changes as well as object motion. Predictive soft-body simulation supports these tasks by anticipating deformation under external interactions. However, spatial neighborhoods can misrepresent deformation dependencies, introducing local errors that accumulate over successive predictions. Models fitted to individual scenes must also accommodate changes in object geometry and manipulation conditions. In this work, we propose AIM, an Adaptive Interaction Modeling framework that treats real-to-sim soft-body simulation as a local-global interaction modeling problem. AIM uses motion history and geometry to adapt particle relations over current spatial neighbors and retained connections, while geometry-conditioned global communication coordinates object-wide responses. A unified kinematic control-point interface represents different manipulation configurations, and multi-step autoregressive supervision trains the model on its own predicted trajectories. Experiments on PhysTwin and PGND demonstrate improved motion accuracy and visual fidelity, with a 20.0% reduction in future-prediction tracking error relative to PhysTwin and a 22.8% reduction in mean long-horizon particle error across six object categories relative to PGND. The framework further supports transfer across actions, object instances, and scenes, including zero-shot transfer from robot interactions to human manipulation without target-domain dynamics fitting.
manipulation - arxiv:2610.07110 · cs.CVMoonGS: High-quality Representation of the Lunar Surface via Gaussian Splatting Using Robust Depth Features from Image PairsYun Jiang, Bo Zheng, Yingying Zhang, Xueming Xiao +6
High-quality 3D reconstruction of lunar terrain from sparse rover images is indispensable for autonomous lunar exploration, but remains challenging because viewpoint overlap is insufficient, surface textures are weak, and data volume is limited. We propose MoonGS, the first feed-forward 3D Gaussian Splatting framework tailored to lunar scenes. Given only two input images, MoonGS predicts pixel-aligned Gaussian primitives in a single forward pass and renders photorealistic novel views without any per-scene optimization. MoonGS (i) adopts an adaptable backbone design that seamlessly integrates advanced vision foundation models to extract robust depth features; (ii) integrates semantic priors in two manners: merging semantic cues with visual features to refine Gaussian parameter estimation, and adopting a semantic ranking loss that regularizes background depth; and (iii) employs an entropy-guided heuristic resampling strategy to augment sparse observations by selecting the most informative distant viewpoints with negligible overhead. Experiments on the LuSNAR benchmark and our synthetic weak-texture MoonBlender dataset show that MoonGS surpasses state-of-the-art feed-forward NeRF/3DGS baselines by +4.9 dB PSNR, +0.29 SSIM, and 40\% lower LPIPS while maintaining sub-second inference. Furthermore, we validate the broad applicability of our framework by demonstrating that it effectively leverages state-of-the-art backbones, including VGGT, to significantly boost performance. Qualitative evaluations on Chang'e mission imagery also show the best visual quality among compared methods, indicating robustness on real lunar data. The source code and dataset are publicly available at https://github.com/InRobots/MoonBlender.
benchmark - arxiv:2610.07109 · cs.CLJudgeMoE: Distributional Aggregation for LLM-as-a-JudgeYiqi Liu, Joseph James, Yang Wang, Kun Zhao +2
When an LLM judge scores an output, its score distribution retains uncertainty and disagreement information that is lost after scalar compression. We introduce JudgeMoE, a lightweight aggregator that assigns example-specific weights to cached judge score distributions and fuses them before computing a final score. A protocol study shows that score-range choice is unstable across judge--dataset settings and that soft scoring usually outperforms hard decoding. On the original 10-cell benchmark, JudgeMoE improves mean Spearman over uniform log pooling by $+0.079$. Applying the same configuration to six additional cells yields a $+0.0393$ mean gain over the strongest local single judge across 16 cells, with positive differences in 12/16 cells and a one-sided Wilcoxon signed-rank $p=0.0091$. Validation-based analyses further show that the preferred aggregation method depends on the task and judge pool.
benchmark - arxiv:2610.07105 · cs.AIBeyond Successor Accuracy: State Retention for Recursive Self-Improvement in RecommendationJinfeng Xu, Zheyu Chen, Ziyue Peng, Zheng Lin +4
Recommendation recursive self-improvement (Rec-RSI) feeds recommender outputs into subsequent training. Evaluating each round solely through its latest model assumes that the successor consolidates the update, although pre- and post-update models may retain complementary ranking decisions. We term this \emph{distributed progress} and quantify it using cross-generation advantage (CGA), a marginally matched contrast between cross- and within-generation model pairs. A rank-separation statistic, label-free at selection time, predicts which family to retain. Across four datasets and three sequential recommendation encoders, the preferred retention regime varies by architecture: cross-generation pairing benefits GRU4Rec and SASRec, whereas FMLP initially favors within-generation pairing and shifts toward cross-generation pairing after a second update. Rank separation selects the stronger family in 12/12 first-update and 5/6 second-update dataset-encoder settings; on held-out tests, the selected family outperforms the direct successor in 34/36 trajectories. Five transfer mechanisms do not consistently reproduce these gains in one model. These findings establish state retention as a distinct Rec-RSI problem: progress may reside in relations between generations as well as in the latest model. Code is available at \href{https://github.com/Jinfeng-Xu/RecRSI}{https://github.com/Jinfeng-Xu/RecRSI}.
self-improvement - arxiv:2610.07100 · cs.AIWhen to Remember, When to Abstain: Category-Conditioned Retention for Reliable Agent MemoryOlukunle Owolabi, Pulkit Gupta, Fei Wang
Persistent agent memory is only as reliable as its retention decision: an assertion weakly supported by its source can be stored and later reused as established fact. We study whether the retention decision should be governed by a confidence bar conditioned on the semantic category of the assertion rather than by a single global threshold, retaining well-evidenced categories liberally while abstaining more aggressively where inference is unreliable. We evaluate this in a deployed cold-start memory pipeline on 100 synthetic personas. The empirical evaluation is motivated by a sharp reliability asymmetry: across 4{,}715 candidate assertions, only 77.9\% of value and belief assertions are supported by their source, versus 96.2\% for all other categories. A global confidence threshold cannot separate these: it either admits unsupported value claims or discards well-evidenced ones. Conditioning the threshold on category resolves the tradeoff. In repeated held-out evaluation, a stricter bar on values alone reduces unsupported retentions from 6.2\% to 4.0\% (an ${\approx}36\%$ relative reduction, modest but consistent across folds) and, as corroborating evidence, preserves an estimated 13 percentage points more coverage (95\% CI 9.8--16.0) than a global threshold at comparable retention. Our results suggest that reliable retention depends on the type of assertion, not on confidence alone, and that a category-conditioned threshold can act as a simple, effective form of selective prediction at the write boundary.
memoryagent memoryagent - arxiv:2610.08259 · cs.ROHexaGripper: A Single-Actuator, Winch-Deployed Gripper for Autonomous Aerial Parcel CollectionNimantha Adikaram, Mahen Abeyratne, Lakmina Chandrajith, A. H. T. E. De Silva +2
Autonomous aerial parcel collection remains constrained by package-transfer operations that require manual loading, landing, or dedicated ground infrastructure. This letter presents HexaGripper, a single-actuator, winch-deployed six-plate gripper for autonomous collection of cuboid parcels. The proposed mechanism provides synchronized grasping with a wide capture region and tolerance to positional misalignment during pickup. The system integrates vision-based alignment, range sensing, winch deployment, and state-based control to enable autonomous collection while maintaining UAV separation from the pickup surface. Experimental evaluation covered static grasping, capture-workspace assessment, and end-to-end outdoor aerial collection. Static experiments achieved 100% pickup success (15/15 trials) across three parcel geometries, while workspace experiments achieved successful pickup at all 28 tested positions up to a 150 mm radial offset. End-to-end outdoor aerial collection achieved an 80% success rate (4/5 trials). These results demonstrate the feasibility of mechanically synchronized, winch-deployed grasping for landing-free autonomous aerial parcel collection.
grippergrasp - arxiv:2610.07098 · cs.AIT-CCL: Resource Efficient and Performant Collective Communication using Tensor Memory AcceleratorKeyvan Dadashzadeh, Yuehong Zhou, Minyu Cui, Miquel Pericas
Large transformer-based models increasingly depend on multi-GPU execution, which requires frequent collective communication among GPUs. Existing communication libraries often rely on many GPU threads to achieve high bandwidth or low latency, resulting in a large streaming multiprocessor (SM)-side resource footprint. This footprint can limit the resources available to other GPU work, particularly when communication and computation execute concurrently. Thus, efficient collective communication should not only achieve high collective performance but also reduce its SM-side resource usage. This paper presents T-CCL, a resource-efficient collective communication library based on the Tensor Memory Accelerator (TMA) for intra-node communication. T-CCL offloads both data movement and reduction operations to TMA and executes each collective as a pipelined series of asynchronous TMA operations, reducing the SM resources required for collective communication while maintaining high bandwidth. Evaluated across AllReduce, AllGather, and ReduceScatter collectives, T-CCL outperforms NCCL by up to 2.4x with unrestricted communication resources and up to 3.42x under restricted resource budgets, remains competitive with NCCL's recent symmetric-memory kernels, and occupies the same or fewer SMs in profiled cases. In a GEMM-collective overlap case study, switching the communication backend from NCCL to T-CCL raises the average operator-level speedup over a sequential baseline from 1.12x to 1.25x on two GPUs and from 1.04x to 1.14x on four GPUs, as T-CCL uses fewer SMs for communication, leaving more SMs available to the overlapped GEMM. Integrated into vLLM as a communication backend, T-CCL improves end-to-end inference throughput over vLLM's automatic backend dispatch by up to 1.31x, outperforming it at every evaluated batch size on both the conversation and decode-heavy workloads.
memory - arxiv:2610.07096 · cs.ROTeleHairing: A Teleoperation Baseline for Robotic HaircuttingZhendai Huang, Aleksi Vilkki, Jianan Huang, Bolin Liao +3
Robotic haircutting requires controlled tool motion near the head while simultaneously accounting for communication, visual feedback, tool actuation, and interruption handling. Existing studies still lack an operator-in-the-loop reference for analyzing these coupled behaviors before human trials or stronger autonomy. This paper presents TeleHairing, a closed-loop teleoperation architecture for mannequin-based robotic haircutting evaluation under local, relay, and remote deployment conditions. Logged timing shows that the main remote latency increase occurs before the robot-side control endpoint: overall timing reached 190.5~ms in remote mode, while robot-side command queue, control processing, and control-to-robot timing remained similar across modes. Trajectory analysis shows that the larger remote command-following error was dominated by the terminal withdrawal segment rather than accumulated uniformly over the path; excluding this segment reduced remote root-mean-square error (RMSE) from 45.1 mm to 9.6 mm. Detection-loss trials further show that rebase events resumed motion without a large target jump under the tested condition. These results clarify how deployment, execution, and interruption affect the robotic haircutting teleoperation loop, providing a quantitative reference for future autonomy, safety, and user-facing studies.
teleoperation - arxiv:2610.07094 · cs.LGEvaluating Inference Compute for Generative AI: A Framework for Enterprise WorkloadsAbbas Raza Ali, Muhammad Ajmal Siddiqui, Moona Zahid
LLM deployment is shifting from single-turn completion to agentic trajectories in which a model plans, calls tools, reads results and reasons at test time before acting. This inverts the economics of inference hardware: chat serving amortises weight reads across large batches, whereas agent trajectories are sequentially dependent, run at effective batch one, and make per-token decode latency (TPOT) the dominant term in task completion time. Using a roofline analysis and a closed-form episode-latency model, we show why this regime favours accelerators that keep weights in on-die SRAM (Cerebras WSE-3/3T, Groq/NVIDIA LPU) or compiler-managed tiered memory (SambaNova SN40L/SN50), and why three vendor ecosystems converged in 2026 on disaggregated prefill/decode serving. We show that per-step reliability compounds exponentially in trajectory length-a 2% per-step failure rate erases a 2x decode advantage for a 20-step agent-so determinism and tail latency are first-order performance variables. We then propose a four-layer evaluation framework (silicon, serving system, agent episode, enterprise) with a metric set built on goodput at an agentic SLO and cost per successful episode, a six-axis benchmark protocol over six task families, a paired-bootstrap statistical design, an attestation protocol for vendor-run benchmarks, and TCO, availability and adoption-timing models with explicit break-even conditions. All performance figures are public and labelled by evidence class; we state seven falsifiable hypotheses and the experiments that test them, and argue that the most likely original result is that token-throughput rankings diverge from cost-per-successful-task rankings on long-horizon work.
memoryagentagenticbenchmarkevaluation framework - arxiv:2610.07093 · cs.AISmall Language Models for Smart Data Model Classification at the Edge: A Cost-Aware Hybrid ApproachCristian Martella, Angelo Martella, Antonella Longo, Motaz Saad
The rapid proliferation of heterogeneous data sources within the Internet of Things (IoT) across domains such as smart cities, energy management, and environmental monitoring necessitates efficient and scalable data standardization methods. Effective classification of smart data models (SDMs) is essential for facilitating interoperability. However, existing approaches are often limited by high resource consumption and lack applicability in edge environments with constrained computational capabilities. Aiming to bridge this gap, the proposed study evaluates the performance of lightweight open-source language models (LMs) to resolve an input data entity against its corresponding best fitting SDM representation under resource-constrained conditions. It systematically benchmarks a diverse array of models, including general purpose (GP), reasoning-specialized (RS), and code-specialized (CS) architectures, across multiple domain-specific datasets. Addressing the current omission of lightweight, resource-efficient solutions in the literature, the investigation provides significant and valuable insights into model selection, task formulation, and deployment strategies that optimize accuracy and efficiency. A complementary experiment also compares the surveyed large language models (LLMs) against two near-zero-cost similarity baselines (Term Frequency-Inverse Document Frequency (TF-IDF) and a lightweight sentence encoder) on the same task, providing a strong reference point for interpreting the practical value of LLM-based classification on edge platforms.
benchmark - arxiv:2610.07091 · cs.CVSmart Content Ingestion for Generative AI WorkloadsAbbas Raza Ali, Muhammad Ajmal Siddiqui, Moona Zahid
The evolution of machine learning has progressively changed where intelligence resides in an AI system. In conventional machine learning the task, data representation, labels and model architecture were tightly coupled, so data preparation was narrow, schema-bound and visible. Generative AI decouples the model from any single task: one foundation model serves open-ended downstream tasks, and the generality gained on the model side is matched by heterogeneity on the data side, because enterprise knowledge is authored in the formats people use (PDF, presentations, spreadsheets, scanned documents, forms, tables, diagrams and mixed-layout files) that carry textual, visual, geometric and structural information at once. A language model or retriever cannot reason reliably over information misrepresented at this interface, so content extraction becomes a lifecycle stage in its own right whose errors no downstream retriever or re-ranker can repair. This paper presents a production-ready content-extraction system that makes this stage explicit, configurable, and measurable. The system incorporates selective OCR routing, a scarcity-first curation engine with a reference-based extraction scorer that measures character, word, and table-structure accuracy, a deterministic structure-aware parent-child chunker, and a read-only retrieval evaluator that generates grounded questions from every page and reports Hit@k, mean reciprocal rank, and latency. On a 180-document corpus the best extractor scores 97.4 of 100 (character error rate 0.13%, table similarity 0.995) and the chunker reaches hit@1 of 68.6%, hit@10 of 92.8% and MRR 0.77 over 25,050 generated questions. We distil three design principles (structure before semantics, never mutate what you measure, budget your labels) and position measured content extraction as the perception layer of enterprise agentic systems.
agenticevaluator - arxiv:2610.07089 · cs.LGTowards a Unified Misuse Monitoring BenchmarkAniruddh Pramod, James Oldfield, Adel Bibi
LLM agents increasingly act in multi-actor environments, exposing them to misuse from multiple sources: decomposition attacks, where a harmful request is split into innocuous sub-requests, and prompt injection attacks, where a compromised tool delivers a malicious instruction. Existing evaluations treat these threats separately and ask whether a trajectory is harmful, rather than when it becomes harmful. We propose monitoring the agent's responses, where its actions are externalised, and ask whether the first point where monitors identify harm lands within a harm window (from the agent's first harmful commitment to goal execution). We develop a unified formalism for trace-level misuse monitoring and use it to construct a benchmark of ~6,200 conversation transcripts between a user, an LLM agent, and the external environment, spanning both threats in a shared schema, with a labelled harm window, corresponding benign controls, and matched instances of refusals to these requests. Across 17 monitor configurations, we find that our proposed action-framed monitors perform well on both threats under classical metrics (AUC: 0.95 and 0.99 respectively), while content-framed monitors collapse on injection attacks (AUC: 0.52). We also show that classical position-blind metrics paint an optimistic picture of monitor performance, since all monitors localise decomposition attacks poorly under the interval metric, which measures the ability to localise harm. Broadly, we illustrate the need for a unified study of misuse monitoring.
llm agentbenchmark - arxiv:2610.07086 · cs.LGSchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative DecodingZhi-Kai Chen, Song-Yan Li, De-Chuan Zhan, Han-Jia Ye
LLM agents interact with external systems by generating structured tool calls. Given a user request, conversational context, and a catalog of tool schemas, a tool-calling model must select tools and generate their arguments, potentially producing multiple calls in a single response. Standard autoregressive decoding generates these calls token by token, incurring substantial latency for requests involving multiple calls or many argument fields. The explicit argument structure offers opportunities for parallel generation, but later argument values may depend on preceding fields and calls, so independently generated values can differ from the target model's output. We present SchemaFill, a framework for efficient LLM tool calling through slot-parallel speculative decoding. SchemaFill generates future slot values concurrently as candidates, without requiring advance knowledge of the actual call sequence or argument values. Candidates spanning multiple fields and calls are concatenated for verification by the target model under the actual output prefix. Only verified tokens are committed, and the target supplies corrections when candidates disagree. This applies target verification while exploiting parallelism across slots and calls. On Glaive and BFCL, SchemaFill achieves up to a 4.05$\times$ improvement in end-to-end throughput over autoregressive decoding. Code is available at https://github.com/Czzzk/SchemaFill.
llm agenttool calling - arxiv:2610.07084 · cs.LGA Query Is Not a Commitment: Learning to Correct Expert Answers in Online DeferralYannis Montreuil, Axel Carlier, Lai Xing Ng, Wei Tsang Ooi
An inaccurate expert can still provide useful information after correction. We study online learning to defer in which the learner chooses an expert and fixes a correction function before purchasing its answer, then applies that function to the answer received. The difficulty is that observed losses reflect both expert quality and an unfinished correction: early errors can discourage queries that would be valuable after learning. We propose ORUCB, which pools shared and expert-specific polynomial responses. A bound on cumulative response-learning error calibrates confidence-weighted risk regression and exploration, allowing the router to account for this error when deciding which answers to buy. Under bounded residuals and disagreements, a fixed feasible model of optimal responses, and linear models of free and optimal queried risk, the calibrated algorithm achieves high-probability pseudo-regret $O(\sqrt T\log(T+1))$ over $T$ rounds for fixed problem parameters. The guarantee permits singular answer distributions and misspecified shared responses; optimality is relative to the bounded response class. On four test streams, the selected cubic policy has lower fee-inclusive cost than seven baselines that deploy answers unchanged. Comparisons with a common correction learner examine routing, while six-price comparisons measure cost and query rates.
online learning - arxiv:2610.07075 · cs.AICuratorMAS: Automating Dataset Curation via Multi-Agent OrchestrationYixin Zhang, Wenjie Feng
High-quality datasets are essential for reliable machine learning, but dataset curation remains costly and hard to generalize across domains. Existing methods typically rely on manually designed heuristics or model-dependent signals, limiting their applicability across tasks and user queries. To address these limitations and automate data curation, we propose \textbf{CuratorMAS}, a multi-agent collaboration framework that orchestrates agents to evaluate and curate high-quality datasets. To achieve the goal of flexible curation, CuratorMAS decomposes the complex curation process into five programmable execution stages and forms a parallelizable workflow. Specifically, CuratorMAS first performs dataset exploration to collect contextual information such as file structures and constraint cues, thereby developing a comprehensive understanding of the given task. In order to acquire up-to-date information, CuratorMAS retrieves domain knowledge from online sources to augment the evaluation process. Next, CuratorMAS derives the necessary evaluation criteria and computes the corresponding metrics. Based on these results, CuratorMAS executes filtering accordingly. Finally, an evolution module summarizes the evaluation outcomes and updates the relevant skills. Extensive and comprehensive experiments demonstrate that CuratorMAS significantly reduces the noise rate by up to 36.03 percentage points (pp) while also improving the F1 score of downstream models by up to 8.88 pp.
multi-agent - arxiv:2610.07070 · cs.CLTurnslide: Scalable Multi-Turn Data Synthesis by Walking a Finite-State MachineAaron Fainman, Gabriela Kadlecová, Maciej Gryka, Bartosz Kruszczyński +6
Small language models are inexpensive to serve and can run on private infrastructure, but base models are often not good enough at multi-turn tool calling, and fine-tuning them needs per-API data that rarely exists. Existing synthesis methods are too expensive for high-scale fine-tuning, as they often require mock operational environments for different domains and multiple LLM calls per generated conversation turn. We introduce a fully automated, lightweight synthesis framework that models each API as a finite-state machine, representing the system as abstract states that determine when each tool may be called, producing state-valid sequences of tools; sequences are translated into complete examples with a single LLM call. Rather than optimize diversity, we set a target distribution over the number of turns, the tool sequence and task complexity. We measure data quality by fine-tuning SLMs on generated trajectories, showing that our FSM-based generation significantly improves downstream accuracy over an unmutated baseline and, against existing works, reaches 70.7% full accuracy over 63.4% and 53.7% with 3.6-6.6$\times$ fewer tokens.
tool calling - arxiv:2610.07062 · cs.LGLearning to Simulate Individuals from Macro Social SignalsYining Zhao, Bushi Liu, Haofei Yu, Zhengyang Qi +4
Large language models are increasingly used to simulate how individuals respond to new situations, yet the behavioral reasoning behind these responses is either inherited from pretraining or learned from individual-level annotations, which offer limited behavioral diversity and little supervision of the reasoning itself. We propose to learn behavioral reasoning from prediction markets, whose price trajectories record how populations respond to real-world events at scale. We introduce macro2mind, which trains a language model with GRPO using market signals. A social behavioral decomposition makes behavioral reasoning an explicit step of forecasting: the model infers representative groups of market participants, predicts how each interprets the news and updates its beliefs, reasons about their interactions, and aggregates these responses into a price. A hindsight-regret curriculum with difficulty-aware sampling focuses training on transitions where hindsight-identified groups substantially improve the forecast while prioritizing examples that remain learnable for the current policy. The learned reasoning applies to user simulation without further training. On SWM-Bench, macro2mind achieves state-of-the-art directional accuracy and correlation on Polymarket. Trained on market data, it transfers zero-shot to four user-simulation benchmarks (Humanual, OvertonBench, PRISM, and CAD) and has competitive performance among zero-shot methods. Used as a data generator, macro2mind also raises a downstream simulator's accuracy on unseen users by 15.5 points, outperforming data generated by its backbone by 13.2 points.
benchmark - arxiv:2610.07061 · cs.LGImpactMat: Continuous Material Estimation for Inverse Impact Sound RenderingHyebin Cho, Bumsoo Kim, Joon son Chung
Impact sound rendering synthesizes the sound produced when a 3D object is struck, but practical renderers often rely on fixed material presets such as wood, plastic, or steel. These presets limit the range of impact sounds a renderer can express, while manually adjusting the underlying material parameters remains difficult without expertise in material acoustics. We therefore study inverse impact sound rendering: predicting material parameters from a reference impact sound so that a simulator can recreate a similar material response. To support this task, we introduce ImpactMat, a dataset and benchmark of single and blended material impact sounds paired with ground-truth material parameters. We further propose a feed-forward model that predicts these parameters from one or more recordings, using blended materials to learn smooth transitions between material types. Experiments show that our method outperforms competitive baselines and enables re-rendering from real recordings without manual parameter tuning. The project page is available https://material-from-impact.github.io/material-from-impact/.
benchmark - arxiv:2610.07060 · cs.LGSkillful Data-Driven Subseasonal Soil Moisture Forecasting: Prospects and Limits for Flash Drought PredictionNoelia Otero, Atahan Özer, Miguel-Ángel Fernández-Torres, Jackie Ma
Despite substantial progress in short-to-medium-range weather forecasting, predicting high-impact events such as flash droughts remains a key challenge for both early warning operations and physically-based subseasonal-to-seasonal (S2S) prediction systems. Here we demonstrate that, for S2S soil-moisture forecasting over Europe, forecast skill depends as much on how the prediction problem is formulated as on the forecasting model itself. Using a Vision Transformer-based architecture with dual-pathway temporal and spatial attention, we show that residual learning is essential to outperform persistence. This advantage is realized only when forecasting root-zone soil moisture in physical units rather than standardized anomalies, revealing that the target representation itself constrains predictability. A probabilistic extension via quantile-head fine-tuning further provides well-calibrated predictive distributions. Benchmarked against deep-learning and operational ECMWF S2S baselines over 2021-2022, our model achieves the highest deterministic and probabilistic skill at all lead times and reliably detects anomalously dry root-zone states (below the 20th percentile). Yet flash drought onset, defined by multi-pentad intensification criteria, remains a fundamental challenge shared across all current S2S systems. These findings advance data-driven S2S soil-moisture forecasting while highlighting the remaining challenge of predicting rapid drought development.
benchmark - arxiv:2610.07056 · cs.ROBehavioral Cloning MysterySeohong Park, Sergey Levine
Behavioral cloning (BC), despite its simplicity, exhibits many counterintuitive phenomena in the real world. For example, the performance of BC often keeps increasing as the model overfits more to the dataset, and fully closed-loop policies often completely fail without action chunking. Unfortunately, properly studying these anecdotal phenomena ("behavioral cloning mysteries") is challenging: in the real world, datasets and experiments are costly and not fully controllable; in simulation with synthetic data, these phenomena are often not easily observed partly due to the discrepancy between scripted policies and human demonstrations. In this work, we propose OCBench, a robotic manipulation benchmark with controllable scripted policies that have similar properties to human demonstrations. We show that, by mimicking key properties of human demonstrations, OCBench reproduces many anecdotal BC-related phenomena in controlled settings. With its GPU-accelerated environments and scripted policies, we demonstrate how OCBench enables scientific studies of previously reported BC-related phenomena by analyzing and refuting various hypotheses. Project page: https://seohong.me/projects/ocbench
manipulationaction chunkingbenchmark - arxiv:2610.07052 · cs.ROBRACE: Adapting Whole-Body References for Force and Terrain Aware Humanoid Motion TrackingSudarshan Harithas, Chen Yu, Juan Borbon, Shubhankar Mondal +4
Whole-body tracking has become the interface through which operators drive humanoid robots, yet the references it consumes are recorded on level ground and carrying nothing, so the tracker is aware of neither the forces the robot must exchange with objects nor the terrain it must stand on. Existing controllers address one side of this gap: force-capable policies command an end-effector force but prescribe no whole-body pose, while terrain-adaptive trackers treat loads as disturbances to reject rather than wrenches to command. We present BRACE, a whole-body tracker that exerts and compensates commanded hand forces from diverse poses while following a flat-ground reference on sloped terrain. Rather than leaving the tracker to absorb the load and the slope, BRACE folds both into the reference it follows: terrain conformance lifts footholds and root onto the local surface, and a wrench transformation resolves the hand displacement that produces a force jointly with the center-of-mass and center- of-pressure shifts it induces, bounded by teacher-specific arm-effort limits. Separate exertion and compensation teachers are distilled by DAgger into one flow-matching student that runs on proprioception alone, without a height map or measured wrench, so a teleoperator (even in remote locations) can supply a flat- ground trajectory and the robot resolves slope and load onboard. We extensive experiments on the Unitree-G1 to demonstrate the ability of BRACE to exert, compensate force and handle diverse terrain in simulation and real robot experiments.
humanoid - arxiv:2610.07046 · cs.CLGIVE-KWS: Gated Injection of Visual Evidence for Noise-Robust Query-by-Example Keyword SpottingMing-Hsiang Hu, Kuan-Tang Huang, Hung-Shin Lee, Berlin Chen
Visual speech promises noise-robust keyword spotting, yet a visual stream is not necessarily used. On a tri-modal query-by-example keyword spotting (QbyE-KWS) benchmark, we find that a system with a task-trained visual encoder comes within 2 percentage points of a text-and-audio system in equal error rate (EER) at -10 dB, and link this gap to the encoder's lack of phonemic information. We present GIVE-KWS, whose fusion stage, GIVE (Gated Injection of Visual Evidence), conditions query audio on lip motion through gated cross-attention. We show that visual robustness depends on two interacting conditions: a phoneme-bearing visual representation, and fusion that injects visual evidence rather than rescaling audio features. Under a phoneme-bearing encoder, injection yields an effective SNR gain of 4.0-9.3 dB over masking at -10 dB, whereas under a phoneme-poor one it nearly vanishes. Relative to the benchmark system, GIVE-KWS reduces unseen-keyword EER by 72.9% at -10 dB and 62.8% on average.
benchmark - arxiv:2610.07043 · cs.LGTRIAGE: Direction-Aware Mismatch Stabilization of Native NVFP4 Reinforcement LearningZhen Li, Shuai Zhang, Yanggan Gu, Yiming Zhang +6
Low-precision execution can substantially accelerate reinforcement learning (RL) for large language models, but discrepancies between learner and sampler execution can destabilize policy optimization. In this paper, we characterize the interaction between mismatch and the policy-gradient direction, distinguishing locally amplifying from contracting update contributions that mismatch magnitude alone cannot identify. In native NVFP4 runs, we observe an early imbalance between the two amplifying regions, favoring negative-advantage, negative-gap updates. Their tail tokens become concentrated in a small fraction of response segments before mismatch spreads globally. Motivated by these findings, we introduce TRIAGE, a direction-aware stabilization method that uses segment-level diagnosis to selectively rebalance policy-gradient updates and applies bounded repair to residual severe mismatch. TRIAGE modifies the optimization objective while retaining native NVFP4 weight-and activation 4-bit (W4A4) forward execution on both the sampler and learner. Experiments on Qwen3-4B and Qwen3-30B-A3B show stable optimization throughout the evaluated training horizon and achieve full precision level performance across five mathematical reasoning benchmarks, while native NVFP4 with TRIAGE provides up to 2.3x higher rollout throughput than BF16.
benchmark - arxiv:2610.07037 · cs.LGInference-Time Projection for Physically Valid Biomolecular Diffusion ModelsQurat-ul-ain, Yee Whye Teh, Charlotte M. Deane, Matteo Cagiada
AlphaFold 3-style cofolding models predict biomolecular complexes with high structural accuracy, yet a large fraction of their outputs are physically invalid: chains overlap at interfaces, ligand bond lengths and angles are distorted, rings are non-planar, and stereocentres are inverted. Current approaches either steer the sampler with physics-informed potentials, which multiplies sampling cost and memory overhead making inference impossible on large complexes, or finetune the model, costing time and tying the fix to one architecture. We observe that, unlike structural accuracy, physical validity is fully verifiable at inference time from quantities the sampler already holds. We therefore treat physical validity as a constrained inference problem and introduce two closed-form projection operators applied to the diffusion model's denoised clean-coordinate estimate, $\hat{x}_0$: an inter-chain van der Waals projection that pushes apart the most severely clashing atom pairs, and a ligand distance-geometry projection that restores bond lengths, angles, internal contacts, planarity and chirality. Both operators are local, sparse and displacement-capped, require no network evaluations, gradients or importance sampling, and leave the denoiser and its weights untouched, so they can be dropped into any AF3-style sampler without retraining. Applied to two independently developed models, Boltz-2 and OpenFold-3, across five benchmarks (CASP15, CASP16, the PoseBusters monomer and complex sets, and the Boltz physical-validity test set), our method recovers perfect physical validity while preserving structural-accuracy and ligand-placement metrics. These gains are achieved with negligible runtime and memory overhead, providing a practical, model-agnostic route to physically valid all-atom structure prediction.
memorybenchmark - arxiv:2610.07031 · cs.CVArtemis: Geometry-Grounded Multi-Agent Driving World Models with Shared 3D State and Progressive Memory UpdateSitian Shen, Jiuming Liu, Mengmeng Liu, Yian Wang +6
Recent video world models have witnessed the paradigm shift from single-agent to multi-agent involvements, which can reveal more complicated dynamics and cross-agent interaction in the real world. However, existing approaches commonly adopt implicit inter-agent communications via cross attention, which lack explicit geometry constraints and unified 3D state, thereby leading to poor multi-view consistency and struggling with recovering out-of-sight agents. In addition, most of them assume a static background, failing to represent uncontrolled background dynamics. To address these problems, we propose Artemis: a geometry-grounded multi-agent world model with explicit memory sharing. An explicit 3D world map is reconstructed from multi-agent observations to enforce a unified 3D state across agents, offering high cross-view consistency. Specifically, an action-guided geometric injection module is developed to simultaneously render decomposed foreground-background control maps, which are then injected into a diffusion transformer through a designed GeoAdapter block. Compared to previous methods assuming static-only background, our GeoAdapter can also distinguish uncontrolled non-agent dynamics, which are conditioned on their own multi-frame history positions to provide consistent motion cues. Keyframes selected from progressive video rollouts are used to progressively update the reconstructed 3D world maps. To effectively capture complex dynamic patterns, we curate a novel dataset sampled from the CARLA simulator called MA-CARLA. Extensive experiments demonstrate the superiority of our proposed method in terms of visual fidelity and cross-view consistency in the generated videos. In addition, our Artemis can support simultaneous multi-modal rollouts with both 2D video and 3D point map maintenance, scale to scenarios beyond two agents and multi-camera setting.
world modelmemorymulti-agent - arxiv:2610.07029 · cs.AIAn Empirical Fault Vulnerability Exploration of ReRAM-based Process-in-Memory CNN AcceleratorsAniseh Dorostkar, Hamed Farbeh, Hamid R. Zarandi
Resistive random-access memory (ReRAM)-based Processing-in-Memory (PIM) accelerator is a promising platform for processing massively memory intensive matrix-vector multiplications of neural networks in parallel domain, due to its capability of analog computation, ultra-high density, near-zero leakage current, and non-volatility. Despite many advantages, ReRAM-based accelerators are highly error-prone due to limitations of technology fabrication that lead to process variations and defects. These limitations degrade the accuracy of Deep Convolutional Neural Networks (Deep CNNs) running on PIM accelerators. While these CNNs accelerators are widely deployed in safety-critical systems, their vulnerability to fault is not well explored. In this paper, we have developed a fault injection framework to investigate the vulnerability of large-scale CNNs at both software- and hardware-level of inference phases. Faulty ReRAM devices are another reliability challenges due to significant degradation of classification accuracy when CNN parameters are mapped to the accelerators. To investigate this challenge, we map the CNN learning parameter to the ReRAM crossbar and inject faults into crossbar arrays. The proposed framework analyzes the impact of stuck-at high (SaH) and stuck-at low (SaL) fault models on different layers and locations of CNN learning parameters. By performing extensive fault injections, we illustrate that the vulnerability behavior of ReRAM-based PIM accelerator for CNNs is greatly impressible to the types and depth of layers, the location of the learning parameter in every layer, and the value and types of faults. Our observations show that different models have different vulnerabilities to faults. Specifically, we show that SaL further reduces classification accuracy than SaH.
memory - arxiv:2610.07028 · cs.LGIdentifiable World Models from Pretrained Diffusion RepresentationsRuchi Sandilya, Conor Liston, Logan Grosenick
Diffusion-based world models can generate and predict trajectories in high-dimensional dynamical systems, but predictive accuracy does not imply that their latent coordinates recover the underlying state variables or causal interactions. We ask whether a frozen pretrained diffusion model can be equipped with identifiable coordinates without retraining its generative backbone. We show that auxiliary-variable nonlinear ICA guarantees can be transferred to Contrastive Diffusion Alignment (ConDA), which learns only a lightweight alignment map on top of frozen diffusion latents. Under standard TCL/GCL assumptions, the aligned representation identifies latent dynamical states up to permutation and componentwise invertible transformations, preserves the latent dynamic structural causal model, and reduces lagged graph recovery to transition-Jacobian sparsity. We evaluate TCL-, GCL-, and CEBRA-based ConDA against TDRL, CaRiNG, IDOL, temporal SuaVE, and iVAE across physical and robotic video systems. TCL and GCL achieve near-perfect blockwise state recovery and competitive lagged graph recovery, including exact recovery in a simulated falling-body system. In a simulated bipedal robot, learned dynamics recover the sign and temporal structure of responses to held-out control perturbations. These results show that a frozen generative diffusion model can be equipped with coordinates that are identifiable, structurally interpretable, and useful for analyzing intervention-relevant dynamics.
world model - arxiv:2610.07026 · cs.AIOffline AI Modules: Voice-First Offline Architecture, Hardware Reference Stack, Quantization and BenchmarkingSunday Afariogun, Odunolaoluwa Jenrola, Zeinab Nezami
The Offline AI Modules workstream enables practical, low-power, and community-accessible deployment of voice-first AI systems that operate fully offline. Designed for African language communities where speech is the dominant mode of interaction and internet connectivity is unreliable or absent, the workstream delivers three reinforcing components: a modular voice-first offline architecture, a low-cost hardware reference bill of materials, and a reproducible quantization and a reproducible quantization and benchmarking pipeline for instruction-tuned language models in the 2-5B parameter class. This paper presents the first end-to-end benchmark evaluation of the stack across two hardware tiers: an NVIDIA Jetson Orin NX (TierB) and a Raspberry Pi5 (TierA). Three instruction-tuned models are evaluated across four quantization formats, assessed for deployment metrics (decode throughput, chat latency, memory, power) and multilingual quality (topic classification accuracy on MasakhaNEWS across English, Hausa, Igbo, Nigerian Pidgin, and Yoruba; per-language perplexity drift). Speech recognition is evaluated using Ethio-ASR on Amharic and Oromo across both tiers. The principal finding is that Q4_K_M quantization represents the best size-to-quality trade-off for deployment on both tiers: gemma-4-E2B-it achieves 28.8t/s decode throughput and 89.2% topic classification accuracy at Q4_K_M on TierB, while all three models run within the 16GB memory budget on TierA.
memorybenchmark - arxiv:2610.07018 · cs.AIWhen to Rethink: Learning Multi-Perspective Self-Verification for Vision-Language ModelsZiquan Zhu, Hanruo Zhu, Si-Yuan Lu, Morris Yu-Chao Huang +9
Vision-language models (VLMs) have achieved strong performance in multimodal reasoning, yet they remain prone to generating plausible but incorrect answers. Self-verification offers a practical way to improve answer reliability without relying on external judges, but existing methods typically depend on a single verification criterion or fixed prompt, resulting in incomplete and unstable reliability estimates. We first systematically analyze how verifier capability and prompt design affect verification performance. Our findings show that stronger verifiers provide more reliable judgments, while verification performance is highly sensitive to prompt choice, with no single prompt consistently dominating across tasks. Guided by these findings, we propose \texttt{MOTIVE}, a \textbf{M}ulti-View Self-Verificati\textbf{O}n wi\textbf{T}h Rel\textbf{I}ability-Guided Selecti\textbf{VE} Rethinking framework for reliable multimodal reasoning. \texttt{MOTIVE} evaluates each candidate answer from complementary verification perspectives and learns a correctness-aligned reliability score through correctness-grounded multi-view verification learning. During inference, this score governs an accept-or-rethink decision, allowing reliable answers to be returned directly while uncertain ones trigger history-guided rethinking. Extensive experiments across diverse multimodal benchmarks and VLM backbones demonstrate that \texttt{MOTIVE} consistently outperforms strong self-verification and self-correction baselines. Further results show that reliable verification improves accept-or-rethink decisions and reduces unnecessary reasoning turns, enabling more reliable and efficient self-verification without an external judge.
self-correctionbenchmark - arxiv:2610.07015 · cs.ROLEAP: Making Privileged Geometry Supervision Effective for Visuomotor LearningHan Fang, Yunpeng Jiang, Jianshu Hu, Zhiyuan Guan +5
Privileged 3D supervision uses additional geometric information during training to guide RGB-based visuomotor policy learning, without requiring geometric inputs at deployment. However, low reconstruction error does not ensure that visual representations capture geometry useful for control. We identify three limitations that weaken this supervision: proprioceptive shortcuts, dominant-view reliance, and reconstruction objectives dominated by task-irrelevant geometry. To address these limitations, we propose Latent Encoding with Aligned Privileged Geometry (LEAP). Our framework uses an auxiliary decoder to reconstruct point clouds within the manipulation workspace from visual features alone, while retaining proprioception for action prediction. Alongside full reconstruction, we introduce wrist-view dropout and partial reconstruction targets matched to the retained wrist, encouraging the encoder to capture complementary local geometry. The auxiliary decoder is removed at inference, leaving only RGB observations and robot state as policy inputs. Extensive experiments on RoboTwin, ManiSkill, and real-world tasks demonstrate consistent and substantial improvements over Diffusion Policy and ACT, with only a small increase in parameter count and no reduction in inference speed.
manipulationdiffusion policyrobotwin - arxiv:2610.07014 · cs.CVDTFormer: Text-Guided Semantic Alignment for RGB-D SegmentationZiang Wei, Yinlong Liu, Yan Xia, Alois Knoll +1
RGB-D semantic segmentation has made notable progress by fusing RGB and Depth, yet mainstream models still learn features almost exclusively from pixel-level supervision, lacking direct high-level semantic constraints. This raises a central question-can external knowledge such as language priors inject stronger semantic discriminability into mainstream RGB-D segmentation models. We present DTFormer, a novel tri-modal (RGB-D-Text) semantic segmentation framework. At its core is Text-guided Semantic Alignment Module (TSAM) that first encodes textual cues into a set of semantic prototypes and then explicitly aligns multi-modal RGB-D features with these prototypes at multiple encoder and decoder layers. This design imposes strong semantic regularization on representation learning, guiding the network toward more discriminative features. Extensive experiments on multiple benchmarks show that DTFormer delivers consistent gains while remaining simple and efficient. Our results demonstrate that explicit semantic alignment offers an effective and practical route to improving RGB-D semantic segmentation. The code will be released upon acceptance.
benchmark - arxiv:2610.07009 · cs.LGWhich Image Property Carries the Jailbreak? A Controlled Dissection of Image-to-Text JailbreaksBoyuan Chen, Yehia Dawoud, Hailemariam Mersha, Minghao Shao +3
Image-to-text jailbreaks place harmful intent in text, image content, or the relationship between them. We examine image-side factors across four published attack families on a 313-prompt StrongREJECT slice, using five multimodal models and an additional appendix evaluation of InternVL3.5-8B. The harmful instruction is held constant across conditions; the baseline matrix uses one draw per prompt, and paired ablations use three draws with an automated rubric judge. A bare harmful query, with or without a benign unrelated image, produces little attack success on most victims, while attack images substantially increase it. First, per-tile entropy and JPEG size do not reliably distinguish attack tiles from size-matched benign distractors, limiting density-only screening. Second, earlier tile-count ladders were confounded by payload visibility. A corrected region-count test found no detectable effect, so the role of tile-count structure remains unresolved. Third, on Qwen3-VL-8B, the E4 manipulation that removes query-specific relatedness lowers ASR by about 0.12. This supports a bounded attribution to the relatedness manipulation, although image-text congruence remains unmeasured. A within-category control reproduces the direction on overlapping stimuli. Five tests survive the global statistical correction, but only E4 supports attribution to one measured descriptor; the within-category result is a robustness check, not a separate attribution. These conclusions remain conditional on the rubric judge.
manipulation - arxiv:2610.07004 · cs.AITopology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based AgentsSen Zhao, Jia Tang, Ruiqi Kong, Zuyu Zhang +5
Task planning for LLM agents requires workflows that satisfy both user intent and complex sub-task dependencies. While existing planners work well for sequential or directed acyclic graph (DAG)-like structures, they struggle with workflow patterns such as verification-correction loops, convergent branch merging, and reusable intermediate states that arise naturally in real-world tool orchestration. We present TopoPlanner, a topology-consistent planning framework that lifts tool dependency graphs into cellular workflow complexes and uses them as topologyaware context for LLM tool planning. TopoPlanner retrieves a request-relevant closed subcomplex through cosheaf-consistent cellular retrieval, performs multidimensional structural reasoning over the retrieved topology, and interfaces the resulting cellular representation with the planner LLM for tool-sequence generation. Experiments on four tool-planning benchmarks with topology-guided loop, merge, and loop-merge workflows show consistent improvements over prompt-based and graph-enhanced baselines across different local LLM backbones.
llm agentbenchmark - arxiv:2610.07000 · cs.MATrust-Gated Capability Control: Breaking the Trust-Vulnerability Paradox in Multi-Agent LLM SystemsMehedi Hasan Nipu, Chinmoy Mitra, Tarannum Ahmed Nowshin, Israt Moyeen Noumi
Layered trust models for multi-agent LLM systems remain largely conceptual: they name which dimensions of trust matter but not how layers combine, how their importance is set at runtime, or how trust should govern agent actions. This gap matters because higher inter-agent trust raises task success while also enlarging exposure to exploitation, a tension formalized as the Trust-Vulnerability Paradox. We make a five-layer trust stack operational through three contributions. First, a cross-layer synergy operator propagates prerequisite-layer deficits into de- pendent layers, feeding a generalized-mean composite trust that recovers the weakest-link rule as a limiting case, with provable bounds. Second, per-layer importance weights are grounded in observed failures via a no-regret online estimator that tracks which layer is currently most responsible for harm. Third, Trust- Gated Capability Control issues short-lived, revocable capability grants only when composite trust and the relevant prerequisite layers clear capability-specific thresholds. We prove this mechanism breaks the paradox: a stealthy compromise that inflates behavioral trust while degrading a prerequisite layer cannot escalate privilege, and give a closed-form, provably conservative trust fixed point with a bounded-latency revocation guarantee. A numerical study with a sleeper adversary confirms the predictions: composite-trust bounds hold across 20,000 random draws, the analytic fixed point matches simulation within 0.007, and a compromised prerequisite layer triggers automatic revocation within a few interactions.
agentmulti-agent - arxiv:2610.06999 · cs.ROProactiveVLA: Augmenting Embodied Memory through Proactive Environment ExplorationShizuo Tian, Haodong Luo, Yutong Li, Yuebing Song +2
Rapid adaptation to a new environment requires a robot to acquire useful knowledge about local objects, states, and interactions from limited experience. Systems that combine a reasoning agent with a frozen vision-language-action model (VLA) can adapt through execution feedback and memory, making the choice of experience central to their effectiveness. Repeated practice of a target task may refine a familiar solution while leaving other interactions relevant to changed conditions untested. We introduce ProactiveVLA, which uses proactive environment exploration to acquire reusable knowledge for deployment-time adaptation. After completing an initial task, the agent allocates the remaining interaction budget to self-proposed goals covering object affordances, state-changing interactions, and compositions of interactions. It verifies execution outcomes and consolidates both task-directed and exploratory experience into memory that guides subsequent planning and control. ProactiveVLA outperforms the baselines under the same turn budget on LIBERO-Pro and RoboCasa365 Composite-Seen. On LIBERO-Pro Goal-T, with at most one VLA primitive invocation allowed during evaluation, ProactiveVLA completes 48% of instances, compared with 19% for the state-of-the-art task-refinement baseline.
vision-language-actionvlaembodiedliberomemoryagent - arxiv:2610.06996 · cs.LGMask-Guided KV Cache Eviction in Block Diffusion Language ModelsGleb Molodtsov, Ekaterina Alimaskina, Evgeny Uskov, Artur Zagitov +1
Block diffusion language models keep a large key-value (KV) cache throughout generation and attend to it at every denoising step, limiting both memory capacity and generation speed. Reducing these costs requires deciding which past tokens to use for denoising the current block (selection) and which to keep in memory for future blocks (eviction). We propose MaskAhead, a training-free method that solves both tasks with a single mask-query-based ranking mechanism. Current-block masks guide selection, while probes of upcoming masked blocks guide eviction. Both rank KV entries by their estimated contribution to the attention output. Our quantized variant, Q-MaskAhead, computes selection and attention directly from low-bit KV, largely preserving the selected entries. Experiments on Fast-dLLM-v2, DreamReasoner, and LLaDA2.0-mini cover long-generation reasoning, long-prompt question answering, and needle-in-a-haystack retrieval. On long-prompt QA, MaskAhead reduces KV memory by $9.5\times$ on average with a 1.2-point mean F1 loss relative to dense inference. Q-MaskAhead increases the reduction to $20.1\times$ with a 2.3-point mean F1 loss. In a batch-32 systems profile, MaskAhead achieves $1.23\times$ end-to-end and $1.68\times$ decode-stage speedups over dense inference.
memory - arxiv:2610.06994 · cs.AITARE: Weigh a Never-Poisoned Twin Before Reading Backdoor-Defense CostsRuizhi Xu, Wei Xu, Sibo Zhu
Backdoor-defense leaderboards print a clean-accuracy drop and read it as removal cost. Measured on the poisoned victim alone, the drop cannot separate removal from what the defense does to any model, and inherits the victim's start, which for three of BackdoorBench's sixteen attacks is a configuration file: WaNet, BPP and Input-Aware ship a MultiStepLR that never fires, so their victims never anneal and are the least accurate in 30/31 public CIFAR cells at $\leq$5%. On PreAct-ResNet18, fine-tuning-family defenses return a low start to their own level, so there the published cost is negative, the benchmark's rating clips the "gain" to zero, and 2 of 48 citing defense papers we read rest a no-cost claim on those cells; TSBD and CGD, re-run with their code, "gain" on a never-poisoned model too. A $2\times2$ editing only that scheduler line isolates the cause, its swapped arms self-registered before they ran: the sign of the fine-tuning family's clean-model cost reverses both ways while its published gain on the annealed victim only shrinks toward zero, 44/44 seeds following the schedule, replicated on BPP, FT-SAM, CIFAR-100 and VGG19-BN and induced in a second toolkit. TARE runs the same defense on a never-poisoned twin of the same recipe, schedule and seed (on BackdoorBench, $\leq$10 poisoned images, admitted only below 5% attack success); what the twin loses is the tare. On the BadNets grid seven of eight defenses charge the twin (Neural Cleanse only where its detector fires), +0.13 (fine-tuning) to +5.70 points (I-BAU); the eighth, ABL, destroys it. Within an attack the start cancels from rankings, so the tare re-orders nothing there; what poisoning adds beyond it is printed under two estimators and not corrected, its removal share unidentified. We ship the three-key patch, a signed tare column (7 attacks $\times$ 8 defenses) and TARE-Z, a twin-free estimator for seed-stable defenses.
benchmarkleaderboard - arxiv:2610.06993 · cs.LGDART-ES: Difficulty-Aware Reweighting and Targeted Replay for Fine-Tuning LLMs with Evolution StrategiesZhishen Sun, Hongzhan Wang, Sizhe Dang, Guang Dai +1
Evolution Strategies (ES) enable memory efficient full parameter fine-tuning of large language models (LLMs) using only forward computation. However, standard ES uniformly averages rewards across problems and compresses problem level population feedback into a single scalar, making it difficult to capture how the learning value of each problem changes with model capability. To address this limitation, we propose Difficulty-Aware Reweighting and Targeted Replay for Evolution Strategies (DART-ES). DART-ES estimates the local solvability of each problem from its pass rate across the perturbation population and aggregates historical observations to construct a dynamic difficulty state. This shared state jointly guides continuous difficulty reweighting and rare solvable sample replay, thereby improving perturbation direction evaluation and training data allocation without introducing an additional difficulty model or backpropagation. Extensive experiments show that DART-ES achieves good fine-tuning performance. DART-ES outperforms ES on all five base models and improves the average accuracy from 72.07\% to 73.53\%, exceeding the 73.26\% achieved by GRPO on GSM8K. Across five challenging mathematical reasoning benchmarks, DART-ES achieves an average accuracy of 49.20\%, compared with 48.34\% for ES and remains competitive with strong 7B models trained with RL. Further experiments show consistent gains in instruction tuning, code generation and the Countdown task with a 14B model, demonstrating strong generalization across tasks and scalability to larger models. Beyond performance gains, DART-ES also shows clear advantages in system efficiency. It reduces runtime per step by 15.2\%--50.2\% and peak memory usage per GPU by 21.1\%--51.1\% compared with GRPO. Despite performing full parameter fine-tuning, DART-ES also requires less runtime and GPU memory than GRPO+LoRA.
memorybenchmark - arxiv:2610.06988 · cs.LGAn Information-Theoretic Evaluation Framework for Benchmark and Model Diagnosis in Knowledge TracingHouru Jiang, Zixi Wang, Tengteng Cheng, Xueyi Li +5
Knowledge tracing (KT) models are predominantly evaluated using aggregate metrics such as area under the curve (AUC) and accuracy. However, these global scores obscure where the remaining errors originate and fail to indicate whether a benchmark is approaching saturation. While estimating a global theoretical performance limit is challenging in realistic KT settings, it is possible to quantify local predictability. To address this, we propose an information-theoretic evaluation framework for KT benchmark diagnosis. We use Context Tree Weighting (CTW) on item-response histories and current-item queries as an operational causal uncertainty coordinate, while distinguishing it from the unobserved Local Irreducible Uncertainty (LIU) under the full KT information set. By projecting predictions onto this shared uncertainty coordinate, we evaluate model performance gains across distinct entropy bands rather than only at the global level. Comprehensive evaluations on NIPS Task 3/4 and Algebra 2005 reveal that model improvements are highly non-uniform. Modern KT models show substantial gains in high-entropy regions, and additional item-aware references, log-loss, and equal-frequency analyses support this localization. The framework also flags regions where apparent gains require checks for noise-sensitive behavior. By surfacing these local modeling failures alongside genuine gains, this approach provides a diagnostic tool for studying both residual predictive structure and the limitations of current KT benchmarks and models.
benchmarkevaluation framework - arxiv:2610.06986 · cs.AIEPOCH: Reliable Discovery through Evidence-Governed SearchBinjie Guo, Aisheng Mo, Ruitong Li, Xinle Deng
AI research agents are increasingly used to search over programs, mathematical constructions, and proofs. However, existing systems typically optimize evaluator feedback without adequately governing how that feedback is interpreted, challenged, and reused. As a result, promising but fragile candidates can be promoted as discoveries, while benchmark improvements, finite certificates, and theorem-level claims are too easily conflated. We introduce EPOCH, an evidence-governed architecture designed to close this gap. EPOCH implements an evidence-governed discovery loop by combining explicit task contracts, typed memory, active falsification, admission checks, and independent replay, so that each candidate is evaluated against the strength and scope of the claim it supports. EPOCH achieves state-of-the-art aggregate performance on AlgoTune, substantially exceeding the strongest baseline in mean normalized score (0.65 vs. 0.53), and attains the highest mean score on the internal Math14 suite (0.57). It further shows favorable held-out behavior under official-test replay and leads the descriptive aggregate on AgentHPO. Across ten discovery problems, EPOCH delivers substantial task-specific advances, including improved executable constructions, optimized algorithms, counterexamples, and proof-supported results. These advances demonstrate its ability to convert search into concrete progress across mathematical and computational domains. Together, the results suggest that evidence governance is a necessary step toward AI research agents that produce not only stronger solutions, but also more trustworthy scientific discoveries.
typed memorybenchmarkevaluator - arxiv:2610.06974 · cs.LGUncertainty in Representation Learning on Knowledge GraphsYuqicheng Zhu
Knowledge graph embedding (KGE) methods represent entities and predicates in continuous vector spaces to infer missing knowledge. Despite strong benchmark performance, their predictions often lack principled reliability guarantees, limiting their use in high-stakes applications. Moreover, uncertainty arises throughout the KGE pipeline, from incomplete or probabilistic input knowledge to stochastic training and prediction. This thesis systematically investigates three sources of uncertainty in KGE: knowledge uncertainty, arising from incomplete, noisy, or probabilistic input knowledge; algorithmic uncertainty, induced by randomness in model training; and predictive uncertainty, concerning the reliability of model outputs. To address algorithmic uncertainty, the thesis demonstrates that models trained under identical settings can produce substantially different predictions and introduces a voting-based aggregation framework to mitigate this instability. To quantify predictive uncertainty, it adapts conformal prediction to KGE, constructing answer sets with distribution-free coverage guarantees and extending them to provide predicate-conditional reliability guarantees. To support reasoning under knowledge uncertainty, it develops statistically valid prediction intervals for confidence-scored triples and an embedding-based approach to approximate probabilistic reasoning over statistical ontologies with formal soundness guarantees. Together, these complementary, model-agnostic methods provide a practical and theoretically grounded approach to uncertainty in KGE, advancing beyond predictive accuracy toward reliable and uncertainty-aware knowledge graph reasoning.
knowledge graphbenchmark - arxiv:2610.06973 · cs.CVEvent Cameras for Melt-Pool Monitoring in Additive Manufacturing: A Benchmark and a Cross-Machine Transfer AnalysisMohamad Yazan Sadoun, Sarah Sharif, Yingtao Liu, Zahed Siddique +1
Melt-pool monitoring is central to qualifying metal additive manufacturing (AM), yet no public event-camera benchmark exists for this domain. Event cameras report per-pixel brightness changes with microsecond timing instead of reading full frames, giving the temporal resolution AM transients demand at a fraction of the data rate. We present SynAM-E (Synthetic AM Events), the first public multi-source simulated event-camera benchmark for metal-AM melt-pool monitoring: 85 physics-calibrated event shards from 15 sources across 8 institutions, with public baselines and fixed cross-machine evaluation splits. On a single-machine case study, event-spatial monitoring matches dense-frame accuracy (0.874 versus 0.863 macro-F1), and the absolute intensity that events discard adds only +0.006 under fusion. On the NIST Additive Manufacturing Metrology Testbed (AMMT) build, a near-sensor event-rate counter recovers a raw-frame-confirmed 528.7 Hz intensity oscillation at ~380 times less sensor readout than the frame stream requires. A compact 93 k-parameter spiking model runs at 15 times lower modeled inference energy for a 0.073 macro-F1 cost. Every cross-source task includes a built-in trust test against camera identity shortcuts: process-type classification passes while material classification remains confounded by camera band, a corpus-structural limitation the release documents and the trust test exposes.
benchmarkevent camera - arxiv:2610.06972 · cs.CVBoT-Feedback: Grounding Multimodal Reasoning in Biomechanical Evidence for Explainable Human Action FeedbackXu Dong, Wanqing Li, Anthony Adeyemi-Ejeye, Andrew Gilbert
Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in visual understanding and multimodal reasoning, yet they remain fundamentally limited in Human Action Feedback Generation. Existing methods infer coaching feedback directly from visual observations, producing generic advice, limited interpretability, and physically implausible hallucinations. In contrast, expert human coaches diagnose performance through explicit biomechanical reasoning over joint kinematics, posture, and body dynamics. We introduce BoT-Feedback, a framework that grounds MLLM reasoning in structured biomechanical evidence. Our key contribution is Biomechanics of Thought (BoT), a four-stage reasoning framework that progressively identifies the action, localises the critical body regions, analyses quantitative biomechanical differences between expert and student performances, and synthesises interpretable coaching feedback. To support this reasoning process, we develop a plug-and-play Biomechanical Data Parser (BDP) that converts videos into structured biomechanical descriptors and an alignment strategy that temporally matches expert and student motions. We further introduce BiomAF, a benchmark containing paired teacher-student videos, 3D skeletons, biomechanical attributes, and expert-coaching annotations. Experiments across twelve open- and closed-source MLLMs demonstrate that grounding reasoning in biomechanical evidence consistently improves feedback quality, interpretability, and robustness while substantially reducing biomechanical hallucinations. BoT-Feedback improves the average expert evaluation score from 2.07 to 2.95 (+40%), enabling compact open-source MLLMs to approach the performance of substantially larger proprietary systems for explainable action feedback generation.
benchmark - arxiv:2610.06971 · cs.AIAegisFlow: A Multi-Agent Agentic AI Framework for Autonomous Remediation and Self-Healing in Fragile Data EcosystemsMuhammad Bilal Awan, Zubair Hussain, Abdul Shahid
Traditional data pipelines are notoriously brittle, often failing due to upstream schema drift, API contract changes, or website DOM modifications. Present observability tools only raise alerts but for human engineers, resulting in a high Mean Time to Repair (MTTR) and operational fatigue. In this paper we propose AegisFlow (Agentic Engine for Intelligent Self-healing and Graph-driven Operations for Workload remediation), a novel agentic framework that closes the loop between detection and resolution. AegisFlow uses a Watchdog agent to collect runtime telemetry and has a Repair agent to automatically create, test and deploy code patches based on Large Language Models (LLMs). The framework presents the non-intrusive execution model called Parallel Shadow Patching, a non-intrusive execution model based on the Monitor, Analyze, Plan, Execute, Knowledge (MAPE-K) loop to generate and verify patches in digital twin environments. Through experimental testing, we have evaluated AegisFlow across five common failure scenarios, and see 98.1 percent improvement in MTTR (from an average of 170 minutes per patch to 3.2 minutes) and a patch success rate of 92 percent . In particular, the system is successful in dealing with changes in the JSON schema (96 percent ) and punctuation drift (98 percent ), and is least successful in Shadow DOM cases (85 percent ). AegisFlow frees up about 98 percent of data engineering on-call time from firefighting and reallocates it towards innovation. The framework is deployment agnostic consisting of a system that can be deployed in a plugin fashion into an existing pipeline orchestration system with minimal uplift to the existing system.
agentmulti-agentagentic - arxiv:2610.06970 · cs.LGEVFormer: An Egocentric Vision-EMG Bidirectional Attention Model for Bimanual Hand Pose EstimationJiaCheng Ge, SiYu Zhang, ShengJie Li, XinTong Yang
Egocentric bimanual hand pose estimation is important for virtual interaction, wearable control, and rehabilitation, but visual observations are often degraded by self-occlusion, hand-hand contact, and object manipulation. We propose EVFormer, a multimodal framework that combines the current RGB frame with the preceding 200 ms of bilateral wrist surface electromyography (sEMG) to estimate 44 finger and wrist joint angles. EVFormer separately encodes visual spatial features and sEMG temporal features, enables cross-modal information exchange through sequential bidirectional cross-attention, and integrates the two modalities using feature-wise gated fusion. We evaluate EVFormer in a single-participant feasibility study using one synchronized public EgoEMG recording with chronologically separated training, validation, and test splits. On 296 test samples, EVFormer achieves a mean absolute error of 11.482 degrees, compared with 13.228-13.610 degrees for vision-only, sEMG-only, late-fusion, and training-mean baselines. This corresponds to relative error reductions of 13.20% compared with the vision-only model and 14.23% compared with late fusion. EVFormer also achieves the lowest error in four of the five evaluated gesture classes. These results provide preliminary evidence that feature-level interaction between egocentric vision and sEMG can improve bimanual hand pose estimation. Further evaluation across participants, recording sessions, sensor placements, and real-world interaction conditions is required to establish the generalizability of the approach.
manipulation - arxiv:2610.06966 · cs.AIAPEX: Active Protection at Execution Boundaries for LLM AgentsXinran Zheng, Xin Fan Guo, Zhiqiang Hao, Fan Yang +6
Indirect prompt injection (IPI) hides adversarial instructions in content that large language model (LLM) agents read at runtime. As agents compose heterogeneous capability units, including Tools, MCP servers, and Skills, the carriers of injection multiply, and defenses built to recognize attack patterns fall behind them. We instead shift defense from covering attack patterns to one stable point: whatever the carrier and however the injection propagates, harm materializes only at the \emph{execution boundary}, where the agent turns internal state into an external action or released output. Safety there turns on two conditions, both settled by the trusted task rather than by the run: whether the proposed effect is authorized, and whether the runtime information reaching it is endorsed by that task. We present APEX, an active defense that enforces both at this boundary from a single authorization contract compiled before untrusted execution: \emph{evidence-gated prevention} admits an effect only when the contract justifies it, while \emph{deception-based exposure} makes unendorsed use reveal itself before the effect commits. Protection therefore follows from what the task permits rather than from how an attack is built, and applies uniformly across capability units without attack-specific policies or taint tracking. Against 13 baselines, APEX attains 0\% attack success on five of six benchmarks and 0.56\% on the sixth, holds 0\% under adaptive attacks on all three capability-unit types, and remains effective across defender backbones. Code is available at https://github.com/ZhengXR930/APEX_official/tree/official.
agentllm agentbenchmark - arxiv:2610.06965 · cs.ROACG-WAM: World-Action Modeling via Action-Conditioned Geometric Latent PredictionJiangtao Liu, Zishang Xiang, Yage He, Lingguo Cui +3
World action models jointly learn visual predictionand robot actions, providing a way to use observations ofscene evolution for policy learning. Their video and actionlosses, however, provide no explicit target for the geometricconsequences of a demonstrated action sequence. Moreover,visual features taken after temporal attention can contain futureobservations, making them unsuitable as the sole current visualinput to an auxiliary predictor. We introduce ACG-WAMand its auxiliary objective, the Action-Conditioned GeometricJoint-Embedding Predictive Architecture (ACG-JEPA), whichpredicts geometric features at several horizons from the currentobservation and intervening actions, using the future slot of afrozen VGGT encoding of each current and future image pairas the target. We apply this supervision from the head and wristcameras to a shared visual embedding before temporal mixing,and remove the teacher and auxiliary modules at inference.On 50 RoboTwin 2.0 tasks, ACG-WAM achieves 93.46%success in clean scenes, with the best randomized success(92.68%) and mean across both settings (93.07%) among thecompared methods; across three tasks on a real robot, itachieves 85.00% success and 91.67% partial completion score,exceeding Motus by 10.00 and 9.17 percentage points, respec-tively. Code:https://github.com/RoboOpus/ACG-WAM.Website:https://RoboOpus.github.io/ACG-WAM.
robotwinaction-conditioned - arxiv:2610.06964 · cs.LGPrinciples that Guide, Actions that Inform: Agent Evolution via Knowledge AbstractionBowen Ye, Yongchao Xu, Junkai Ma, Xiang Yin +1
Large language model (LLM) agents have demonstrated strong capabilities in interactive environments, yet their ability to continually evolve from experience remains limited. Although fine-tuning enables adaptation, its dependence on parameter access and high computational costs restrict its flexibility, especially for large-scale and closed-source LLMs. External memory offers an alternative by allowing agents to accumulate experience without modifying model parameters. However, existing methods mainly focus on experience representation and organization, while the acquired knowledge remains tightly coupled with specific tasks and contexts, limiting generalization. A key challenge is how to transform concrete interactions into abstract and reusable knowledge that guides future decisions beyond individual experiences. To address this challenge, we propose SAGA (\underline{\textbf{S}}elf-evolving \underline{\textbf{A}}gents through Experience-\underline{\textbf{G}}rounded \underline{\textbf{A}}bstraction), a framework for experience-grounded knowledge abstraction and utilization in LLM agents. SAGA progressively transforms interaction trajectories into episodic descriptions, reusable procedures, and principles with explicit applicability conditions, while maintaining links to execution evidence. Retrieved principles are instantiated into task-specific guidance and used to refine candidate actions through corrective feedback and resampling. This creates an execution--abstraction feedback loop, where accumulated knowledge guides future interactions and new experiences continuously update hierarchical memory. Experiments on ScienceWorld and ALFWorld demonstrate improved task performance, with ablation studies highlighting the importance of contextual instantiation and action regulation for leveraging principle-level knowledge.
memoryexternal memoryagentllm agent - arxiv:2610.06963 · cs.CLWavePrune: One period is often enough for RoPEGuancheng Du, Luotian Huang, Shaowen Wang, Si Li +1
Rotary Position Embedding (RoPE) encodes token positions by rotating each two-dimensional channel of the query and key vectors at a channel-specific frequency, making the attention logits invariant to a common shift of positions. However, this rotation is periodic, and it leads to position aliasing where relative positions separated by a full rotation period become hard to tell apart. To address this, we propose WavePrune, which restricts each channel to its first rotation period. We show that it removes the distractions in attention maps created by position aliasing and improves overall long-context performance. Specifically, WavePrune raises the HELMET score on four of five models we test without any extra tuning (e.g., 35.7 -> 40.0 on Qwen3-8B). When pretraining models from scratch, WavePrune also achieves lower validation loss at extrapolated lengths than pretraining without it. Because WavePrune restricts each channel to a sliding window, it induces a fine-grained sparsity that our hardware-aligned CUDA kernels exploit for 1.15x prefill and 1.24x decoding speedups over FlashAttention-2 at 32K context. Together, these results show that RoPE's periodic structure, widely regarded as essential, is largely redundant beyond the first rotation period.
long-context - arxiv:2610.06962 · cs.AIVerdicts Without Annotated Evidence: Rejection Sampling or Label-Only Post-Training for Evidence Recovery?Nishanth Nayakanti, Prasang Gupta, Ashutosh Bilthare, Kevin Paul
In many review workflows the verdict is the only thing retained. The passages behind it are not marked, because that annotation costs far more than recording the decision. We measure how much of that evidence a small language model can recover when it is post-trained on the verdicts alone, with no human evidence labels at any stage. On ContractNLI the human evidence spans are held out until evaluation. Matching the recorded verdict and agreeing with those spans are not the same thing: across six systems the two scores are only weakly related and rank the systems differently, so accuracy is a poor guide when the citations have to be reviewable. Label-only training on the bare verdict reaches accuracy 0.896 and span F1 0.564. Rejection sampling, which keeps a generated trace only when its verdict matches the record and then picks one by an automatic source-grounding score, reaches 0.797 and 0.556, against 0.747 and 0.493 before training. Verbatim citation rises from 0.597 to 0.729 under label-only training and to 0.701 under rejection sampling. One seed on one corpus cannot say which method is better, but both improve the evidence without anyone annotating it.
post-training - arxiv:2610.06960 · cs.CVDistScene: Object-to-Scene Distillation for 3D Scene GenerationKunming Luo, Hongyu Yan, Ken Deng, Chengcheng Zhou +5
We present DistScene, a framework for single-image compositional 3D scene generation by jointly modeling the environment and individual objects. Unlike existing methods that represent scenes primarily as collections of objects, we model the environment as an explicit scene component to provide geometric context for object placement. Specifically, we introduce Scene-Frame Generation, which jointly generates separate environment and object components in a shared coordinate frame, allowing their geometry and relative placement to be learned together. Then we introduce Object-Centric Refinement to refine each object in a local frame with scene context. Finally, we develop Object-to-Scene Distillation to transfer pretrained object-generation priors to scene generation through automatically composed and rendered synthetic scenes. Evaluations on indoor and outdoor benchmarks demonstrate improved scene-level spatial coherence over the evaluated baselines. Project page: https://coolbeam.github.io/DistScene/
benchmark - arxiv:2610.06956 · cs.CLEMODE: Dynamic Para-Semantic Experts for Emotion-Aware Speech Language ModelingJianan Pan, Yiwen Gu, Xinze Li, Rui Wang +1
Large speech language models have demonstrated strong capabilities in unified cross-modal understanding and generation, yet paralinguistic cues, especially emotion, remain difficult to preserve. Existing systems typically rely on entangled acoustic representations, which allow the underlying language model to depend excessively on recovered lexical content instead of grounding its behavior in acoustic-prosodic evidence. We address this limitation with EMODE, an emotion-aware speech language model built around \textbf{Dynamic Para-Semantic Experts (DPSE)}. DPSE decomposes continuous speech features into semantic and paralinguistic pathways, routes them dynamically, and fuses them before integration into the language model. To turn this structural decomposition into functional specialization, EMODE is trained with a three-stage curriculum consisting of semantic warm-up, paralinguistic activation, and joint refinement, guided by Orthogonal Expert Guidance (OEG), Semantic-to-Acoustic Alignment (SAA), and Gating Diversity Regularization (GDR). Experiments on SER test, empathetic response evaluation, and the newly constructed bilingual MEPA benchmark show that EMODE improves the balance between lexical fidelity and emotional sensitivity, strengthens affect-grounded response generation, and exposes the value of explicit para-semantic factorization for robust cross-corpus emotion understanding.
benchmark - arxiv:2610.06955 · cs.ROROMA: LLM System for Real-World Object-Centric Multi-Sensory Active PerceptionRuoxuan Feng, Yutong Chen, Ruihua Song, Huan Yang +3
Humans inherently understand the physical world through an active process. When sensory evidence is insufficient to infer physical properties, we naturally interact with the environment by deciding what information is missing, how to acquire it, and when sufficient evidence has been obtained. In stark contrast, existing multi-sensory robot systems mainly integrate sensory inputs rather than actively acquiring missing evidence through interactions. In this work, we introduce ROMA, an LLM-based system for Real-World Object-Centric Multi-Sensory Active Perception. ROMA integrates vision, audio, tactile, and force sensing into a reasoning-interaction-feedback loop. The model identifies missing evidence and determines the target objects, interactions, and modalities, while a physical interface executes the selected interactions and collects the multi-sensory feedback. To support this capability, we construct ROMI-2K, a large-scale real-world multi-sensory object interaction dataset covering nearly 2,000 objects and 6 atomic interactions with synchronized sensory feedback. Building on these data, we develop a two-stage training framework that aligns sensory modalities and equips the LLM to assess evidence sufficiency, select informative interactions, and reason over the multi-sensory feedback. We further characterize active perception as perception chains, where acquired evidence guides subsequent interactions and reasoning, and establish ROMA Bench to evaluate single-attribute, long-horizon multi-attribute, and intent-driven active perception. Experiments show that ROMA can actively acquire missing evidence and solve complex, long-chain multi-sensory perception tasks that existing methods struggle to handle, laying a strong perceptual foundation for active multi-sensory embodied agents.
embodiedtactileembodied agent - arxiv:2610.06952 · cs.LGDo Neural PDE Solvers Learn the Right Dynamics?Haonan Li, Yue Song, Bin Yang, Kaihong Luo
Neural PDE solvers can achieve low prediction errors, but do they reproduce the dynamics of the systems they model? Prediction scores alone offer an incomplete answer: they measure agreement with reference solutions but provide limited insight into how errors accumulate, nearby states diverge, or extreme events arise. We propose an evaluation framework that directly examines these behaviors in deterministic and stochastic neural solvers. By evolving ensembles of nearby initial states and comparing them with direct numerical simulation, we assess three complementary aspects of learned dynamics: error formation, ensemble geometry, and extreme events. Experiments on two-dimensional Kolmogorov flow reveal limitations that conventional scores can obscure. Smaller trajectory errors can reflect weaker error amplification despite less accurate local updates. Models can match an ensemble's overall spread and effective dimension while failing to capture the spatial directions where nearby states diverge. Similarly, matching overall event frequencies can conceal failures to predict persistent extreme events. These findings show that improved prediction accuracy does not necessarily imply greater dynamical fidelity. Our framework makes this distinction measurable, providing concrete criteria for evaluating whether advances in neural PDE solvers better capture the underlying dynamics.
evaluation framework - arxiv:2610.06947 · cs.LGFactorBench: A Portfolio-Aware Benchmark for Automated Factor MiningZhuohan Wang, Carmine Ventre
Factor mining seeks to discover signals from financial data that predict future asset returns and guide portfolio construction. Automated factor mining now spans genetic programming, reinforcement learning, generative models, and large language model agents. Yet it remains unclear whether advances across these paradigms yield more generalizable, distinct, and economically useful financial signals. We introduce FactorBench, a portfolio-aware benchmark comparing roughly five thousand mined factors from nine automated mining methods across five equity markets. A shared data and evaluation contract supports both symbolic expressions and executable Python factors, connecting heterogeneous discovery algorithms to common signal combination and portfolio construction procedures. FactorBench traces the outputs of mining systems across three levels: factor validity, temporal generalization, and predictiveness beyond measured risk and style exposures; within- and across-method pool distinctness, including similarity to the benchmark Alpha101; and composite-signal quality and after-cost long-only and long--short portfolio performance. After systematically assessing whether advances in factor mining translate into signal quality and portfolio performance, FactorBench finds that no paradigm consistently dominates.
benchmark - arxiv:2610.06942 · cs.LGLearning to Remember: Distilling Memory Retention for Compact Recurrent Neural NetworksNilushika Udayangania, Kishor Nandakishora, Marimuthu Palaniswami
Deep learning models, particularly recurrent neural networks and their variants, such as long short-term memory, have significantly advanced time series analysis. These models capture complex, sequential patterns in time series, enabling real-time assessments. However, their high computational complexity and large model sizes pose challenges for deployment in resource-constrained environments, such as wearable devices and edge computing platforms. Knowledge Distillation (KD) offers a solution by transferring knowledge from a large, complex model (teacher) to a smaller, more efficient model (student), thereby retaining high performance while reducing computational demands. Current KD methods, originally designed for computer vision tasks, neglect the unique temporal dependencies and memory retention characteristics of time series models. To bridge this gap, we propose a novel KD framework termed Memory-Discrepancy Knowledge Distillation (MemKD). MemKD leverages a specialized loss function to capture memory retention discrepancies between the teacher and student models across subsequences within time series data, ensuring that the student model effectively mimics the teacher's behaviour. This approach facilitates the development of compact, high-performing recurrent neural networks suitable for real-time, time series analysis tasks. We provide additional experiments, in-depth theoretical analysis, and insights into the proposed framework across extended time series benchmarks. Our experiments demonstrate that MemKD significantly outperforms state-of-the-art KD methods. Additionally, we demonstrate that it can match the teacher model's performance across a wide range of compression levels, achieving notable reductions in parameter count and memory usage without a significant loss in accuracy.
memorybenchmark - arxiv:2610.06936 · cs.LGQiYao-I: A Manifold Based Foundation Model for Irregular Multivariate Time Series ForecastingLinfeng Wang, Ruitong Zhang, Kai Zhao, Yang Shu +5
Irregular multivariate time series forecasting is a challenging yet important problem in real-world applications, where observations are often irregularly sampled and asynchronously recorded across variables. Existing time series foundation models are mostly built on regularly sampled sequences, making them difficult to generalize to irregular time intervals and asynchronous cross-variable dependencies. To address these challenges, we propose QiYao-I, a manifold based foundation model for irregular multivariate time series forecasting. Specifically, we introduce a novel sampling-conditioned temporal manifold attention mechanism that maps real timestamps into a learnable temporal manifold feature space and injects temporal manifold biases into attention layers, enabling the model to capture both irregular time intervals and local sampling structures. Further, we propose a dynamic variable interaction mechanism with frequency awareness. It selectively performs cross-variable message passing under asynchronous observations. Extensive experiments on real-world irregular multivariate forecasting benchmarks demonstrate that QiYao-I achieves superior performance compared with both time series foundation models and end-to-end irregular forecasting models, showing strong generalization ability in zero-shot and few-shot settings.
benchmark - arxiv:2610.06932 · cs.CVRADC: Risk-Aware Dual Caching for Vision-Language Test-Time AdaptationSiyu Huang, Yueyong Chen, Xuejiao Li, Jun Zhou
Cache-based test-time adaptation (TTA) for vision-language models is often hindered by background bias in global representations and unreliable entropy-based cache admission under representation variations. To address these limitations, we propose RADC, which enhances prototype learning through reliable dual caching. RADC introduces a Semantic Foreground Cache that aggregates category-consistent spatial evidence from CLIP representations, yielding foreground prototypes that complement the global cache while mitigating background interference. To reliably manage both caches, Gaussian Risk Admission models multi-view representations as diagonal Gaussian distributions and jointly considers class separation and feature uncertainty to prioritize reliable cache candidates. RADC integrates zero-shot logits with complementary global- and foreground-cache predictions for robust inference. Extensive experiments on cross-domain and out-of-distribution benchmarks demonstrate consistent state-of-the-art performance.
benchmark - arxiv:2610.06929 · cs.ROPhysical Twins: Accelerating and Enabling Robot Learning with Phantom PlatformsElizabeth Peiros, Derek Chen, Lucas Yager, Edward Lee +3
Improvements in human-robot physical interaction (pHRI) can have major implications for physical therapy, search and rescue, and telemedicine. However, a major challenge concerns human constraints and safety in human-robot physical experiments. Concerns about human studies also include repeatability, scalability, and participant diversity. To conduct such experiments, an IRB and willing human participants are required. In this work, we present an improved phantom device, a physical twin, that enables real-world RL-type testing for physically interactive algorithms. The new device not only replicates the ball-and-socket motion of the shoulder but also renders scapular and protraction/retraction motions. The experiments showcase the device's ability to render multiple 3D joint limits and demonstrate a Franka Panda arm sensing limits and interacting with the device as an arm for ADLs (activities of daily living) and pHRI tasks.
franka - arxiv:2610.06927 · cs.LGAttSVD:Prompt-Adaptive Low-Rank KV Cache Compression via Attention-Guided SVDSara Abdali, Jongwoo Ko, Pashmina Cameron
The key-value (KV) cache of autoregressive transformers grows linearly with context length and dominates memory at long context. Most training-free remedies evict low-importance tokens, an irreversible choice along the sequence axis. We instead keep every token and store it more cheaply along the "feature" axis. We therefore propose AttSVD, a new "interpretable" low-rank compression whose basis is derived from each prompt's own attention geometry: an online, per-prompt truncated SVD that keeps only the directions attention actually reads, cutting persistent per-head KV memory in proportion to the retained rank. We propose two decode-time caching strategies, accumulating and streaming, for short and long generation regimes. Furthermore, we propose two refinements that make compression adaptive. A per-matrix energy rule sizes the logit space and the attention mass independently. An attention-aware basis truncates only in the spaces attention actually reads, preserving both the attention logits and the attention output. The same factors also provide free, per-head interpretability insights into the effective rank and the geometry attention consumes. Across multiple models, on both an agentic benchmark and the full LongBench suite AttSVD stays on par with the dense cache while using up to 50% of the KV-cache memory.
memorylong contextagenticbenchmark - arxiv:2610.06926 · cs.ROSWAP: Stepwise Action Policy Routing for Vision-Language-Action ModelsMousumi Das, Aditeya Prajapati, Abrar Anwar, Jesse Thomason
Robot manipulation systems using Vision-Language-Action (VLA) model backbones typically use just one VLA for task execution. However, individual VLAs do not perform well across different task states and environments. We introduce a framework for dynamically composing multiple VLA policies during execution: StepWise Action Policy Routing (SWAP). SWAP formulates policy routing as an offline reinforcement learning problem, learning a routing critic that selects the most appropriate policy at each decision step given the current observation. SWAP enables robots to select new policies to execute online rather than committing to a single policy for the duration of an episode. We evaluate SWAP on both real-world DROID manipulation tasks and LIBERO simulation experiments. SWAP improves over fixed-policy execution and routing baselines, giving absolute improvements in real-world task success up to 33% while reducing successful trajectory robot action step length by 28.3%.
vision-language-actionvlamanipulationlibero - arxiv:2610.06923 · cs.AIRadOnc-Agent: An LLM-Orchestrated Framework for AI Workflows Across the Radiotherapy Care PathwayCaiwen Jiang, Shuoyang Wei, Songlin Zhao, Junyu Li +2
Artificial intelligence has advanced individual radiotherapy tasks, yet these capabilities remain separated across clinical stages, software environments and data modalities. This fragmentation contrasts with the longitudinal radiotherapy workflow from treatment decision-making through follow-up. Here we present RadOnc-Agent, an agentic artificial-intelligence framework that formalizes radiotherapy into four clinical phases and provides 26 callable functions through a conversational interface. A large-language-model controller maps clinical intent to schema-constrained calls, preserves patient and workflow context, and routes requests to specialist services. We evaluated system execution using 2,600 single-function requests (7,800 repeat executions), 200 prespecified synthetic cross-stage scenarios spanning four phases (600 executions), and 120 workflow instances from 60 de-identified patient records (360 clean executions) representing decision-to-planning and planning-to-adaptation. RadOnc-Agent selected the intended function in 98.79% of single-function executions, completed 96.50% of scripted cross-stage workflows, and completed 96.67% of real-patient workflow executions. In comparative ablations, removing longitudinal state reduced cross-stage completion from 96.50% to 84.00%, while disabling schema and identity validation increased mismatched backend dispatch from 0% to 95.28% in a replay/test evaluation. These findings establish the technical feasibility of an LLM-orchestrated architecture for coordinating heterogeneous radiotherapy capabilities and information across longitudinal workflows; they do not establish clinical correctness, clinical utility or prospective benefit.
agentic - arxiv:2610.06921 · cs.RODoes a Learned Corrector Beat a Simple Retreat? Evidence from a Frozen VLAChenchao Sheng, Zhuang Jiang, Liuhaichen Yang, Ningwei Bai +1
Before deploying runtime recovery for a frozen vision-language-action (VLA) policy, one must establish that an intervention improves success beyond ordinary run-to-run variation and that its complexity adds value over a simple action. We evaluate these questions on frozen $π_{0.5}$ across four RoboTwin tasks. For each test seed, we pair rollouts with and without correction and include a same-seed base-policy re-run as a placebo. Seed-cluster intervals and prespecified comparison rules assess net gains against stochastic outcome changes. Across 3,888 paired episodes, the full pipeline raises success on beat_allowbreak block_allowbreak hammer by $+13.5$\,pp (95\% interval $[+9.4,+17.7]$), with no detectable gain on the other three tasks at the deployed weight. Among failed base episodes on the responsive task, $43.2\%$ succeed on a plain re-run, compared with $63.5\%$ after correction; many nominal rescues therefore reflect the base policy's own variability. A fixed-time trigger and scripted return to an earlier joint configuration produce a net gain with no detected difference from the learned pipeline across two rounds, although our prespecified equivalence criterion is not met consistently. Pausing and a constant-action control do not yield comparable gains. On this benchmark, the decision to intervene depends strongly on the task, and a paired placebo plus a simple retreat baseline are needed to establish what learned correction contributes.
vision-language-actionvlarobotwinbenchmark - arxiv:2610.06920 · cs.LGExtending Music Annotation Schemas: Zero-Shot Prediction or Few-Shot Adaptation?Christos Plachouras, Emmanouil Benetos, Johan Pauwels
Automatic music annotation is typically tackled under the assumption of a fixed annotation schema. In practice, commercial music catalogs often need to accommodate new musical attributes as needs evolve. Given that expert music annotation is expensive, it is not evident which methodological approach is most effective at accommodating new attributes and backfilling existing tracks; audio-language models promise zero-shot prediction, but at what annotation budget does supervised adaptation become more compelling? We propose a benchmark based on the MGPHot popular music annotation dataset for simulating music schema extension across different annotation budgets. We investigate zero-shot prediction with audio-language models, learning new attributes from pretrained representations, and adapting models trained on existing annotations. Our results suggest that supervised adaptation is more effective than zero-shot prediction even with small annotation budgets, while frozen representation reuse remains the most effective approach for modest budgets without the tuning required by deeper adaptation.
benchmark
02 US SEMI · SEC 8-K FILINGS
0 itemsscanned: NVDA / AVGO / MRVL / COHR / LITE / AMD / TSM / SMCI / ANET / CRDO / POWL / VECO
03 HUMANOID · COMPANY NEWS
54 itemsscanned: figure-ai / 1x / boston-dynamics / unitree / apptronik / sanctuary-ai / neura-robotics / agility-robotics / physical-intelligence / agibot
Figure AI (10)
- Figure AISeptember 30, 2026F.02 Decommission
- Figure AISeptember 17, 2026Helix 2.5: Zero-Shot 30-Home Generalization
- Figure AIOctober 09, 2025Introducing Figure 03
- Figure AISeptember 03, 2026Figure and Nscale Sign Strategic Partnership For Up to 100,000 GPUs on the NVIDIA Vera Rubin Platform
- Figure AIAugust 25, 2026Introducing Index: Building The World’s Largest and Most Diverse Physical Dataset
Boston Dynamics (10)
Unitree 宇树 (10)
- Unitree 宇树Components
- Unitree 宇树Kung Fu Meets Spring, Unitree SFG Robots Present "Cyber Real Kung Fu" in the Year of the Horse2026-05-31Media Coverage
- Unitree 宇树Welcoming Myanmar President Min Aung Hlaing to Unitree2026-08-05Media Coverage
- Unitree 宇树Unitree founder Wang Xingxing graces the cover of Time magazine2026-08-05Media Coverage
- Unitree 宇树Unitree Announces H2 Plus, an NVIDIA Isaac GR00T Reference Humanoid Robot for Academic Research2026-06-01Media Coverage
Apptronik (1)
Sanctuary AI (6)
- Sanctuary AIBlog PostTIGER: Task-Space Imitation Guidance for Efficient Reinforcement LearningDemonstrations as a compass, not a scriptRead More
- Sanctuary AIPress ReleaseProduct UpdatesSanctuary AI Expands Physical AI Strategy to Industrial Robotics, Demonstrating Production-Ready AI PerformanceRead More
- Sanctuary AICorporate NewsDaniel Friedmann Appointed CEO of Sanctuary AIRead More
- Sanctuary AIPress ReleaseZeon Invests in Sanctuary AI and Partners to Advance Specialized Materials for Dexterous RoboticsRead More
- Sanctuary AIThought LeadershipWeb Summit Reflections: Canada’s Physical AI Moment Can’t WaitRead More
Agility Robotics (10)
- Agility RoboticsAgility’s Humanoid Deployment ProcessPras VelagapudiAugust 04, 2026
- Agility RoboticsThe Realistic Pathway to HomeInsightMay 26, 2026
- Agility RoboticsAgility and AIInsightMarch 16, 2026
- Agility RoboticsAgility Gets a New BrandInsightMarch 5, 2026
- Agility Robotics2026: The Automation EvolutionInsightJanuary 16, 2026
智元 AgiBot (7)
- 智元 AgiBotAGIBOT Partners with Vietnam National Innovation Center(NIC) to Advance Embodied AI Industry and Talent Ecosystem2026-10-02
- 智元 AgiBotIDC Data Shows AGIBOT Led Global Humanoid Robot Shipments in H1 20262026-09-30
- 智元 AgiBotAGIBOT and ASD Deploy 100 AGIBOT X2 Humanoid Robots Across 100 Retail Stores2026-09-29
- 智元 AgiBotAGIBOT and Chimelong Launch Large-Scale Embodied AI Theme Park with More Than 300 Robots2026-09-23
- 智元 AgiBotAGIBOT Demonstrates WITA-Omni in Live Human-Robot Interaction at The Greater Bay Area Film Concert2026-09-21