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.
408 items today · 353 arxiv · 1 SEC 8-K · 54 humanoid · 0 CN photonics
01 ARXIV · PHYSICAL AI PAPERS
353 items- arxiv:2610.13948 · cs.AICan Language Models Play the Wikipedia Game?Alexander Hickey, Joanna Knight, James Bishop
Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requires specialist linguistic or scientific knowledge. We used the Wikipedia Game to test language models on an analogous information retrieval task. In the game, players must reach a target article using only article links. We compared sentence embedding models and LLMs across five Wikipedia languages and five academic-literature datasets. We construct very large local graphs of Wikipedia pages and of paper citations using OpenAlex and provide code to build and navigate them. This allows the study of language models' navigation capabilities without relying on third-party APIs. We compared the models with human and TF-IDF benchmarks. The Wikipedia Game format enables robust comparisons across techniques, languages, and domains. No model significantly outperformed humans, although the best models (GPT-o3 mini, GPT-4o, QwQ:32B, and DeepSeek-R1:70B) achieved comparable success. Performance and rankings varied across languages and topics, with implications for practitioners utilising these techniques.
benchmark - arxiv:2610.13947 · cs.CVTowards Physically Grounded Articulated 3D Assets: A Multi-Agent Pipeline and BenchmarkXudong Cai, Ruijie Zhu, Haoliang Shang, Ruining Li +4
In this paper, we study physically grounded articulated 3D asset generation---moving the goal from reproducing how objects look to capturing how they move and function. Inspired by the literature on procedural and agentic generation, we present Artisan, a system that extends the latest method Articraft by introducing a multi-agent pipeline with physical simulation feedback, enabling comprehensive attributes beyond geometry, appearance, and physically plausible articulation, such as collision-free motion, stability under gravity, and accurate mass and material properties. Furthermore, we construct a unified benchmark spanning four key aspects: spatial fidelity, physical plausibility, downstream task performance, and overall quality. The benchmark encompasses 100 reference assets from ArtVIP and LightWheel, 50 stability prompts, and 50 ABO objects with reference masses, with protocols evaluating various metrics. Through extensive evaluation of more than 10 representative models, Artisan achieves competitive spatial fidelity while attaining the lowest collision rates and highest stability rates among the evaluated methods. Together, our system and benchmark establish insights for advancing 3D generation towards physically plausible, functionally usable assets.
multi-agentagenticbenchmark - arxiv:2610.13945 · cs.ROSplat2Act: From Captured Scenes to Personalized VLA ManipulationXiaomeng Ye, Krishna Jaganathan, Gyubeum Lim, Gunjan Chhablani +2
A user who brings a generalist manipulation policy into their home or office wants it to pick up their objects from their shelves, counters, and tables. Yet even a strong generalist like $π_{0.5}$ achieves 0% pickup success in our captured deployment scenes without adaptation, and collecting real demonstrations in every user's environment is prohibitively expensive. We present Splat2Act, an automated real-to-sim-to-real pipeline that personalizes a pretrained vision-language-action (VLA) policy to a specific scene and object set using only a handheld phone scan and images of the user's objects. Unlike prior real-to-sim work that reconstructs individual tabletops, Splat2Act operates on building-scale indoor environments: it builds a photorealistic digital twin with 3D Gaussian Splatting and collision geometry, automatically discovers tabletop and non-tabletop receptacles, constructs feasible pickup tasks, and generates successful demonstrations with a privileged simulation oracle, with only scene and object capture required from a human. Applied to 101 scanned campus environments with a median navigable area of 104.87 m$^2$ and 7 receptacles, the pipeline yields 852 receptacles and over 68,000 pickup demonstrations. We fine-tune $π_{0.5}$ in two stages: Stage 1 adapts to hundreds of public object assets, drawn either from the deployment scene alone or from all 101 scenes; Stage 2 personalizes to the user's own objects on the deployment scene's receptacles. Our strongest personalized policy reaches 62.5% aggregate pickup success in the target scene. Deployed on a real Stretch 3, the same policy achieves 63.9% success on a 12-task subset, closely tracking its 66.7% simulated success on those tasks. These results suggest that automated real-to-sim-to-real training can personalize VLA manipulation policies using only simulation-oracle data.
vision-language-actionvlamanipulationsim-to-real - arxiv:2610.13943 · cs.RONoise Space Learning for VLA AdaptationJunjie Lu, Chuheng Zhang, Yucen Wang, Yuhua Jiang +3
Pretrained vision-language-action (VLA) models encode broad manipulation priors, yet adapting them to specific tasks requires balancing limited robot interaction, computational resources, and safety constraints. Noise space learning (NSL) adapts flow-matching-based VLAs by learning a context-conditioned distribution over noise while keeping the pretrained VLA fixed. Building on prior noise-steering methods, we formulate NSL as an interface for VLA adaptation that accommodates different learning algorithms and instantiate it with PPO, SAC, and AWR. Theoretically, we provide an information-theoretic analysis of how NSL enables efficient adaptation. Empirically, we study these NSL algorithms on LIBERO, RoboTwin, and four real-robot manipulation tasks under interaction, computation, and execution constraints. Across these settings, we develop a suite of effective NSL variants and derive practical recommendations for choosing among them under different resource and deployment regimes.
vision-language-actionvlamanipulationliberorobotwin - arxiv:2610.13915 · cs.CVWhere to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised LearningJunkai Liu, Le Zhang
Self-supervised learning on 3D medical images commonly relies on random sub-volume sampling during pretraining. However, random cropping implicitly treats all spatial regions as equally worth observing, despite anatomical priors and spatial redundancy that make regions inherently unequal in their value for representation learning. To this end, we first show through controlled crop-quality manipulations that better sub-volumes lead to better downstream transfer, revealing the observation policy as an overlooked bottleneck in 3D medical SSL. Motivated by this finding, we revisit sub-volume sampling as a \emph{where-to-look} problem. We propose \textbf{\method}, a plug-and-play framework that replaces random cropping with an offline coarse-to-fine probe bank guided by \textit{anatomy-awareness}, \textit{informativeness}, and \textit{diversity}. We instantiate \method as a lightweight \lite variant using geometric and image-statistical cues, and a diagnostic \feat variant using frozen visual features, to examine whether lightweight volume-intrinsic priors suffice or richer semantic cues reliably provide additional value. Extensive experiments across multiple 3D medical SSL backbones and downstream tasks demonstrate that \method-\lite consistently improves transfer performance over random sampling. Mechanistic analyses further attribute these gains to more anatomically plausible and informative observations, reduced spatial redundancy, more efficient learning dynamics, and more structured representations.
manipulation - arxiv:2610.13912 · cs.CLRSI-Anything: Unlocking Recursive Self-Improvement with World ModelsTaoyong Cui, Pinxian Zeng, Wanghan Xu, Hao Xiao +7
Recursive self-improvement (RSI) aims to transform interaction experience into persistent improvements, yet external feedback is costly and world-model predictions may become unreliable as policies evolve. We introduce RSI-Anything, a domain-general framework built on JEPA-Anything that uses predictive world models to guide action and learning-data selection. Observed feedback drives policy or workflow improvement and conditional world-model adaptation, while component and compatibility checks govern the retention of updated policy-model pairs. Across diverse computational and scientific domains, RSI-Anything demonstrates substantial gains. In code repair, with the coder fixed, success increases from 26.3% with a static verifier to 29.2% through predictive selection and 31.2% after world-model adaptation, at comparable test usage. Graphical user interface (GUI) evaluations showed higher task completion, while average actions decrease by 39.4%. Across five successive policy versions, laboratory-planning scores more than double from 21.80% to 46.01%. In reaction optimization, RSI-Anything achieves 96.15% mean best observed yield versus 82.16% for Bayesian optimization under the same 40-experiment budget. An end-to-end immune-science application further connects workflow evolution and predictive modeling with therapeutic hypothesis generation. These results demonstrate how predictive world models and retained system updates enable recursive improvement across diverse environments.
world modelself-improvement - arxiv:2610.13910 · cs.CLWhen VLMs Destroy What They Know: Spatial Representations Fall Below Lexical PriorsShubh Garg, Chen Shani
Vision-Language Models (VLMs) increasingly analyze and reason about images, yet it remains unclear whether their internal representations faithfully encode the structured relations required for such reasoning. We introduce EICS (Evaluation-Invariant Concept Stability), a metric for testing whether representations consistently encode concepts under controlled one-concept interventions, and CASP-VL (Causally controlled Spatial Perturbations for Vision-Language models), a benchmark of causally controlled spatial perturbations derived from Visual Genome scene graphs. Across multiple VLM architectures, we find that spatial relations are represented substantially less faithfully than lexical information, even when the same models score well above chance on compositional benchmarks. Further analysis shows that the relation is identifiable at the predicate's own tokens but is lost when the sentence is aggregated into a global representation, whether through the (EOS) token or by mean pooling. These findings reveal a systematic failure invisible to output-based evaluation: VLMs do not preserve, in the representation used downstream, relational information that is present in their own input.
scene graphbenchmark - arxiv:2610.13909 · cs.LGRevisiting Tabular Deep Regression: Objectives and the Limits of Global Early StoppingDanil Rudenko, Georgii Bulgakov, Nikolay Kartashev, Ivan Rubachev +2
While deep learning models for tabular data have recently received significant research attention, the choice of objective functions for regression tasks remains an understudied degree of freedom. Several lines of research offer alternatives to the standard Mean Squared Error (MSE), but differences in datasets, backbones, and evaluation protocols make their practical benefits difficult to compare. In this work, we address this gap by performing a systematic re-evaluation of regression objectives across a broad collection of established tabular datasets and multiple neural backbones. Our comparison reveals that many proposed objectives provide limited or inconsistent gains over a properly tuned MSE baseline, while quantile loss yields consistent aggregate improvements over MSE across the tested backbones. We then identify a limitation that remains even with this strong objective: regions with different levels of target noise can reach their best predictive performance at different training epochs. Consequently, a single global early-stopping checkpoint can impose a compromise between uncertainty regions, even when the objective can represent heteroskedastic target distributions. Motivated by this limitation, we introduce a heteroskedasticity-aware extension of quantile loss that uses input-dependent label smoothing as a potential remedy and improves over quantile loss on several backbones. Overall, our results provide a modern empirical picture of regression objectives for tabular deep learning and highlight how differences in optimal stopping times across uncertainty regions can limit the effectiveness of global early stopping. The code is available at https://github.com/yandex-research/tabular-regression.
evaluation protocol - arxiv:2610.13889 · cs.AIRATED: Reliability-Aware AI Agent Tool Retrieval via Execution DynamicsWeiliang Chen, Song Liao
As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance but largely ignore tool availability during execution. To address this gap, we propose RATED (Reliability-Aware Tool Retrieval via Execution Dynamics), a retrieval framework that combines robust semantic matching with dynamic reliability adaptation. RATED employs a frozen dual-encoder with contrastive fine-tuning for semantic matching, and a lightweight contextual bandit module that re-ranks candidates based on real-time execution feedback. This design enables rapid adaptation to runtime tool failures without expensive model retraining. We introduce EcoAgent, a benchmark of 5,172 real-world tools and over 210,000 query-tool pairs for offline retrieval and dynamic reliability evaluation. Experimental results demonstrate that RATED achieves a 52.2% relative MRR improvement over the ToolLLM API retriever on real-world queries, and reduces fault selection rate from 86.2% to 2.9% under severe API outage scenarios with a 30% failure rate, while incurring negligible latency overhead of less than 1 ms over encode-only inference. The code and dataset are available at https://github.com/Elliotes/EcoAgent.
agentai agentbenchmark - arxiv:2610.13886 · cs.AIX-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service EcosystemsYeonsung Jung, Zhiyuan Wang, Zifan Wang, Vítor Albiero +4
Personal agents increasingly connect to services across the web and applications by using tools. As the effects of their actions accumulate and interact across services, unintended or harmful outcomes can arise when agents fulfill benign user requests. Proactively identifying these compositional failures requires systematically exploring diverse cross-service paths. Existing red-teaming methods often simply prompt LLMs to identify potentially harmful paths from task and environment descriptions or decompose harmful objectives specified by humans or LLMs into seemingly benign action combinations. However, generation is biased toward patterns learned during training, potentially favoring familiar tool combinations and leaving novel cross-service interactions underexplored. To address this, we propose X-AgentRed, a self-evolving red-teaming framework that discovers harmful tool call paths through a graph of tool dependencies and expands and refines them using execution feedback. By analyzing each tool's effects, potential harms, and preconditions for execution, the red-teaming agent constructs a directed graph that captures how one tool's effects can satisfy another's execution preconditions. Recipes sampled from this graph are instantiated as realistic scenarios in which agents can produce harmful outcomes. Execution feedback enables self-improvement by diversifying paths that produce harm through tool substitution and refining preconditions at blocked steps in unsuccessful paths to enable further execution. Across four frontier agentic models, X-AgentRed achieves $1.77\times$ the harmful path rate of STAC and explores a more diverse set of tools, yielding $2.99\times$ the tool coverage on average.
agentagenticself-improvementself-evolving - arxiv:2610.13881 · cs.LGPrediction Is Not a Sufficient Memory StateRobert Jenkinson Alvarez
A memory that reproduces every current prediction may still have forgotten how to learn from the next observation. We characterize this distinction for exact cumulative learning and attention. For smooth convex residual losses with unrestricted real features and labels, a continuous recurrent state of fixed dimension exists exactly when the loss is polynomial. With ordinary, unweighted observations, degree $D$ requires precisely $r=\binom{d+D}{D}-1$ coordinates; even among histories with one fixed current predictor, exactly $r-d$ coordinates can remain necessary for continuation. Nonpolynomial losses have unbounded requirements on such equal-prediction histories. Bounded scalar logistic examples retain this obstruction after fixing any finite derivative jet. For ridge regression, the hidden evidence is the design matrix: the exact state costs $dp+d(d+1)/2$, versus $dp$ for the predictor. On a well-conditioned zero-prediction family, optimal $B$-bit compression has average one-update error of order $d^{-1}2^{-2B/s_d}$, $s_d=d(d+1)/2$, even with arbitrary randomized codes. Kernel attention gives a second exact closure classification. The results identify what future updates reveal, rather than proposing a new regression algorithm or asserting trained-model gains.
memory - arxiv:2610.13870 · cs.MAAsk Your Advisor: Learning When to Consult Stronger Models in Agentic SystemsPascal Sowietzki, Steffen Holter, Yannick Metz, Emil Kasper +2
To balance task performance and computational cost, agentic workflows can use a lower-cost model for execution and selectively consult a stronger model. In such executor-advisor systems, the executor decides when to seek advice, making escalation depend on self-assessment, although current language models struggle to detect where their own reasoning fails. The need for stronger reasoning emerges during execution and varies across workflow phases. We introduce ARIA, a meta-controller that learns when to consult by balancing task success against consultation cost. Our approach formulates consultation as a sequential resource-allocation problem. At workflow contact points, ARIA maps execution evidence to a compact state abstraction and selects SILENT or CONSULT, with action values learned by Monte Carlo control from cost-penalized outcomes. Across evaluated tasks of SWE-bench Verified, Terminal-Bench 2.1, and $τ^2$-bench, ARIA recovers 44-81% of the executor-advisor success gap at less than half the advisor model's cost. ARIA achieves the best observed success-cost trade-off among ten other evaluated conditions, including routing and cascading methods, fixed and prompted consultation, and random placement at matched advice volume. The policies are compact and inspectable, with a single consultation-price parameter governing the success-cost trade-off without retraining either underlying model.
agentic - arxiv:2610.13862 · cs.ROBT-Agent: Deploying Onboard Robot Agents with Behavior Trees and Multi-Fidelity EvaluationFabio Hübel, Adam Lilja, Yue Yin, Siming He +4
Deploying language-model agents onboard mobile robots requires task reasoning and responsive execution within limited compute and memory. We propose BT-Agent, an onboard architecture combining LLM-driven task decisions with predefined behavior-tree (BT) skills. These skills enforce execution conditions and return structured failure feedback. We demonstrate fully onboard operation with a 9B model on a quadruped across five task categories. Intervention tests show that local checks stop ongoing navigation without waiting for another model decision, while the agent remains active to retry or report constraints. To compare agent designs efficiently, we introduce a 161-task multi-fidelity benchmark, evaluated in text on all tasks and in Habitat on 39. Text supports 10.9$\times$ higher evaluation throughput, while simulation reveals how perception and motion failures change task outcomes. BT-Agent's largest success gains over the strongest Act/ReAct baseline occur at 4B and 9B: approximately 10 and 5 percentage points. Ablations identify structured tool calls and informative failure feedback as the most useful components.
quadrupedagentbenchmark - arxiv:2610.13856 · cs.CVEvent-based Action Recognition by Pre-Training on Multi-Frame RepresentationsEmma Norrby, Tomas Wilkinson, Per Nyblom, David Gustafsson
Action recognition is a crucial task in domains like robotics, patient monitoring, or surveillance. Recently, event-based action recognition has attracted much attention due to the event camera's ability to capture fast motions and its improved privacy over conventional vision cameras. While frame-based event representations work well for short event sequences, their discriminative ability declines sharply with longer and more complex event sequences. In this work, we introduce a multi-frame representation that greatly improves recognition performance over its single-frame counterpart. We adopt a masked auto-encoding framework to pre-train a Vision Transformer using a sparsity-aware masking algorithm and token selection mechanism to improve downstream performance and control computational complexity. We also introduce multiple mask tokens for the decoder with a position-aware attention mechanism, leading to further improved performance. Our proposed method shows impressive performance for challenging long-duration and complex event sequences, yielding state-of-the-art performance on THU-EACT-50 CHL and DailyDVS-200.
event camera - arxiv:2610.13838 · cs.ROMapless, Stabilizing, and Anti-Stuck Flipper Control for Articulated Tracked RobotsValentýn Číhala, Pavel Sarga, Martin Pecka, Tomáš Svoboda +1
Nearly every autonomous or semi-autonomous flipper controller assumes access to an elevation map of the terrain under and in front of the robot. The terrain beneath the chassis is occluded in the sensors, so the map is remembered through odometry integration, whose drift corrupts it. We present Stabilizing Anti-Stuck (SAS), a mapless controller that combines a stabilization term for body roll and pitch with an anti-stuck term that frees the robot when it gets stuck. As input, SAS uses the IMU, the flipper joint angles, and a motion cue that only tells whether the robot is moving. The cue is computed over a short window and never accumulated, so SAS does not inherit the odometry-integration drift that corrupts the map. We deploy SAS on a tracked robot with four flippers and evaluate it against manual teleoperation and prior flipper controllers in a large comparison, both in simulation and on a real obstacle. In simulation and on the real robot, SAS achieves traversal quality comparable to state-of-the-art map-based controllers. On a log hidden in tall grass, invisible to the LiDAR, the best map-based controller gets stuck while SAS traverses the hidden obstacle without a problem.
teleoperation - arxiv:2610.13834 · cs.LGOn the Design Space of Continuous Diffusion Language ModelsOscar Davis, Daan Roos, Alice Bizeul, Amitis Shidani +4
Continuous diffusion language models (CDLMs) promise to bring the benefits of continuous flow modelling to language, including accelerated sampling and controllable generation. The field has grown rapidly, and the capabilities of CDLMs have begun to rival those of discrete diffusion. Yet, unlike for continuous modalities such as images or videos, our grasp of the levers that matter when training CDLMs remains limited. In this work, we focus on two of these levers, namely self-conditioning and embedding geometry, and shed light on some of the mechanisms behind them, which in turn suggest cheaper and more effective designs. We begin by showing that self-conditioning corrects a train/inference mismatch by exposing the model to inference-like states that are otherwise rare during training. These gains can be recovered without an extra forward pass by a two-level interpolant, coined $\mathrm{DoubleCat}$, which improves TinyGSM accuracy more than threefold. Self-conditioning also aids in recognising tokens dominated by large-norm Gaussians$\unicode{x2013}$an issue known as token identifiability. To address it directly, we introduce discrete reveals to $\mathrm{DoubleCat}$, yielding $\mathrm{SemiCat}$, which achieves discrete diffusion-level performance on TinyGSM, reaching $49.94\%$ with standard training hyperparameters and a tuned sampler. At the $1.7$B scale, $\mathrm{SemiCat}$ outperforms discrete diffusion on four of six likelihood-based evaluations, and surpasses one-hot flows on unconditional generation. On embedded spaces, we find that cross-entropy drives embeddings towards a geometry whose decoding error rate closely matches the one-hot one. We briefly explore a range of further options, such as hybrid corruption processes and noise schedules, including asynchronous ones. We believe this exploration can help the community better understand and advance the design space of CDLMs.
grasp - arxiv:2610.13832 · cs.CVSpatialASM: Internalizing Active Mentalization for Spatial ReasoningYuhong Liu, Shenxi Wu, Junyi Chi, Beichen Zhang +4
When solving complex spatial reasoning tasks, ordinary humans naturally revisit the scenes from task-relevant viewpoints and mentally reconstruct the spatial layouts from those viewpoints. But can Large Vision-Language Models (LVLMs) proactively think in the same way? We term this ability Active Spatial Mentalization (ASM), an intrinsic component of visual intelligence that remains substantially underdeveloped in current LVLMs. To bridge this gap, we introduce SpatialASM, a scalable framework to internalize ASM into LVLMs through training-time spatial simulation. SpatialASM employs an allocentric novel-view generator to ground hypothetical viewpoints in visual evidence and produces two complementary forms of supervision: i) explicit ASM trajectories that teach LVLMs when and how to adaptively invoke view planning and imagination during spatial reasoning, and ii) automatically-constructed perspective-taking tasks that further strengthens viewpoint-conditioned scene imagination. On seven benchmarks spanning relatively perception-oriented spatial understanding to more challenging tasks requiring multi-image, cross-view and viewpoint-transformation reasoning, SpatialASM yields performance gain on LVLMs of four LVLM backbones in spatial reasoning while retaining their original general vision capabilities. The experimental results demonstrate that our approach improves average accuracy across the seven spatial benchmarks. And the synthesis of ASM trajectories provides a scalable pathway to alleviate the scarcity of spatial Chain-of-Thought (CoT) supervision for eliciting active viewpoint exploration and mental scene simulation.
benchmark - arxiv:2610.13829 · cs.ROMC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft AgentsJingwei Song, Zhisheng Chen, Bingfan Zeng, Jing Tang +4
A central challenge in embodied recursive self-improvement is enabling agents to convert interaction history into capabilities that persist beyond one world and transfer to later tasks. A saved memory or successful final action does not by itself establish that a reusable capability was acquired; evaluation must separate capability change from carried-over resources, unequal source exposure, and early execution failures. We construct MC-EvoBench as a controlled Minecraft benchmark with a fixed catalog of 19 registered evolution chains, including 12 primary evaluation chains and seven calibration or probe chains, together with three graph-aligned paired probe families for transfer. The benchmark represents each task as a task-state graph, defines stage-level environment verifiers, assigns matched source and target roles, resets the target world, and permits only a declared agent artifact to cross the source-target boundary. For each probe, no-prior, related, unrelated, and shuffled source conditions are evaluated under matched environment-step budgets and five seeds; we report TSR, WGP, and VMP and retain provenance records. The benchmark reveals a consistent direct-capability gap between controller and planner-backed variants, while related experience yields no stable transfer: it does not improve either tool probe, its small wood-species gain hinges on one seed, and all intervals include zero. Stage audits further show that early wood-collection and crafting bottlenecks often leave later capabilities unobserved. MC-EvoBench thus offers a controlled testbed for durable, transferable embodied capabilities. Code and data are available at https://github.com/xzw-ustc/mc-bench-open-source
embodiedmemoryagentself-improvementbenchmark - arxiv:2610.13823 · cs.AISame Query, Different Answer: Run-to-Run Variance in Semantic Query ProcessingOktie Hassanzadeh, Dharmashankar Subramanian
Semantic query engines ask a large language model (LLM) to judge individual rows, and benchmarks compare these engines on the quality of a few executions at temperature 0. We measure how much another execution changes. We re-execute the text and tabular workloads of SemBench, LRO-Bench, and UDA-Bench through their own harnesses, log every one of 1.2 million model calls, and reanalyze SemBench's published executions. At temperature 0, between 0.07% and 10.2% of rows change their operator output over five executions, depending on the model, and up to 24.0% on one task. Plans amplify these changes exponentially in the number of rows an answer exposes, as a possible-worlds model predicts: on UDA-Bench, a few percent of extracted values change, but about two thirds of the answers do. In SemBench's published results, 21% of text results change quality between executions, including on engines whose plans are deterministic. Several per-query system comparisons, and 16 of 28 tests of LRO-Bench's implementation recommendations, are not settled by the executions the benchmarks run. Changing rows are rows on which models disagree with each other; identical requests within one execution disagree as often as across executions; and one execution's decision margin or reasoning length predicts which rows change. Voting reduces the variance but does not remove it, and a calibrated cascade keeps its guarantee while the rows it returns change. We derive reporting rules for benchmarks and design rules for engines.
benchmark - arxiv:2610.13818 · cs.LGTabMF: Learning Dataset Representations with Tabular Foundation ModelsRafiq Kamel, Nicolas Atienza, Aziz Fouché, Nicola Cancedda +1
Representations of supervised datasets support higher-level machine-learning tasks such as dataset retrieval and distribution-shift monitoring. However, existing approaches typically rely either on hand-crafted meta-features or on dataset encoders trained specifically for representation learning. We introduce TabMF, a framework that repurposes pretrained tabular foundation models (TFMs) as encoders of supervised datasets. TabMF equips a predictive TFM with an architecture-aware dataset-level readout and adapts the model end-to-end using contrastive post-training on stochastic views of synthetic supervised datasets. We instantiate TabMF on TabICLv2 and TabPFN-2.5 and evaluate the resulting representations across six tasks on unseen real datasets. Simple frozen TFM readouts yield competitive representations, indicating that predictive pretraining already induces substantial dataset-level structure. The two TabMF encoders obtain the strongest aggregate performance among the evaluated learned and classical dataset representations, with particularly strong results in dataset retrieval, compact benchmark construction, and distribution-shift severity assessment.
post-trainingbenchmark - arxiv:2610.13816 · cs.RODream to Remember: Continual Steering of Generalist Robot Policies with World ModelsBahey Tharwat, Iman Nematollahi, Marvin Alles, Xingyuan Zhang +2
Generalist robot policies are trained with imitation learning and are bounded by the quality and coverage of their demonstrations. Reinforcement learning can improve and extend them, either by fine-tuning the policy weights or by training a small module to steer the input noise of a frozen generative policy. When tasks arrive sequentially, both approaches suffer from catastrophic forgetting. Fine-tuning on a task degrades prior tasks, and steering only shifts forgetting to the shared steering module. We propose Dream to Remember (D2R), which continually steers a frozen generalist policy toward new tasks, while retaining its earlier skills. As the steering module learns a new task, a frozen pretrained world model rehearses prior tasks through imagined rollouts, anchoring the module to its earlier behavior without a replay buffer or new data. When the world model is faithful enough, D2R learns the new task entirely in imagination. Otherwise, it learns the task in the environment while using the world model only to rehearse prior tasks. On CALVIN, D2R improves eight tasks in sequence entirely in imagination, raising average success from 63.7% to 74.8%, while LoRA fine-tuning on the same sequence drops it to 11.7%. With a frozen off-the-shelf generalist policy and world model, $π_0$ and A2World, D2R learns unseen LIBERO-90 tasks in the environment while keeping $π_0$'s performance on the LIBERO suites it was fine-tuned on, even though the world model is not accurate enough for policy optimization. Finally, on a real Franka robot, D2R improves three tasks in sequence entirely in imagination while retaining the earlier improvements.
liberofrankaworld model - arxiv:2610.13811 · cs.LGQTestBench: A Test Framework for Evaluating LLM-Generated Quantum CodeMeriem Terki, Nouhaila Innan, Minghao Shao, Muhammad Kashif +2
Large language models (LLMs) have shown strong results in classical code generation and are increasingly used to write the unit tests that safeguard that code. Whether they can do the same for quantum software is less clear, because quantum programs are probabilistic, depend on numerical tolerances, and are judged by domain-specific checkers, so a well-formed test can still disagree with the benchmark's verdict. Existing quantum benchmarks measure whether a model produces a correct solution, but not whether its tests can distinguish correct implementations from faulty ones. We introduce QTestBench, a framework that evaluates LLM-generated quantum test suites against independent benchmark checkers, never treating the tests themselves as ground truth. For each task, QTestBench prompts models to produce syntactic, semantic, and behavioral tests, injects candidate solutions at runtime, and compares each test verdict with the checker's label under three validation cohorts, each answering a distinct diagnostic question. We benchmark five LLMs on eight PennyLane QHack challenges and ten Qiskit HumanEval tasks. Generated suites almost always execute, but discrimination lags behind: the best generator reaches a test quality of 0.71 on QHack and 0.34 on Qiskit HumanEval, so executability alone overstates test quality. Oracle-verified synthetic mutants stabilize bug-detection estimates when natural faulty solutions are scarce, as on three of ten Qiskit tasks that yield none. QTestBench offers a reproducible, cross-framework benchmark for the trustworthiness of LLM-generated quantum tests.
benchmark - arxiv:2610.13810 · cs.CLTracing and Taming Hallucinated Terms via Subsequence-Association Filtering and Breadth-Aware Selection for LLM Query ExpansionAmit Kumar Jaiswal, Sagar Uprety, Prayag Tiwari
Large language models (LLMs) are now a standard source of query expansion terms but they hallucinate. They inject non existent entities and off-topic terms that add ranking noise and can hurt strong retrievers. Existing remedies such as corpus grounding, mutual verification and preference alignment treat hallucinated terms as an undifferentiated nuisance to be filtered by agreement heuristics, without a mechanistic account of why a given term appears or a principled criterion for how many terms to keep. We propose Subsequence-Association Filtered, breadth-aware query expansion (SAFE-QE), a training-free, retriever agnostic method that draws on the subsequence-association account of hallucination. We score each candidate expansion term by its corpus conditioned cross-context reproducibility, terms that reappear under randomised query contexts yet lack support in the pseudo-relevant set are flagged as products of dominant hallucinatory associations and down-weighted. Drawing on the characterisation of language generation as a trade-off between consistency (no hallucination) and breadth (coverage), we cast term selection as constrained coverage maximisation over the pseudo-relevant set, keeping a set that is approximately broad but consistent and stable across resampling. We also introduce the Hallucinated Expansion Term Rate, a query side faithfulness metric that counts injected expansion terms no relevant document supports. We evaluate our approach on benchmarked TREC and BEIR collections. Our SAFE-QE is statistically indistinguishable from generative and corpus-steered expansion on nDCG@10 while injecting fewer unsupported terms 4.3 per query against 27.8 for Query2doc and 57.5 for HyDE and on a strong learned sparse retriever, where every expansion method regresses. Faithfulness is therefore available at no measurable cost in ranking quality.
benchmark - arxiv:2610.13808 · cs.LGDiversity-Aware Ensemble of Quantum-Classical Models via Combinatorial FusionJingyan Xu, Yuanhong Wu, Samuel Yen-Chi Chen, Sean Patten +2
Variational quantum circuits (VQCs) are highly sensitive to circuit architecture, yet most quantum machine learning pipelines select a single best design and discard the remaining candidates. This paper addresses whether the structural diversity across quantum circuit search spaces can be used to produce stronger predictions through model fusion. We apply Combinatorial Fusion Analysis (CFA), a model fusion framework that selects and combines multiple scoring systems using rank-score function (RSF) and cognitive diversity (CD), to a pool of 29 architecturally diverse classical models and quantum circuits. Using a diversity-aware model selection method, we identify subsets of maximally diverse models and combine them with both score and rank combination. Experiments on four binary classification benchmarks covering different domains demonstrate that CFA-based hybrid classical-quantum fusion consistently outperform the best individual model on every dataset considered with improvements up to 6.03% in accuracy. When comparing with relevant literatures, the CFA framework further achieves superior performance across all four datasets.
benchmark - arxiv:2610.13804 · cs.LGConstrained Probabilistic Numerics: Gaussian Process Solvers for Linear PDEs under Linear Inequality ConstraintsBoyuan Deng, Kshitiz Upadhyay, Michael Shields
Gaussian process solvers for linear partial differential equations (PDEs) return posteriors rather than point estimates, but they condition only on equality information: the PDE residual, boundary data, and measurements. Many solutions of interest also obey inequality constraints, including nonnegativity, monotonicity, and absence of arbitrage, which equality conditioning cannot enforce. We prove that conditioning a Gaussian process prior jointly on linear equality observations and a finite-dimensional inequality event is equivalent to conditioning sequentially in terms of Borel measures on the solution space. The physics-informed posterior is therefore a valid prior for the inequality update at virtual points. The combined law is non-Gaussian yet computable through truncated-Gaussian moments, and neither the PDE conditioning nor the inequality update requires modification. We evaluated the construction on a Poisson benchmark, option-price surfaces, and air-quality fields. Under incomplete boundary data, a monotonicity constraint lowered the error of a two-dimensional Poisson reconstruction by $63\%$. On a real S&P 500 option chain thinned to $20$ retained quotes, no-arbitrage constraints reduced held-out extrapolation error by $22\%$ and cut the calendar-arbitrage rate from $10\%$ to $1\%$. On four real air-quality snapshots, nonnegativity reduced a Gaussian moment-based sub-zero-tail proxy by $74\%$ at the sparsest monitor count. Changes in mean accuracy and constraint diagnostics differed across data regimes. The probability of the noisy virtual constraint event under the equality posterior measures agreement with the specified bounds before the update. The construction turns admissibility from a post-processing step into conditioning information for probabilistic PDE solvers.
benchmark - arxiv:2610.13797 · cs.CLREFLECT: Role-Aware Detection of Sentiment, Emotion, Politeness, and FormalitySangpil Youm, Annabel Stocks Natalias, Hayden Heninger, Leah Jones +3
Detecting communicative meaning in dialogue requires modeling not only lexical content but also the participant-role structures through which sentiment, emotion, politeness, and formality (SEPF) are expressed. Existing approaches rely on contextual language representations while leaving semantic roles implicit. We introduce a role-aware transformer architecture that maps the four SEPF dimensions to theory-grounded Semantic Role Labeling (SRL) configurations, incorporating these configurations directly into the transformer's self-attention mechanism. Role-aware attention models non-directional internal states (sentiment and emotion), while directional role-aware attention captures initiator-to-recipient relations for external cues (politeness and formality). The resulting role-aware representations are fused with contextual embeddings through a learned gate that adaptively weights how much role information each input contributes, rather than appending semantic roles as an auxiliary feature vector. Across four benchmark datasets, the framework yields statistically reliable gains over strong BERT-based baselines for emotion, politeness, and formality, with gains concentrated in theoretically predicted cases such as low-frequency, complex emotions and highly polite expressions; sentiment improvements are marginal and non-significant, suggesting that sentiment is conveyed more through lexical choice than participant-role structure. Additional evaluation on real-world data demonstrates that the framework improves both predictive performance and model traceability. These results demonstrate that linguistically grounded modifications to transformer self-attention improve the detection of communicative meaning, generalize beyond benchmark datasets to real-world mental-health data, and yield traceable, role-grounded explanations that extend beyond predictive performance to interpretability.
benchmark - arxiv:2610.13790 · cs.CVOccludeBench: Can VLMs Find What's Missing?Jasin Cekinmez, Addison J. Wu, Ryo Mitsuhashi, Linrong Cai +2
How well can vision-language models (VLMs) reason about what is missing from an image? We study this question with OccludeBench, a manually curated benchmark for recovering fully occluded objects from the visual evidence that remains. OccludeBench distinguishes direct cases, where the hidden object must be recovered from a specific physical cue such as a shadow or reflection, from inferential cases, where it can be inferred from broader scene context. Across five VLMs, accuracy averages 42.7% on direct cases versus 62.7% on inferential cases, exhibiting a 20.0-point gap. Humans attain higher accuracies of 63.4% versus 68.5% for direct and inferential images, respectively, with no significant gap. To locate this failure, we introduce OccludeTrace, a four-stage diagnostic that isolates where the visual reasoning process breaks down. The bottleneck emerges when models must recover the relevant object from the projection within the full image: they succeed on only 50% of failed examples, compared with 91% of examples they answer correctly. Extended reasoning, tool use, and few-shot prompting yield inconsistent improvements and do not reliably eliminate the gap. In contrast, an inpaint-then-confront intervention, which prompts models to first generate a candidate hidden object and then evaluate that hypothesis against the visible physical cue, reduces the gap to a statistically non-significant difference for both models with image-generation capabilities. Together, our results establish a tractable, controlled diagnostic for isolating how VLMs reason about visual content that is missing from an image.
tool usebenchmark - arxiv:2610.13783 · cs.CVUkrMeme: Multimodal Explainable Persuasion Detection in Ukrainian MemesNazar Andrushko, Vera Schmitt, Veronika Solopova
Memes play a central role in modern online communication, especially in contexts of political conflict where visual and textual cues combine to convey persuasive messages. We study persuasive technique detection in Ukrainian memes using vision-language models (VLMs). We introduce UkrMeme, a dataset of 200 organically produced Ukrainian wartime memes annotated for persuasion techniques, and PTM-UA, a Ukrainian translation of a subset of the Propaganda 950 benchmark that preserves original visual content while translating meme text. We evaluate VLMs in a zero-shot prompting setup across image, text, and multimodal inputs using hierarchical F1 metrics. Finally, we compare Layer-wise Relevance Propagation (LRP) and model-generated token attributions and analyze the semantic categories of evidence emphasized by each explanation method.
benchmark - arxiv:2610.13781 · cs.CVSimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action ModelsChanghui Jing, Haochen Tian, Hongchen Li, Tianyu Li +7
Driving world action models (WAMs) learn from paired trajectories and future observations. Post-training with reinforcement learning allows the policy to explore alternative trajectories and improve planning using driving rewards. However, driving logs contain future videos only for the recorded trajectories, leaving these alternatives without corresponding visual supervision. Thus, we introduce SimVTA, a simulation-grounded post-training framework that combines trajectory optimization with video supervision. First, we sample candidate trajectories for each observation and use a real-world simulator (e.g., World Engine) to render future videos for high-reward candidates in real-world scenes reconstructed with 3D Gaussian Splatting (3DGS). This provides trajectory-matched supervision independent of the model's own predictions. Under a limited rendering budget, we prioritize video supervision for higher-error futures among these rendered candidates. Finally, we optimize trajectory planning with Group Relative Policy Optimization (GRPO) and use a flow-matching loss on the matched videos to update shared representations. At inference time, the model predicts trajectories directly, without simulator calls. On NAVSIM v1, applying SimVTA to a WAM initialization improves PDMS from 86.2 to 91.3 (+5.1). It achieves 88.2 EPDMS on NAVSIM v2 and an average HD-Score of 38.8 in closed-loop evaluation on HUGSIM. Ablations show that updating shared representations with video supervision improves planning, while prioritizing higher-error futures among high-reward trajectories further improves performance.
post-training - arxiv:2610.13780 · cs.CVDetection of extremely rare dead cells in fluorescence microscopy imagesPrateek Verma, Benjamin Butter, Jian Zhang, Xintao Wu
Dead cell detection in fluorescence microscopy is essential for phenotypic screening and drug efficacy assessment. However, automated identification remains challenging due to signal variability, optical artifacts, and colocalization ambiguities across multiple channels. Markers that define nuclear boundaries do not neatly coincide spatially or temporally with apoptotic markers. Furthermore, marker accumulation kinetics vary across individual cells and apoptosis stages, making universal thresholds unreliable. We present a systematic comparison of several computational approaches for detecting apoptotic cells in nucleus-stained specimens: (1) heuristic methods using intensity thresholds, distributions, correlations, and domain guidance; (2) classification using numerical features (Logistic Regression, Random Forest, XGBoost and LightGBM) and image features (ResNet-18 and EfficientNet-B0); and (3) anomaly detection, also using numerical features (Isolation Forest, one-class SVM and PCA reconstruction) and image features (convolutional autoencoders and Deep SVDD). Using a dataset of 258 images containing 65,527 cells/nuclei across multiple scenes with 243 manually annotated ground truth dead cells, we evaluate each method on metrics such as PR-AUC, Precision, Recall, F1-score, and macro-F1. Our results indicate that classification using image features (deep learning) and numerical features (traditional) achieved the best performance, with ResNet-18 and XGBoost significantly outperforming manually designed heuristics and anomaly detection methods. Our findings demonstrate that such biomedical problems remain highly challenging to solve even with the state-of-the-art computational and learning techniques. We aim to provide an effective decision-support tool to researchers while tackling such problems either fully-automatically or in a human-in-the-loop setting as an aide to domain scientists.
human-in-the-loop - arxiv:2610.13778 · cs.LGReplaySSM: Cache SSM Inputs, Not StateZe-Wei Liou, Harris Nover, Amey Naik, Andrii Skliar +3
State-space models (SSMs) maintain a fixed-size recurrent state, but reading and writing it at every decoding step can bottleneck hybrid models. This eager state management causes large state I/O with low arithmetic intensity, leaves speculative decoding no cheap rollback, and feeds state quantization error into subsequent recurrent updates. We introduce ReplaySSM, which unrolls the recurrence to represent the state as a checkpoint and a buffer of recent SSM inputs. This separates output computation from checkpoint updates. By updating the checkpoint periodically, ReplaySSM avoids state writes on most steps and roughly halves the dominant state memory traffic. Keeping recent inputs also makes speculative rollback a buffer-pointer operation and enables output-only verification without materializing intermediate states. The same separation allows a low-precision checkpoint to serve output computation on most steps while a higher-precision checkpoint serves recurrent updates, so rounding error in the low-precision copy never enters later updates. We implement ReplaySSM in vLLM for Mamba-2 and Gated DeltaNet. At serving batch size 256, it accelerates standard decoding by $1.20$--$1.47\times$ over a tuned vLLM baseline across four hybrid models, and delivers about $1.8\times$ the throughput of vLLM's speculative decoding on the two 120B-class models. Separate state precisions also reduce output KL divergence and downstream accuracy losses compared with a shared low-precision checkpoint.
memory - arxiv:2610.13772 · cs.ROMARGoS: A Configuration-Driven Platform for Reproducible MARL Experiments in ARGoSTom Philipp Backert, Mohammad D. Soorati, Javad Ghofrani
Multi-agent reinforcement learning (MARL) has become a prominent research direction, particularly within collective robotics, where the ARGoS simulator is widely used to study emergent swarm behavior. Yet despite this growth, systematic support for reuse and reproducibility in MARL-based swarm robotics remains limited and insufficiently standardized: a single experiment is assembled from manually aligned simulator files, training scripts, configuration values, paths, seeds, and environment details, so reuse and reproduction stay fragile even within one research group. To address this gap, we introduce MARGoS, a lightweight, configuration-driven platform developed in this project that elevates these experiment-defining inputs to first-class, platform-managed artifacts. MARGoS enables reproducible experimentation through configuration hashing, end-to-end seed propagation, frozen (immutable) configurations, structured logging, environment fingerprinting, and exportable experiment bundles that facilitate sharing, replay, and verification of results across machines and over time. A five-dimension evaluation (architecture, efficiency, reproducibility, usability, and collaboration) supports our claim that managing experiment variation as a platform responsibility makes ARGoS+MARL experiments easier to reuse, reproduce, and hand off. Our code is available at https://github.com/tombackert/margos.
multi-agent - arxiv:2610.13767 · cs.LGDualQuant: Dual-scale Calibration-free Weight-and-Activation Quantization for LLMsMahsa Salmani, Sayeh Sharify, Hesham Mostafa
Low-bit inference on accelerators with native 4-bit support requires quantizing both weights and activations to realize the full throughput gains these formats provide. While post-training weight quantization has been extensively studied, activation quantization remains considerably more challenging and typically requires calibration data. In this work, we introduce DUALQUANT, a dual-scale, calibration-free post-training quantization framework that directly minimizes the weight-reconstruction Mean Squared Error (MSE) and, as an immediate by-product, yields per-channel activation rescalings prior to activation quantization. Our key observation is that the scaling factors obtained by minimizing weight-reconstruction error provide effective activation rescalings, enabling competitive activation quantization without calibration data. We formulate DUALQUANT as a non-differentiable weight-reconstruction problem and develop an efficient solver based on variable splitting and block coordinate descent, where each subproblem admits a closed-form update. DUALQUANT provides a unified algorithm supporting a wide range of formats, including the full MX family and NVFP4. To our knowledge, DUALQUANT is the first dual-scaling method to formally support MX and NV block formats. Across Llama and Qwen models evaluated on WikiText-2, C4, and zero-shot downstream tasks, DUALQUANT matches or exceeds the accuracy of calibration-based SmoothQuant across most models and formats, and substantially outperforms calibration-free baselines, with large gains for MX and NV block formats. We validate these gains with a real packed W4A4 inference path for Llama-3.1-8B on an RTX 4090. The resulting implementation closely matches the accuracy of fake quantization while delivering up to 2.61x memory reduction and up to 2.46x throughput speedup over BF16.
memorypost-training - arxiv:2610.13763 · cs.CVNeurons++: A Unified Visual-Stream Framework for Image and Video Reconstruction from fMRI with Neural-to-Visual InterpretabilityHaonan Wang, Yuchen Wang, Jingyu Lu, Qixiang Zhang +3
Decoding visual experience from fMRI is important for understanding human perception and developing brain-computer interfaces. Recent generative decoding methods can reconstruct plausible images and videos, but visual plausibility alone does not ensure that the output is faithfully grounded in brain activity. In this work, we propose Neurons++, a visual-stream fMRI reconstruction framework for both static image and dynamic video reconstruction. Compared with our conference version Neurons, Neurons++ extends the paradigm from video-only reconstruction to visual-stream reconstruction for both images and videos, and replaces parallel task conditioning with serial cortex-inspired decoding. The model first uses image-fMRI pretraining to obtain a stable spatial-semantic initialization, and then performs subject-specific fine-tuning for image and video reconstruction separately. The serial design organizes fMRI-derived representations into explicit spatial, semantic, language-level, and temporal cues. Extensive experiments show that Neurons++ achieves state-of-the-art video reconstruction and competitive image reconstruction across standard benchmarks. Beyond reconstruction fidelity, neural-to-visual analyses indicate that Neurons++ exhibits qualitative directional controllability under neural perturbation, that its fMRI encoder read-out is sensitive to stimulus-relevant cortical features, and that it supports ROI-guided semantic modulation. Code and model weights are available at: https://github.com/xmed-lab/NeuronsPlusPlus.
benchmark - arxiv:2610.13757 · cs.CVGaussian Splatting with Reflections Guided by What is SeenYiming Liang, Tianyu Xiao, Hiroshi Ishikawa
While novel view synthesis methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have shown impressive performance on common scenes, they often struggle with capturing view-dependent specular effects, particularly near-field reflections. Existing methods utilize environment maps, which only represent lights from infinity, or environment Gaussians, which rely solely on indirect supervision from reflections, are insufficient for accurately modeling such effects. Here, we propose a framework based on 2D Gaussian Splatting (2DGS) that leverages directly observable environment information in input images. Our approach also integrates a hybrid reflection appearance representation and view-dependent specular modeling. Experiments on public benchmarks and a newly curated near-field reflection dataset demonstrate that our method achieves superior rendering quality and geometric accuracy.
benchmark - arxiv:2610.13755 · cs.LGMatched-Context Group Policy Optimization for LLM Agent TrainingChenxu Zhang, Yaorui Shi, Wenlong Zhang, Jianchao Tan +2
Training long-horizon language model agents requires assigning credit to intermediate decisions from sparse terminal feedback. Within a finite group of sibling rollouts, useful action comparisons depend on their context, evidence for both alternatives, and how that evidence enters learning. We propose Matched-Context Group Policy Optimization (MCGPO), a procedure for constructing weighted action preferences from already collected trajectories. MCGPO defines comparison contexts with pre-action state summaries and observed rubric progress, annotated by task rules. Two-action support selects among ordered exact and coarse matching rules. Fixed folds separate candidate decisions from the terminal outcomes used to orient their preferences, and support-dependent evidence weights scale an auxiliary pairwise objective alongside shared GraphGPO task learning. MCGPO reuses rollout data and each response's original history, preserving critic-free training. Across six environment-backbone settings with three training seeds each, MCGPO improves mean success over matched GraphGPO: by 0.47-1.46 percentage points on ALFWorld and WebShop with Qwen2.5-1.5B and 7B, and by 3.96 and 5.16 points on WebShop with Qwen3-4B and 8B. The ALFWorld gains build on baseline success above 92%, where remaining headroom is limited. Integrated success improves in three of four Qwen2.5 settings. Three-seed factorial controls support opposite-fold evidence and evidence weighting; joint state-rubric matching achieves the highest mean in all four representation-control settings.
agentllm agent - arxiv:2610.13740 · cs.ROSmolWAM: A Latent World-Action Model for Robotic Manipulation on Edge DevicesTimi Owolabi, Hikmah Olawore, Frances Adelakun, Ayotomiwa Oyewumi
World-action models (WAMs) predict a robot's actions together with the observations those actions will produce. However, the strongest models rely on video diffusion transformers that are far too computationally expensive for resource-constrained edge devices. We present SmolWAM, a latent WAM that we derive from the 2B-parameter Cosmos Policy by keeping its pretrained trunk and rebuilding its inference interface: single-frame visual latents, cached text features that preserve the trunk's attention sinks, 12 of 28 transformer blocks, and 1,008 tokens from which actions and future visual latents are read out in one rectified-flow step. Trained in 3.6 GPU-hours, SmolWAM succeeds in 95.5% of 400 LIBERO episodes at 57 ms and 2.3 TFLOP per 16-action chunk with 2.4 GiB of GPU memory, 11x faster than its teacher with 18.5x fewer FLOPs and 3.2x less memory, and its world head still forecasts scene motion.
manipulationlibero - arxiv:2610.13737 · cs.LGSafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement LearningHongrui Zheng, Aditya Singh, Rahul Mangharam
Cooperative multi-agent tasks often impose constraints on a shared objective or collective safety. A team level violation cost function can measure this constraint outcome, but does not distinguish which agents' actions most strongly influence that violation. We present SafeDiSTL, a constrained multi-agent reinforcement learning framework that allows for credit assignment even with joint constraint measurements. We use Signal Temporal Logic (STL) robustness to measure episode-level violation through running-maximum cost increments. Smooth full-episode robustness and differentiable dynamics provide action sensitivities, which allocate each cost increment across agents at the same decision time. These sensitivities account for delayed effects when weighting agents' shares of each cost increment. We study the framework in cooperative payload transport, connected navigation, and networked traffic control tasks. SafeDiSTL achieves 1.6-5.1x the safe-success rate in transport, improves navigation safe-success by 11.1%, and delivers 50-68% more throughput in traffic when compared to constrained baselines. Results demonstrate a strong improvement of the learned policy in dealing with shared constraint while retaining the performance of unconstrained policies.
multi-agent - arxiv:2610.13735 · cs.LGOrthros: Phase-Aware Heterogeneous Attention for Efficient TransformersYuhong Chou, Zehao Liu, Yuqi Pan, Qian Liu +3
Efficient attention mechanisms, such as linear and sliding window attention, aim to reduce the computational complexity of Transformers from quadratic to linear. However, their degraded in-context recall often necessitates interleaving full attention layers, leaving the quadratic bottleneck unresolved in long-context processing. To address this, we introduce Orthros attention, which shifts the efficiency paradigm from structural allocation to phase-aware decoupling. As a unified module, it dynamically switches its computation pattern across different phases of sequence processing, enabling linear complexity prefilling and full attention decoding. Our design grants Orthros attention a lower asymptotic complexity compared to vanilla Transformers in prevalent long-context scenarios characterized by heavy prefilling and light decoding. Beyond theoretical formulation and complexity analysis, extensive empirical evaluations demonstrate Orthros's superiority across multiple dimensions. First, we validate its fundamental language modeling capabilities, demonstrating scalability across varying model sizes and strong competitiveness in comprehensive architectural comparisons. Second, Orthros exhibits exceptional conversion feasibility via a data-efficient Transformer-to-Orthros conversion, yielding performance that even surpasses the original Transformer. Finally, Orthros achieves a $21.9\times$ prefilling speedup over Transformers with end-to-end inference gains, while preserving long-context capabilities, as demonstrated by near-perfect 128K needle-in-a-haystack results and Transformer-level performance on real-world in-context recall tasks. Overall, these advantages in high performance, flexibility, and efficiency position Orthros as a promising candidate to succeed the Transformer in industrial applications.
long-context - arxiv:2610.13732 · cs.ROLAPT-Scale: Scaling Embodied Policies with Latent Action Pre-Training on Human VideosZhiyuan Xiang, Peidong Liu, Mingyang Li, Jiawei Li +3
Scaling generalist robotic policies is limited by the high cost of collecting embodied interaction data. Large-scale egocentric human videos offer a rich alternative, but they lack robot action labels, and existing action annotation methods are often noisy under real-world visual complexity and diverse manipulation dynamics. We introduce LAPT-Scale, a scalable latent action pre-training paradigm with two components: LAPT-Scale-LAM learns continuous latent actions by explaining frame-to-frame visual transitions in human videos and uses them as human-derived supervision, while LAPT-Scale-Policy trains a VLA policy through human-video latent-action pre-training, target-robot embodiment alignment, and task-specific post-training. Unlike prior vector-quantized LAMs, LAPT-Scale-LAM uses a continuous latent space to preserve fine-grained motion and interaction dynamics. We further combine perceptual, semantic, and optical-flow alignment signals to improve transition-level supervision beyond pixel reconstruction. Trained on 23.3K hours of egocentric video, LAPT-Scale-LAM provides implicit action supervision for policy pre-training, yielding consistent scaling gains and improving real-robot success from 63.3% to 85.0% as annotated human video scales from 1K to 5K hours. The learned policy also generalizes to unseen visual conditions.
vlavla policyembodiedmanipulationpost-training - arxiv:2610.13730 · cs.LGSeoulMMOD: A Large-Scale Multimodal Origin-Destination Flow BenchmarkTaeyoung Yu, Seonbin Jo, Jiwon Kim, Junyoung Byun
Origin-destination (OD) flow forecasting supports urban mobility decisions by predicting the volume and patterns of human movement across a city. Most existing public OD benchmarks provide only a partial view of citywide mobility, covering a single transport service or at most two modes. With partial mode coverage, observed demand changes are difficult to separate into shifts across transport modes and changes in total travel. We introduce SeoulMMOD, a large-scale public benchmark for citywide multimodal mobility in Seoul. SeoulMMOD provides three years of hourly OD flows estimating total mobility for 6 urban travel modes across 25 districts and 426 sub-districts, together with travel-time, travel-distance, calendar, rainfall, and point-of-interest (POI) signals. Using SeoulMMOD, we benchmark 14 forecasting baselines under a common protocol and analyse the effects of spatial scaling, joint versus mode-separate training, and cross-year generalization. Results show that several spatio-temporal models that work at district level do not scale to sub-district OD forecasting, and that naive joint multi-mode training does not consistently improve accuracy. Together, the dataset and benchmark establish a reproducible testbed for multi-mode, multi-year OD forecasting at the city scale.
benchmark - arxiv:2610.13724 · cs.LGAmortized Counterfactual Prediction with Graph Neural NetworksHendrik Stumpf, Francesco Quinzan
Counterfactual inference asks how an observed outcome might have differed under different circumstances, such as whether a patient would have recovered had they received a different treatment. Such questions arise whenever decisions depend on the outcomes of alternatives that were not observed. Answering counterfactual queries generally requires knowledge of the underlying causal structure, which is often unavailable in practice. A common approach is therefore to first estimate the causal graph from observational data and then perform counterfactual inference. However, errors in the estimated causal graph can propagate to downstream counterfactual predictions. To address this challenge, we introduce the Counterfactual Graph Neural Process (CFGNP), an end-to-end approach that answers counterfactual queries directly from observational data without first estimating a causal graph. CFGNP uses Graph Neural Networks (GNNs) to exploit the dual-graph structure by restricting cross-world message passing to corresponding factual--counterfactual variables. Across synthetic and image-based benchmarks, CFGNP achieves stronger predictive performance than existing approaches, including on the German Loan benchmark, where it reduces MSE from $4.51 \times 10^{-2}$ to $0.19 \times 10^{-2}$. Furthermore, on synthetic causal graphs, a model trained only on 10-node graphs maintains strong predictive performance on graphs with up to 30 nodes, without retraining.
benchmark - arxiv:2610.13722 · cs.CLEnhancing Legal Reasoning in Pre-trained Language Models via Knowledge Graph-Guided Multi-Task Pre-trainingIbrahim Siddig, Munir Georges
Legal language understanding requires reasoning over semi-structured regulatory documents, yet standard pre-training objectives do not explicitly target this structural capability. Because current legal language models rely solely on masked language modeling, they treat statutory text as flat token sequences and ignore the underlying hierarchical constraints. To bridge this gap, we present a multi-task pre-training approach for German traffic law (StVO). Our approach combines three complementary objectives: Next Sentence Prediction (NSP), Knowledge Graph (KG) Guided Clustering (CLU), and Knowledge Graph (KG) Aware Paragraph Classification (CLS). This approach explicitly encodes structured legal knowledge directly into the model weights. This encoding enables zero-shot legal reasoning at inference time and removes the need for discrete graph traversal. We evaluate our approach across nine Transformer-based encoders and 324 experimental runs. On synthetic StVO question answering, our models demonstrate consistent relative improvements between 10.3% and 155.0% over baselines. Furthermore, relative to the established LexGLUE baselines (Chalkidis et al., 2022), our models improve over prior results on four of seven legal benchmarks. It also achieves consistent zero-shot transfer gains between 3.4% and 15.8% on Austrian driving regulations. These experimental results indicate that our training approach generalizes successfully beyond the initial training legal domain.
knowledge graphbenchmark - arxiv:2610.13720 · cs.CVState-Isolated Vision Mamba via Update-Tendency Routing for Underwater Image EnhancementYan Luo, Laibin Chang, Zefan Feng, Yi'ang Chen +2
Vision Mamba has recently emerged as an efficient alternative to convolutional and Transformer-based architectures by modeling long-range spatial dependencies through recurrent state evolution. Existing studies primarily improve token serialization, scanning strategies, or expert routing, yet largely overlook a state level question question: how should recurrent states be organized for spatially heterogeneous visual restoration? In this paper, we show that forcing tokens with heterogeneous update behaviors to recurrently modify a shared hidden state leads to persistent cross-content interference, which we term \textbf{State Contention}. We further argue that effective recurrent modeling should organize state evolution according to token compatibility rather than token ordering. Based on this observation, we introduce \textbf{State Isolation}, a new recurrent state organization principle for Vision Mamba,tokens with compatible state-update tendencies evolve within independent recurrent state streams. To instantiate this principle, we propose \textbf{IsoMamba}, a $Δ$-guided architecture that constructs model-intrinsic update representations, discovers update-compatible token groups through label-free clustering, and routes them to isolated Mamba experts following a \textbf{cluster--route--isolate} paradigm. In addition, we develop a dynamic channel-wise reweighting objective to compensate for wavelength-dependent reconstruction difficulty in underwater images. Extensive experiments demonstrate that IsoMamba consistently achieves state-of-the-art performance on multiple underwater image enhancement benchmarks while providing cleaner hidden state responses, validating the effectiveness of state isolated recurrent modeling.
benchmark - arxiv:2610.13710 · cs.MAOpenSocialJax: Evaluating Social Adaptation in Sequential Social Dilemmas with Open-Ended Environmental DynamicsZihao Guo, Meng Fang, Joel Z. Leibo, Yali Du
Sequential social dilemma benchmarks capture diverse social interactions, but rarely test whether agents can infer hidden environmental rules through repeated interaction while adapting to other agents. We introduce \textbf{OpenSocialJax}, which extends Clean Up and Commons Harvest across an open-ended distribution of latent environment configurations, systematically varying spatial layouts and hidden rules governing tool crafting, payoffs, and resource dynamics. Each episode samples one configuration from tens of millions of possibilities and holds it fixed across five trials. We evaluate eight large language models, including three closed source models and five open source models. Our evaluation tests whether models can discover hidden rules and adapt to other agents in homogeneous and mixed teams. We find that rule discovery often improves performance but does not reliably sustain cooperation, as the cleaning burden becomes concentrated among fewer agents in OpenCleanup and every team eventually exhausts the shared resource in OpenHarvest. In our mixed arena, one cooperative agent was able to sustain the public good in OpenCleanup at a cost to its own return, but could not prevent resource depletion in OpenHarvest. Together, these results highlight the difficulty of adapting jointly to unfamiliar environmental dynamics and the changing behavior of other agents.
agentbenchmark - arxiv:2610.13708 · cs.LGAdaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV HierarchyNaji Alazhar, Wassel Alazhar
Long-context serving runs out of KV memory before the hardware reaches its useful throughput. HiSparse stores history in host memory and fetches only the selected entries, but it uses one cache budget at every load and does not handle draft-model speculative decoding such as DSpark and DFlash2. We present Adaptive DHiSparse, which supports speculative decoding over hierarchical sparse KV and adapts residency to load. It protects the required working set, retains additional history while GPU memory is spare, and recovers the rest through exact fused retrieval. DSpark and DFlash2 keep their proposal and acceptance rules: queries share missing-row retrieval, draft KV uses a window-bounded ring, and verification staging is reused across layer groups. At 100K context and concurrency 128, GLM-5.3 with DFlash2 delivers 793 output tokens/s per decode GPU, 1.45$\times$ HiSparse and 1.27$\times$ non-speculative adaptive serving. Held to the same latency bounds as HiSparse, it sustains up to 4$\times$ the concurrency and 2.3 to 3.7$\times$ the output, depending on the per-token bound. On DeepSeek-V4.1-Flash at 500K context and concurrency 512, Adaptive DHiSparse with DSpark delivers 1.85$\times$ the output of resident serving with DSpark. In a load step, optional residency reduces host fetches from 14.2% to 1.4% of selected rows at low load and releases memory under pressure.
memorylong-context - arxiv:2610.13706 · cs.CVGLIMPSE: Global-Local Indexing with Multi-Precision Spectral Encoding for Explorable Video World ModelsZhufeng Xu, Henglei Lv, Bailin Deng, Yikang Ding +4
A camera-controlled video world model must keep a scene consistent when the camera returns to it. Memories that render stored features into the target frame can turn depth and pose errors into ghosting or duplicated structure. Positional transport avoids that resampling by relocating a historical patch's address rather than its content, but assigns full positional precision even to inaccurate projections. We present GLIMPSE, a global-local memory interface with band-wise multi-precision coordinates and geometry-conditioned spectral attenuation to reduce sensitivity to inaccurate projected addresses. Local patch memory supplies view-specific appearance, while recurrent global memory provides scene context. Footprint-guided retrieval selects historical patches under a fixed local read budget. Under matched retrieval and read budgets, GLIMPSE improves geometric correspondence and photometric consistency over deterministic positional transport.
world modelmemory - arxiv:2610.13703 · cs.AIA Baseline Assessment for the Agentic Web Technology StackVagner Figueredo de Santana, Diogo Cortiz
The fast pace in which protocols, frameworks, and technologies are being proposed for LLM-based agents results in a complex scenario for anyone aiming to create state-of-the-art AI solutions. Without an assessment on how different protocols, frameworks, and libraries work together to compose an Agentic Web solution, developers and organizations face different challenges (e.g., skilling, governance, infrastructure) even before becoming part of the Agentic Web ecosystem. In this context, we propose a system for performing Agentic Web evaluations called MASTIF (Multi-Agent System TestIng Framework) and present a baseline assessment of Agentic Web technologies, including 3 LLMs, 3 protocols, and 4 agent implementation frameworks, against 300 Mind2Web benchmark tasks. Results suggest that selecting a task-specific technology stack may result in gains of task completion rate, efficiency score, and social value stability scores; and reductions in verbosity and time to complete tasks. With the presented results, we expect to present a baseline in terms of metrics and results for this complex and fast evolving scenario for those aiming at designing, assessing, and developing multi-agent systems.
agentmulti-agentagenticagent systembenchmark - arxiv:2610.13697 · cs.CVImproving Semantic Coverage in AI Test & Evaluation through Generative AugmentationConnor Hashemi, Bharadwaj Ravichandran, Connor Anderson, Shitij Govil +3
In test and evaluation (T&E) of AI models, evaluators typically have access only to a held-out test dataset and no knowledge of the training data or its semantic composition. If critical input conditions---such as time-of-day, weather, or scene location---are underrepresented in this test dataset, T&E results can be misleadingly due to this semantic coverage gap. We propose a three-stage generative AI pipeline to detect and fill such semantic gaps without requiring ground-truth labels of these semantics. First, vision-language models (VLMs) perform zero-shot binary labeling of semantic factors, and an embedding-space clustering step identifies which semantics most affect downstream model behavior. Second, diffusion-based image-to-image models transform existing covered images into the underrepresented semantic domain, preserving scene content while augmenting high-level appearance. Third, statistical analysis of the augmented image embeddings verifies that the synthetic imagery improves dataset coverage before it is incorporated. Crucially, the synthetic data is used only to enrich the test set and no model retraining is performed for T&E. We validate the full pipeline on both image classification and object detection under day/night semantic gaps, showing that the augmented test datasets better distinguish models with and without exposure to the missing semantic, thereby yielding T&E conclusions that more closely match those of an ideal, fully covered dataset. Code available at https://github.com/Hashe037/DEDUCE
evaluator - arxiv:2610.13695 · cs.CLVerifiable Retrieval for Legal Reasoning through Structure-driven Knowledge GraphIbrahim Siddig, Sviatoslav Tugeev, Munir Georges
Any automation within reliability-critical contexts such as medicine or law has to be transparent and verifiable. Despite their advantages, current LLM-based systems do not meet these requirements due to their inherent black-box nature. Retrieval Augmented Generation (RAG) attempts to ground the generative process in the relevant interpretable documents, thereby reducing the risk of AI 'hallucinations' and potentially enabling verification of the initial generation context. However, as the number and size of potential sources increases, naive retrieval approaches tend to perform worse, ignoring critical context elements. In this paper we aim to tackle this problem in the context of German Legal Code. Using structure-driven parsing to create a Knowledge Graph (KG) for the source document navigation and retrieval, we compare several KG-informed chunking and retrieval strategies and evaluate their effect on the accuracy of retrieved citations.
retrieval augmentedknowledge graph - arxiv:2610.13688 · cs.ROTowards a Unified Taxonomy of Agricultural Harvesting Technologies: Linking Physical Interaction, Automation, and SelectivityRenato Cristiano Torres, Fabiano Mariath D Oliveira, Claudio Gottschalg Duque
Harvesting technologies have evolved from conventional mechanized systems based on bulk mechanical interaction toward increasingly automated and robotic systems capable of perception, decision-making, and localized actuation. This evolution has also created a classification problem, as harvesting systems are commonly described according to crop type, mechanical removal principle, sensing technology, robotic architecture, or degree of automation, making direct comparison difficult. This paper proposes a unified taxonomy for agricultural harvesting technologies based on two primary classification axes: the physical principle governing plant-machine interaction and the level of automation incorporated into the harvesting process. Selectivity is treated as an emergent functional attribute that expresses the biological and spatial scale at which perception and decision-making influence physical actuation. Conventional mechanized methods, including cutting, pulling, vibration, impact, brushing, pneumatic action, and combined systems, are analyzed together with semi-automated and robotic harvesting approaches. The analysis shows that increasing automation does not necessarily result in greater selectivity. A qualitative transition occurs when perception and decision-making directly influence product-level actuation, shifting harvesting from distributed or bulk interaction toward localized and selective manipulation. The proposed framework provides a common conceptual basis for positioning and comparing mechanized, automated, and robotic harvesting technologies. By separating the physical mechanism of product removal from the automation level and resulting selectivity, the taxonomy clarifies technological boundaries, identifies intermediate configurations, and supports the analysis and development of future harvesting systems.
manipulation - arxiv:2610.13676 · cs.LGOn the Encoding of Calendar Features in Covariate-Informed Time Series Foundation ModelsAlexander Kreusel, Maximilian Beichter, Alexandra Nikoltchovska, Benjamin Schäfer +3
Time series foundation models (TSFMs) increasingly offer covariate support, with calendar information being the most common type of categorical covariate in practice, as it is available for every point in time. However, how these features are encoded is largely treated as an implementation detail rather than as an object of study, despite encoding being one of the few design choices left for pretrained models at inference time. With the present study, we demonstrate that the way information is propagated into the model substantially affects forecast accuracy of TSFMs. Therefore, we systematically compare seven calendar encodings, including three conventional target-agnostic representations (ordinal, one-hot, and cyclic) and four target encodings, across four state-of-the-art TSFMs on nine datasets from multiple domains in a zero-shot rolling evaluation. The nine datasets are influenced by social activities, such as weekends and holidays, making calendar information particularly relevant for forecasting. We find that encoding choice affects forecast accuracy across all models, with MASE differences of up to 9.9 % on non-holidays and 83 % on holidays within a single model. Effectiveness and utilization vary substantially across models. Improvements are concentrated around holidays, where calendar information provides signals unavailable from target history, while some model encoding combinations also improve non-holiday forecasts. A SHAP-based attribution analysis locates the contribution of the covariates relative to the autoregressive component and explains why some model-encoding combinations degrade performance. Our findings suggest that current benchmarks for covariate-informed TSFMs can distort model comparisons by imposing fixed encoding strategies.
benchmark - arxiv:2610.13675 · cs.CVCan Multimodal Decision Models Classify Breast Ultrasound Images? Benchmarking CLEF and CLEF-Flash Across Prompts and DatasetsTran Cao Minh, Hai Tran, Ha Minh Tan
Multimodal decision models return probabilities over predefined alternatives, offering a structured interface for image classification. This study benchmarks inference with CLEF and CLEF-Flash on 2818 breast ultrasound images from Dataset B, BUSI, and BUS-BRA. Dataset B and BUS-BRA use binary benign-malignant classification, whereas BUSI includes normal, benign, and malignant categories. Model parameters remain unchanged, and original images are submitted without user-defined preprocessing. Three prompts provide minimal labels, an explicit classification task, or sonographic criteria. We report accuracy, macro F1, balanced accuracy, macro precision, throughput, and latency. CLEF-Flash with the clinical prompt achieves the highest accuracy on all three datasets: 74.85% on Dataset B, 66.28% on BUSI, and 51.63% on BUS-BRA. On BUSI, however, CLEF with the task-guided prompt achieves the highest macro F1 (64.51%) and balanced accuracy (68.72%). CLEF-Flash has lower latency in every matched comparison. Clinical instructions improve CLEF-Flash accuracy relative to the minimal prompt but reduce CLEF accuracy on all datasets. Confusion matrices reveal frequent benign-to-malignant errors, particularly on BUS-BRA, where all configurations fall below the 67.63% accuracy of a majority-class predictor. These findings demonstrate dataset-and prompt-dependent performance and motivate class-specific evaluation before applying multimodal decision models to breast ultrasound analysis.
benchmark - arxiv:2610.13672 · cs.AIInject a Turn, Not a Token: Learning Where to Redirect LLM Reasoning for Self-CorrectionJiwon Jeon, Myungsik Cho, Jeonghye Kim, Youngchul Sung
Large language models struggle to reliably identify and correct errors in their own reasoning. Unlike prior training-based approaches that fine-tune an LLM to generate revisions or feedback, we learn where to intervene in failed rollouts and determine how to redirect them. To choose where to intervene, we train a 130K-parameter MLP head on a frozen encoder using only final-answer correctness. For redirection, we find that under a fixed generation budget, the tested inline injections fail to reliably redirect reasoning, whereas presenting the same instruction in a new user turn changes the model's course. The resulting correction framework, UPTURN (User-Prompt TURN injection at a learned position), requires no LLM fine-tuning: it retains a selected prefix, injects an instruction as a new user turn, and regenerates the suffix. Across four reasoners and six math benchmarks, UPTURN improves average accuracy in every setting over a 32-rollout baseline. It outperforms self-correction and reflection-token injection baselines under matched correction budgets, transfers across reasoners and to GPQA-Diamond without retraining, and complements GRPO and self-correction methods.
self-correctionbenchmark - arxiv:2610.13669 · cs.AIA Step Harder, Not a Step Too Far: The Benefits and Limits of Curriculum Difficulty Progression in GRPORonghan Li, Fei Chen, Mingyu Lu
Curriculum learning typically organizes training samples from easy to hard. In GRPO, medium-difficulty samples are attractive for online selection because they are more likely to yield informative group-relative learning signals, and prioritizing them can improve training efficiency. However, it remains unclear whether persistently selecting such samples also leads to the strongest final model performance, or whether training can benefit from progressing toward harder samples. Meanwhile, sample difficulty changes as the policy evolves, so fixed difficulty estimates can become misaligned with the current policy. We therefore re-estimate sample difficulty under the current policy and, inspired by the easy-to-hard principle of curriculum learning, design and evaluate a staged curriculum that progressively shifts the active difficulty band toward harder samples. Experiments on GSM8K show that persistent medium-difficulty selection does not achieve the strongest observed performance. Across three random seeds, progressing to a moderately harder difficulty band improves test accuracy to $0.6591 \pm 0.0077$, compared with $0.6449 \pm 0.0024$ for the fixed-medium curriculum. However, further progression to a harder difficulty band reduces accuracy to $0.6405 \pm 0.0053$. These results show that staged difficulty progression can outperform persistent medium-difficulty selection, but its benefit is non-monotonic. Effective GRPO curricula can therefore benefit from progressing beyond medium difficulty, while avoiding excessive progression toward overly difficult samples.}
curriculum learning - arxiv:2610.13665 · cs.ROCooperative Aerial Transportation of a Payload with a Sliding Cable AttachmentSebastian Tilaguy Lezama, Diego S D'Antonio
This paper presents a dual-quadrotor hook- suspended transport system for cooperative aerial manipulation of a payload that is not rigidly attached to a fixed point along the cable. Two quadrotors are connected by a single inextensible cable that passes through a frictionless hook mounted on the payload, allowing the cable to slide between its two segments. This introduces a cable-distribution variable that couples the quadrotor motion, cable geometry, and payload dynamics. A feasible reference-generation framework is formulated using the desired payload pose, cable distribution, and system shape while satisfying the cable-length constraint and elliptical workspace. The quadrotors track the geometrically generated trajectories while maintaining positive cable tension and respecting actuator limits. The payload pose is estimated from the system geometry, and its measured position is used only to validate the desired trajectory. The approach is evaluated through experimental demonstrations.
manipulation - arxiv:2610.13663 · cs.LGA Multi-Agent LLM System for Automated Tuning of Specialized Neural Network ModelsIvan Moloshnikov, Dmitry Kunitsyn, Alexander Sboev, Maksim Skorokhodov +2
Many machine learning approaches are two-level: an expert selects a class of methods, within this class the choice of key components is critical and usually manual. This paper addresses the automatic tuning of these components and proposes a framework transferable across models of different nature. The multi-agent large language model (LLM) framework has three roles---analyst, coder, and recorder~---with an experiment log and a sandboxed execution environment. Unlike systems that optimize the entire ML script or search architectures in a discrete space, the framework operates over an open but semantically narrow space: the agent generates code only for the specified components, leaving the overall network structure unchanged. The approach is validated in two directions: tuning a classification spiking neural network with correlation learning, and solving high-order differential equations with Physics-Informed Neural Networks (PINN). Across five tasks---spiking classification on MNIST and Digits, and boundary-value problems for the generalized nonlinear Schrödinger equation (GNLSE) and Kuramoto--Sivashinsky (KS) equations---the agent outperforms the baselines: classification accuracy is 13 percentage points (MNIST) and 6 percentage points (Digits) higher; the error against the analytical single-soliton solution is reduced approximately 2491-fold; the invariant-preservation error drops approximately 325-fold in the selected GNLSE run with a Gaussian perturbation and by more than 100-fold on average over repeated initializations; and the mass drift drops 14-fold for the KS problem with a Gaussian perturbation. The framework thus tunes key components on tasks of different nature without changing its internal structure.
agentmulti-agent - arxiv:2610.13660 · cs.LGPretraining and Test-Time Training Budgets Matter for ARC: A Controlled Study of VARC and TRMAdrien Deliege, Marc Van Droogenbroeck
The Abstraction and Reasoning Corpus (ARC) is increasingly used to evaluate whether neural networks can infer task-specific transformations from few demonstrations. Recent ARC models differ in architecture, but also in broader training and evaluation protocols, including pretraining data, data augmentation, test-time setup, and optimization budgets, making conclusions about architecture benefits debatable. In this work, we study how the performance of the vision-inspired VARC and recursion-based TRM models is affected by pretraining and test-time training (TTT) budgets under a common inductive protocol on ARC-AGI-1. We cross five pretraining budgets with four TTT budgets for each test task. Each budget specifies a task-variant count and total sample presentations, defining the controlled training budgets. We observe that increasing TTT sample presentations improves the standard ARC pass@2 metric in all settings for both models. Increasing the TTT task-variant count consistently helps only TRM, whereas VARC often performs better with fewer variants. VARC also remains competitive without pretraining, while TRM benefits much more from it. These results show that pretraining and TTT budgets affect ARC evaluation and motivate reporting at comparable budgets.
evaluation protocol - arxiv:2610.13654 · cs.LGTabReliBench: Evaluating Tabular Foundation Models Beyond Predictive AccuracyTianqi Zhao, Jia Guo, Yan Shuo Tan, Qiong Zhang
Tabular foundation models (TFMs) are increasingly popular for their strong predictive performance. Many also provide posterior predictive distributions (PPDs), whose reliability remains less studied. We assess reliability through point prediction, distributional quality, marginal and subgroup calibration, and interval efficiency. We then introduce TabReliBench, a large classification and regression benchmark for these comparisons and dataset-level analyses. We find that TFMs' rankings change between TabArena and our benchmark and across reliability metrics. Regression TFMs usually achieve near-nominal marginal coverage and retain narrow intervals, but this favorable marginal behavior does not imply valid conditional coverage. Dataset-level analyses show that classification difficulty often accompanies poor calibration, whereas regression predictive performance is not a reliable indicator of calibration. Ensembling improves predictive performance but does not consistently improve calibration of PPDs; TFMs also benefit little from conformal post-processing, which does not reliably resolve subgroup gaps. Reliable TFM selection therefore requires multidimensional evaluation beyond aggregate rankings. Code is available at https://github.com/Tianqi-Zhao/TabReliBench.
benchmark - arxiv:2610.13644 · cs.LGSelectArena: A Modern Benchmark for Feature Selection on Real-world Tabular DataBastian Schäfer, Dominika Matus, Lennart Purucker, Ricardo Knauer +4
Selecting a subset of features (columns) from a tabular dataset is a ubiquitous challenge in real-world applications. Industry experts seek to minimize model training costs, climate scientists require an interpretable subset of factors to understand extreme weather events, and clinicians need to choose among diagnostic tests due to financial and time constraints. When looking at the scientific literature to determine which feature selection method to use, practitioners across domains face an unrepresentative landscape of benchmarking. Despite extensive research, existing feature selection benchmarks provide limited guidance because they rely on outdated models, ad hoc evaluation protocols, or artificially generated data that do not reflect real-world problems. To close the gap between scientific benchmarking and real-world applications, we introduce SelectArena, a modern benchmark for feature selection. We compare 15 widely used feature selection methods on 71 manually curated real-world tabular datasets, covering classification and regression problems, using standardized evaluation protocols and state-of-the-art tabular (foundation) models. Our results reveal clear trade-offs across predictive performance, runtime, stability, and validity. Tree-based methods, CART and RFImportance, along with F-Test are Pareto-optimal when taking into account predictive performance and runtime. F-Test, information-theory-, and distance-based methods lead on stability and validity, with F-Test emerging as a balanced choice across our metrics. Search-based methods are slow, unstable and achieve low performance. SelectArena turns these findings into practical guidance and, as an extensible platform, supports future feature selection research.
benchmarkevaluation protocol - arxiv:2610.13643 · cs.ROAutoBio+: Benchmarking Dexterous Manipulation with Dynamic Experimental Phenomena in Realistic LaboratoriesXuanye Wu, Yue Shi, Yongcan Yang, Yiqun Wang +6
Automating biological laboratories requires robots to perform dexterous tool interactions under realistic visual conditions while handling dynamic experimental phenomena, presenting significant challenges for robotic manipulation. To enable systematic evaluation under these conditions, we introduce AutoBio+, a simulation benchmark and framework for dexterous manipulation in realistic biological laboratory environments. AutoBio+ comprises 14 tasks across 4 robot embodiments, spanning functional tool use, precision manipulation, language-conditioned visual grounding, and instrument operation. We introduce controllable dynamic experimental phenomena, including flames, vapor, and bubbles, to capture the evolving visual conditions of laboratory procedures. To further enhance environmental realism, we develop a hybrid rendering pipeline that integrates interactive simulated foreground objects with Gaussian-splatting backgrounds reconstructed from 6 real laboratory scenes. For efficient large-scale data generation and evaluation, we further build a parallel simulation framework on top of mjlab, proposing Parallel Finite-State Machine (PFSM) and integrating batched rendering with decoupled trajectory replay for demonstration generation and model-independent closed-loop policy evaluation. Our evaluation reveals substantial variation in policy performance across tasks, exposing distinct strengths and weaknesses of current manipulation policies. Real-world experiments further demonstrate a reduced sim-to-real gap, supporting the validity of AutoBio+ for realistic manipulation evaluation. Supplementary materials are available at https://autobio-plus.github.io/AutoBioPlus.
manipulationdexteroussim-to-realtool usebenchmarkpolicy evaluation - arxiv:2610.13637 · cs.CVModel-agnostic Knowledge Augmented Machine Learning for Weakly Annotated Bioimaging DataJayanie Bogahawatte, Sachith Seneviratne, Simon Maksour, Dzung Do-Ha +5
Machine learning models are increasingly used for automated feature extraction from weakly annotated bioimaging data, such as microscopy and cytomorphology images. Due to the sole dependency of automated feature extraction, existing methods yield inconsistent classification performance across weakly annotated datasets. Here, we propose a model-agnostic knowledge augmentation method that enables ML models to exploit domain knowledge beyond what automated feature extraction can capture. The proposed approach improves classification performance across seven ML architectures. When integrated with masked autoencoder-based self-supervised learning, our method achieves the strongest overall performance, improving precision by 2.9% over the next-best method on three in-house microscopy datasets and by an average of 6.8% across three public cytomorphology benchmarks. We perform nucleus-level classification based on mislocalization of TAR DNA-binding protein 43 (TDP-43) from the nucleus to the cytoplasm, a phenotype linked to Amyotrophic Lateral Sclerosis (ALS), using three independent microscopy datasets of motor neurons derived from human induced pluripotent stem cells. Accurate quantification of this phenotype at scale remains challenging and may contribute to inconsistencies across studies. Application of the best-performing model to these microscopy datasets reveals biological interpretations related to ALS, including dose-dependent effects of the proteasomal stressor, MG132, and the oxidative stressor, sodium arsenite (SA), on TDP-43 mislocalization, variable pathology in motor neurons from sporadic and familial ALS donors, and a lack of protection of the pharmacological compounds, edaravone and niclosamide, against SA-induced TDP-43 mislocalization. Together, our pipeline enables in-vitro cellular image analysis to advance understanding of ALS-associated pathology and potential treatments.
benchmark - arxiv:2610.13636 · cs.CVBenchmarking Answer-Grounding Consistency in Remote Sensing Visual Question AnsweringPing Guo, Zhiqi Huang, Xinran Li, Linkun Yu +2
In grounded remote sensing visual question answering, a model produces a textual answer and identifies relevant objects in the image as grounding evidence. Existing evaluations measure answer correctness and localization quality, but do not directly assess answer-grounding consistency. We propose the Answer-Evidence Support Protocol (AESP) to assess this consistency through evidence support: whether the grounding evidence supports the model's own answer. AESP applies task-specific rules to existence, counting, and comparison questions. We further construct the Grounded Remote Sensing Visual Question Answering (G-RSVQA) benchmark, containing 15,027 samples with questions, reference answers, and all related object-level annotations. Experiments on seven grounded vision--language models reveal failures of evidence support across all three question types. Up to 50.82% of correct answers in the evidence evaluation subset are not supported by the provided grounding evidence.
benchmark - arxiv:2610.13635 · cs.LGPANDA: Prior-guided Attentional Dual-path ArchitectureRishabh Jain, Federico Belotti, Stefano Coniglio, Pietro Lio +1
Hypergraph Neural Networks (HNNs), designed to model higher-order relations beyond pairwise interactions, typically rely either on fixed structural weights or on normalised attention. Fixed weights can propagate misleading information in heterophilic settings, while normalisation makes attention coefficients competitive, in the sense that, in a message-passing framework, increasing the weight of one sender must reduce the weight of others in the same aggregation set. Our main contribution is the introduction of PANDA (Prior-guided AttentioNal Dual-path Architecture), a plug-in for two-stage message passing HNNs applicable to both undirected and directed settings. The main path interpolates between learned receiver-normalised attention and structural incidence priors, while a non-competitive (not normalised) auxiliary path lets each sender contribute its own transformed information. We also show that, with fixed structural coefficients, PANDA recovers a certain complex-valued convolution operator adopted in previous works. Across four HNNs spanning spatial and spectral methods in both directed and undirected settings, plugging PANDA in yields an average improvement of 5.18 percentage points across eight real-world benchmark datasets. The code is available at https://github.com/jainris/panda.
benchmark - arxiv:2610.13632 · cs.AIHumanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, VerifyZhengyang Zhang, Jing Xiong, Hongzhou Lin, Juihui Chung +4
Large language model (LLM) agents are rapidly improving on long-horizon scientific and olympiad tasks. Recent systems have produced a Lean-formalized resolution of the Navier--Stokes problem and autonomous solutions to four open questions in the Erdős Conjectures database. Yet neither system releases both its underlying model and complete inference stack. More broadly, a single agent session remains brittle on difficult problems: early errors can propagate, missing domain knowledge can stall progress, and apparent success can mask a misinterpretation or weakening of the original task. We introduce HOA (Humanize Olympiads Agent), an open, flow-level framework that coordinates multiple agent sessions through three complementary feedback channels. First, an independent reviewer evaluates each candidate and provides actionable feedback. Second, a structured wiki supplies task-specific knowledge that may be missing or unreliable in model pretraining. Third, a verifier checks generated Lean proofs against trusted challenge statements. With GPT-5.6 Sol, HOA achieves perfect scores on the IMO, IPhO, and IOI 2026, near-full marks on the IChO 2026 problem set, and solves all 672 problems (100%) on PutnamBench. On the Lean-Eval leaderboard, HOA ranks first, solving 251 of 304 problems (82.6%). We further evaluate HOA with open models. Using Kimi-K3, HOA achieves full scores on the IMO, IPhO, and IOI, and a gold-level score of 97.1% on the IChO. These results closely match the closed-source GPT-5.6 Sol + /Goal baseline on the IMO and IPhO, while exceeding it on the IChO and IOI, demonstrating that systematic feedback can help bridge substantial differences in base-model capability.
agentleaderboard - arxiv:2610.13631 · cs.LGPrivate and Distributionally Robust Federated Multiclass ClassificationAndrea P. Hernandez, Michael Ibrahim, Nagi Gebraeel
Fault diagnosis in asset-intensive industries requires multiclass models trained on noisy, sensitive data collected across geographically distributed client sites. Federated learning enables collaborative training without centralizing data, but most approaches do not provide formal privacy guarantees for individual records stored at client sites and can degrade under label noise. To address these limitations, we develop a differentially private, distributionally robust framework for federated multiclass classification that provides sample-level privacy for records stored at each client. We build on a federated Wasserstein distributionally robust multiclass objective with the Crammer-Singer loss, solved using an Alternating Direction Method of Multipliers (ADMM)-based algorithm. To protect the released client updates, our method injects calibrated Gaussian noise into the proximal linearized client updates of both the local model and the local distributionally robust variable before aggregation at the central server, and we quantify the cumulative privacy loss using the moments accountant. We provide per-round sample-level $(ε,δ)$-differential privacy guarantees and an overall composed privacy guarantee across all training rounds, together with convergence results and an explicit privacy-utility tradeoff. Experiments on simulated industrial fault data and UCI benchmark datasets show that our method outperforms differentially private federated empirical risk minimization and stochastic gradient descent baselines in most tested settings, with the largest gains under strong privacy-induced noise.
benchmark - arxiv:2610.13630 · cs.CVMulti-Stream Attention ResidualsXiaohan Qin, Xiangdong Zhang, Tuo Dai, Sunan Zou +6
Attention Residuals (AttnRes) enables content-dependent retrieval over network depth, which can be viewed as single-stream softmax attention along the depth axis. Inspired by the success of multi-head attention along the sequence axis, we introduce Multi-Stream Attention Residuals (MSAR), an extension of AttnRes that generalizes this mechanism to multi-head depth attention, yielding substantial performance gains with minimal additional overhead. MSAR draws stream diversity from sequence context through multi-scale causal convolutions, allowing different heads to retrieve historical representations through distinct contextual views while preserving the integrity of the hidden representation. The retrieved streams are combined through lightweight adaptive mixing to generate the single-stream layer input. By retaining single-stream sources and expanding them on demand, MSAR supports multi-stream computation without requiring persistent multi-stream storage or communication. Across all 12 downstream benchmarks at the 18B and 28B MoE scales, MSAR consistently outperforms prior residual variants, including standard residual connections, manifold-constrained Hyper-Connections (mHC), and AttnRes. Scaling-law experiments yield an iso-loss compute speedup of $1.58\times$ over the standard residual baseline, compared with $1.35\times$ for AttnRes and $1.30\times$ for mHC. These results make MSAR a promising residual architecture for large-scale pre-training.
benchmark - arxiv:2610.13628 · cs.ROJitterVLA: A Replay Benchmark for Motion Quality in VLA-Driven Human-Robot ManipulationFaith Ogunwoye, Didar Seyidov, Konstantin Gubernatorov, Dzmitry Tsetserukou
Vision-language-action (VLA) policies issue sparse targets whose arrival at the robot controller is delayed and irregular, so a reasonable predicted action can still produce abrupt motion near people. Remedies are evaluated on different streams, delays and metrics. JitterVLA replays identical commands and arrival traces through alternative controllers, isolating the controller's effect. We apply it to synthetic reaches, hand trajectories from 20 people, three open VLA pipelines (838 episodes) and a physical UR3. Interpolation lowered modeled p99 jerk for every source, by 83% (615 to 106 m/s^3) on human motion with 200 ms delay, at a 2.0 cm tracking cost, and the effect replicated on 598 new episodes; jerk-limited generation lowered jerk further at a larger cost. Entropy-discontinuity associations had opposite, replicated signs in two pipelines, and entropy gating helped in one but not the other. On the UR3, interpolation lowered accelerometer-derived jerk by 3.0-14.0% in all six exploratory pairs, while a position-derived metric did not resolve the contrast. JitterVLA supports screening before human-centred studies; code and data will be released.
vision-language-actionvlamanipulationbenchmark - arxiv:2610.13626 · cs.AISWE-DeceptionBench: Benchmarking Deceptive Behaviors of LLMs Across the Software Development LifecycleXiting Liu, Lin Yang, Yitong Zhang, Jia Li +1
Large Language Models (LLMs) are increasingly used throughout the software development lifecycle. This growing reliance on LLMs raises concerns about their trustworthiness, with deception posing a particularly important risk. Deceptive behavior takes the form of misleading responses or assistance in fabricating, concealing, or distorting information. To study this behavior, we introduce SWE-DeceptionBench, a benchmark for evaluating LLM deception in software engineering. The benchmark covers six lifecycle stages and two deception triggers: Active Deception, where models recognize infeasible or conflicting requirements but still present them as achievable, and Passive Deception, where models help fulfill explicit user requests to mislead others. We further introduce Neutral, Reward, and Pressure conditions to study the effect of external inducements, resulting in 720 test instances in Chinese and English. Evaluating seven mainstream LLMs, we find substantial deception even under the Neutral condition, with aggregate rates of 49.88% for Active Deception and 64.29% for Passive Deception. Deception rates vary across lifecycle stages, and external inducements affect Active and Passive Deception to different extents. We also evaluate lightweight defenses, finding that guard models miss many deceptive requests, and Self-Reminder reduces but does not eliminate deceptive responses. These findings highlight the need for more effective deception detection and mitigation methods to support trustworthy LLM-based software engineering.
benchmark - arxiv:2610.13623 · cs.CLAPEX-Harm: Evaluating Agent Safety in Shared Professional WorkspacesZiyi Yang, Adel Bibi, Guohao Li, Bernard Ghanem +1
Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and business applications. These environments create safety risks that are difficult to capture with attacks placed at a single, known read location. We introduce APEX-Harm, a benchmark for evaluating prompt and script injection against long-horizon agents performing finance, consulting, and legal tasks in large workspaces. Each task contains 115 to 328 files, together with email, calendar, chat, document, spreadsheet, PDF, and code-execution tools exposed through MCP servers. The benchmark includes six attack categories covering static and dynamic injections, task-specific script replacement, and attacker-provided generic scripts, and evaluates attack success, exposure, and task performance. We evaluate 12 frontier models on 180 task instances per model. Opus 5 and Sonnet 5 have the lowest overall attack success rates (8% and 20%), while task-specific script replacement and attacker-provided generic script attacks remain substantially more effective, averaging 81-84% and 73% attack success, respectively. Gemini 3.8 Flash achieves the highest mean task score (0.877) while still exhibiting a 33% attack success rate. These results show that completing the requested task is not sufficient evidence of safe behavior: an agent can produce a correct deliverable while also performing an unauthorized action in the workspace.
agentbenchmark - arxiv:2610.13610 · cs.CVCUBE: Class-conditioned Unknown Boundary Evidence for Open-Set Insect Species RecognitionHao Tan, Qimin Zhang, Zhe Xiao, Zekai Zuo +2
Open-set insect species recognition faces significant challenges when deployed in real-world biodiversity scenarios, particularly when encountering unknown species that are visually close to known training classes. Unlike generic out-of-distribution samples, fine-grained unknown insects are often not visually anomalous. They instead tend to appear near the decision boundary of specific known species, leading to unreliable closed-set predictions. To address these challenges, we propose \textbf{Class-conditioned Unknown Boundary Evidence (CUBE)}, a novel evidence-based framework that models unknownness around each known species rather than as a single global unknown class. Our key idea is to evaluate a test sample relative to the known species it most closely resembles, enabling local rejection for visually confusable unknown insects. CUBE learns class-conditioned boundary evidence from auxiliary species, preserves auxiliary species as shadow references during inference, and incorporates taxonomic candidate calibration to verify biological plausibility. When ecological metadata is available, we further introduce CUBE-E, which adds a lightweight location-consistency term without modifying the visual backbone. Experiments on the Open-Insect C-America benchmark show that CUBE achieves superior performance, outperforming state-of-the-art baselines with 95.8\%, 98.7\%, and 99.1\% AUROC on local, non-local, and non-moth unknown splits, respectively, while maintaining 94.9\% closed-set accuracy. With ecological metadata, CUBE-E further improves the results to 96.0\%, 99.7\%, and 99.5\% AUROC with 95.2\% closed-set accuracy.
benchmark - arxiv:2610.13607 · cs.CLBLiMPPI: Benchmark of Linguistic Minimal Pairs for Polarity ItemsArzu Burcu Güven, Anna Rogers, Leonie Weissweiler, Joakim Nivre +1
Negative polarity items (NPIs), such as "anymore" and "ever", are grammatical only in select environments, predominantly in the context of negation. Because their grammaticality depends on both syntax and semantics, they have a rich, multilingual literature in theoretical linguistics, yet work on NPIs in language models is almost entirely confined to English. We introduce BLiMPPI, a multilingual evaluation suite of over 12,000 NPI minimal pairs in 33 languages, built by a pipeline that discovers NPIs in Universal Dependencies (UD) treebanks, labels their licensing environments, and perturbs these into minimal pairs. Evaluating 12 multilingual and 2 monolingual models alongside n-gram baselines, we find that multilingual models struggle most with lower-resource languages and with pairs that are not n-gram solvable. We further examine the effects of NPI typology, language family, licensing variability, and NPI-licenser distance. Data: https://github.com/arzuburcuguven/blimppi-data
benchmark - arxiv:2610.13604 · cs.CVThyroid Nodule Segmentation in Ultrasound Images with Conformal Uncertainty EstimationFrancesco Teodori, Pierpaolo Brutti, Umberto Ferraro Petrillo
Thyroid nodules affect a large proportion of the general population. Although most are benign, a non-negligible fraction is malignant. Ultrasound imaging is the primary diagnostic modality, and accurate nodule segmentation is a prerequisite for CAD systems to classify malignancy and assess metastatic risk.\\ In this work, we propose a thyroid nodule segmentation framework that integrates a DeepLabV3+, channel-attention modules and post-hoc conformal prediction, providing both accurate mask and pixel-level uncertainty estimates. We address thyroid ultrasound nodule segmentation as the first stage of a pipeline that also includes malignancy classification and metastatic risk prediction. We adopt DeepLabV3+, whose Atrous Spatial Pyramid Pooling (ASPP) captures multi-scale context, with an EfficientNet-B5 backbone for its accuracy-efficiency trade-off. Additionally, we test three channel-attention modules: Squeeze-and-Excitation, CBAM and Grouped Channel Attention (GCA), paired with two loss formulations (Dice-BCE and Boundary).\\ Since binary masks do not indicate prediction confidence, we wrap the trained model with a split conformal prediction layer that produces pixel-level uncertainty maps with statistical coverage guarantees.\\ We evaluate all configurations on the TN3K public benchmark using a fixed split and directly compare them with state-of-the-art methods. The plain backbone already improves upon previously reported results, with CBAM + Dice-BCE emerging as the best overall configuration.
benchmark - arxiv:2610.13594 · cs.AIMENTOR: Learning from Failure with On-Policy Pedagogical InterventionGuanlan Yue, Hang Yu, Xiaoyong Huang, Ruipeng Li +3
Reinforcement Learning from Verifiable Rewards (RLVR) is a key driver for Large Reasoning Models, but it is vulnerable to "zero-reward collapse", a training failure where a sudden increase in task difficulty causes the learning signal to vanish. We argue that the conventional approach of discarding these failed trajectories is wasteful, as they contain valuable diagnostic information about the model's cognitive gaps, a bright side that can be leveraged for recovery. Existing solutions, however, often regress to static, "off-policy-style" interventions like pre-defined hint libraries or perform post-hoc refinement, failing to provide the adaptive, forward-looking guidance needed to escape the collapse. To address this, we propose a paradigm shift towards on-policy pedagogical intervention and introduce MENTOR, a multi-agent framework that acts as a live mentor. MENTOR diagnoses the root cause of failure in real-time and dynamically generates targeted, instructional prompts to guide the learning agent's next attempt. As a plug-and-play module, MENTOR integrates seamlessly into existing policy optimization pipelines like GRPO without modifying the training infrastructure. Extensive experiments on math and code generation show that MENTOR effectively mitigates zero-reward collapse, outperforming state-of-the-art baselines. Notably, it achieves massive average relative gains of up to 78.3% on Llama-3.2-3B-Instruct over its base model.
multi-agentagent framework - arxiv:2610.13583 · cs.CLMeasuring Artifact Reliance in Machine-Generated Text DetectorsAnastasia Voznyuk, Andrey Grabovoy
Detectors of machine-generated text score almost perfectly on scientific-literature benchmarks, implying we can reliably distinguish with these detectors human and machine-generated documents. We looked at ten scientific-document subsets from six popular resources, and on several of them that apparent ease is a side effect of how the documents were put together. A logistic regression using 27 superficial features reached 0.833-0.997 macro-F1, and on the three arXiv subsets it outperformed every detector we evaluate with F1-scores 0.951-0.997. The strongest cue to the detector is the PDF extraction artifact: human texts retain their original line breaks, whereas generated texts are extracted as a single block of prose. This cue, together with three other formatting features, tell the classes apart at 0.996 AUC. To distinguish benchmarks that contain such a signal from detectors that rely on one, we introduce format counterfactuals: just re-wrapping a machine-written abstract without changing a single word reverses 20-27% of a public detector's correct decisions. Normalizing formatting before training reduces the generalization gap from 0.32 to 0.22. On format-clean benchmarks, it also raises out-of-domain macro-F1 from 0.33 to 0.65 for detectors trained on artifact-containing subsets.
benchmark - arxiv:2610.13578 · cs.RORARA: Robust Policy Fine-Tuning through Retrieval-Anchored Representation Alignment for Robotic ManipulationXuhui Kang, Sung-Wook Lee, Yan Zhuang, Tianle Zhong +1
Pre-trained robot policies, such as Vision-Language-Action (VLA) models, provide a strong foundation for generalist robotic manipulation, but adapting them to new tasks with only a few demonstrations remains challenging. Directly fine-tuning a pre-trained policy often achieves strong in-distribution performance, yet it can distort the representations learned during pre-training and weaken the model's generalization ability under out-of-distribution shifts. We propose Retrieval-Anchored Representation Alignment (RARA), a two-stage adaptation method, to address this issue. First, RARA retrieves representation features from pretraining with similar task intent and motion, and aligns the policy's representations of the target demonstrations with the pre-trained representations of the retrieved demonstrations. Second, RARA fine-tunes the policy on the target demonstrations while limiting how much its representations of the retrieved demonstrations change during fine-tuning. By reducing the representation mismatch before action learning and preserving pre-trained knowledge during adaptation, RARA limits unnecessary representation drift during fine-tuning. Experiments with Diffusion Policy and GR00T on 13 tasks in RoboTwin, RoboCasa, and on a real robot show that RARA improves the average success of fine-tuning by 9.5 points in-distribution and 13.6 points out-of-distribution, and outperforms all compared baselines. Project page: https://shua-kang.github.io/RARA_robot/
vision-language-actionmanipulationdiffusion policygr00trobotwin - arxiv:2610.13572 · cs.ROATHLETE: Learning Reactive Humanoid Tennis via Trajectory-Guided Motion MatchingZhihao Tian, Zifan Wang, Enzheng Zhu, Xun Yang +3
Humanoid tennis requires reactive whole-body coordination under rapidly changing ball dynamics, yet collecting task-specific motion-capture demonstrations that cover diverse approach states, contact locations, and timing conditions is costly. Inspired by how humans acquire new skills by combining reusable motor experience with task-specific demonstrations, we present ATHLETE, a framework for learning reactive humanoid tennis from generic locomotion data and ordinary tennis videos. ATHLETE combines LAFAN1 locomotion with video-derived striking motions and uses Trajectory-Guided Motion Matching (TGMM) to construct diverse task-conditioned whole-body references. These references are transformed into a reactive policy through physics-based teacher--student learning with online DAgger distillation, followed by PPO fine-tuning for the tennis task. The resulting policy responds directly to robot and ball observations without requiring reference-motion inputs at deployment. On a real humanoid robot, ATHLETE achieves forehand and backhand hit rates of $90.00\%$ and $86.67\%$, respectively, and enables multi-shot rallies with human players. These results demonstrate that ATHLETE can learn dynamic humanoid tennis skills from reusable locomotion data and video demonstrations. Result videos and code can be found at https://anonymous.4open.science/w/ATHLETE2027/.
humanoid - arxiv:2610.13570 · cs.AIConstructing Pareto Frontiers of Optimal Reasoning Termination Methods for Overthinking in Reasoning ModelsWeixin Guan, Liang Li, Shiyu Xie, Jiapeng Liu +6
Reasoning models can benefit from test-time scaling, but continued reasoning may become ineffective or harmful, a phenomenon termed overthinking. Evaluations against full thinking compare accuracy and token usage but lack references for overthinking severity and strategies' theoretical mitigation potential. To characterize overthinking at the model-task level, we first introduce Step-wise Truncation Probing (STP), repeatedly generating answers from multiple retained prefixes along each fixed sampled reasoning trajectory. Using each trajectory's earliest measured position attaining maximum empirical accuracy as a reference, we define Overthinking Ratio and Accuracy Degradation as the fraction of thinking tokens generated afterward and the accuracy decrease from this reference to full thinking, respectively. Secondly, we then formulate dynamic routing, fixed budgets, and dynamic early exit within a unified framework to quantify the theoretical mitigation potential of different termination strategies. Based on this unified framework, we use the complete STP measurements to construct a token-accuracy Pareto frontier for each strategy under a common normalized thinking-token budget. We further develop OTBench, a reusable benchmark built from the STP process, which produced 70.5B reasoning tokens and the corresponding probing measurements across six models and four benchmark groups.
benchmark - arxiv:2610.13563 · cs.CLNot All Correct Fixes Run Alike: An Empirical Study of Patch Performance in Repository-Level Issue ResolutionHan Peng, Xing Hu, Feifei Niu, Huan Li +1
Repository-level issue-resolution benchmarks such as SWE-bench evaluate submitted patches primarily based on whether they pass the correctness tests, leaving the runtime performance of different test-passing patches largely unexplored. Evaluating patch performance is essential but challenging since designing performance workloads for each benchmark instance is costly. However, these benchmarks already provide a natural candidate: the built-in \emph{FAIL\_TO\_PASS} (F2P) tests, which exercise the behavior affected by the issue fix. We therefore investigate whether the provided F2P tests can be repurposed to evaluate patch performance. Overall, we choose four frontier models, Claude Opus~5, GPT~5.6, DeepSeek V4 Pro, and Qwen~3.8 Max, paired with SWE-agent to resolve the pre-filtered measurable corpus from verified splits of SWE-bench and SWE-bench-Live, yielding 262 cases with at least two different correct solutions, including the developer ground-truth patch. We then measure each solution's runtime performance in instruction count and wall-clock time on the native F2P test, and use Welch ANOVA instead of the RSD proposed in prior work as a more robust statistical discrimination criterion. We find that this methodology exhibits notable discrimination capability in runtime performance and identifies performance differences among patches in almost half of the instances. Our empirical study shows that the runtime performance of generated patches is independent of the issue resolution rate of LLMs, with nearly reversed model rankings. The case study also shows that the performance analysis reveals architectural regression in some patches that the correctness evaluation overlooked. These findings suggest that resolution rate does not adequately characterize LLMs' capability for repository-level issue resolution, motivating future evaluations to consider patch performance alongside it.
benchmark - arxiv:2610.13557 · cs.ROProbabilistic Ship Trajectory Forecasting using Transformer Models on AIS DataFrederik E. T. Schöller
Anticipation of vessel trajectories is an essential task when navigating at sea. This applies to both human navigators and autonomous surface vessels. Trajectory forecasting enables sub-routines such as collision avoidance to assess the situation and react accordingly in time. This paper investigates Transformer and Performer models for trajectory prediction of surface vessels in confined waters. Using widely available position data from the Automatic Identification System (AIS), candidate models are trained and evaluated. Historical information on how other vessels have moved in the local area surrounding each agent is conveyed using positional heat maps. The heat maps are generated using Kernel Density Estimation (KDE) and encoded with a Convolutional Neural Network (CNN) before entering the Transformer models. The models are trained with quantile loss to efficiently obtain a model-aware prediction interval, as this is crucial for timely collision avoidance. The proposed model architectures are shown to greatly outperform previous work while the inclusion of local heat maps enables the prediction of vessel movement that is not otherwise indicated from the previous positions.
agent - arxiv:2610.13553 · cs.CVLearning Holistic Scene Layout against View Shifts in Cross-View Geo-LocalizationChao Yang, Songlian Li, Zhigang Tu
Cross-view geo-localization remains challenging due to drastic appearance variations and geometric distortions caused by viewpoint changes. Existing methods primarily rely on discriminative feature learning or explicit geometric alignment, yet often overlook an important observation: humans tend to match scenes by integrating the spatial context of multiple landmarks rather than relying solely on isolated local visual cues. Inspired by this, we propose a Spatial Context Modeling (SCM) module, which traverses feature maps along four orthogonal directions and models interactions among the resulting directional representations at each spatial position. By aggregating complementary directional observations, SCM constructs richer scene layout representations. Since reliable spatial context depends on robust visual features, we introduce a High-Frequency Information Guidance (HFIG) module that extracts stable structural cues from the frequency domain. By emphasizing edges and contours that are less sensitive to appearance variations, HFIG encourages the model to learn more robust representations. Extensive experiments demonstrate that our method achieves competitive performance on standard cross-view geo-localization benchmarks while exhibiting strong robustness under more challenging scenarios with unknown orientations and limited fields of view (FoVs).
benchmark - arxiv:2610.13550 · cs.CLPersonalization Without Stereotyping: Do Speech LLMs Know When to Turn a Deaf Ear?Kshitij Ambilduke, Caroline Brun, Thibaut Thonet, Vassilina Nikoulina +1
Recent speech LLMs can leverage rich paralinguistic cues, enabling more complex and personalized interactions. However, little work investigates how this sensitivity can lead to stereotyping, and existing evaluations largely measure demographic disparities without distinguishing beneficial personalization from stereotypical behavior. We introduce BASIS-Bench, a benchmark designed to disentangle these two aspects through three axes: (1) demographic robustness, measuring disparities in content-based tasks across speakers and demographic classification capabilities; (2) stereotypical bias, measuring whether perceived demographic cues trigger unprompted stereotypical behavior; and (3) personalization, measuring whether models can tailor responses to demographic characteristics when explicitly requested. We evaluate eight recent speech LLMs and find that, despite often recognizing demographic cues, most fail to translate them into appropriate personalization. Explicit demographic labels improve personalization but also amplify stereotypical associations already present in the textual backbones. These findings highlight the need to train speech LLMs not only to perceive demographic cues, but to learn when they should shape their responses.
benchmark - arxiv:2610.13549 · cs.CVELMA: Benchmarking Anaphoric Compositions for Long-Term Text-to-Motion GenerationShun Kato, Dixin Yang, Kotaro Amaya, Yuiga Wada +4
Text-guided long-term human motion generation is essential for applications such as continuously operating digital avatars. Despite recent progress on short clips, existing models struggle with multi-segment instructions that involve anaphora, where constraints established in earlier segments must be preserved over time. In this paper, we introduce a novel task of long-term motion generation from such anaphoric compositions. To mitigate this, we present ELMA, an episodic long-term motion dataset with dense segment-level annotations that preserve cross-segment dependencies. Built via a fully automated collection and filtering pipeline, ELMA extracts high-quality, continuous 30-second clips from in-the-wild videos, capturing the episodic narratives necessary for long-range state modeling. Leveraging this dataset, we fine-tune state-of-the-art motion generation models to incorporate long-range context. Extensive experiments reveal fundamental shortcomings in current models when handling context-dependent instructions. We demonstrate that ELMA enables significant improvements in both global physical realism and semantic alignment, setting a robust new baseline for long-term motion synthesis.
benchmark - arxiv:2610.13548 · cs.CVAuditing VLM Benchmarks from Existing Evaluation RunsDenis Degtiarev, Anna Gromova, Sergey Katkov, Artem Mikhailin +4
Every evaluation run of a vision-language model (VLM) already produces per-question artifacts (predictions, judged correctness, metadata) that leaderboards reduce to a single score and then discard. We reuse those artifacts to audit the benchmark itself, and add an audit layer to VLMEvalKit: six detectors that run as post-processing over saved outputs, plus one additional text-only rerun with visual inputs removed, emitting a per-question report. The layer reports per-question findings together with aggregate audit statistics; for the headline quantities, it attaches permutation-null excess where applicable, interval estimates for proportions, and sensitivity to the model pool. Auditing MMStar, a benchmark curated specifically so that the image is indispensable, with three models, we find zero aggregate accuracy gain from the image on 20.2% of its questions. An item-matched permutation null accounts for 17.0%, leaving a +3.2 pp excess (corrected permutation p = 0.001). This excess is concentrated in the mathematics and science categories and is absent from coarse perception, a localization consistent with knowledge substituting for visual evidence; confirming that mechanism would require item-level review. A second detector flags 134 questions on which every model that answered in parseable form picked the same non-gold option, and these candidates peak in the perception categories, whereas the zero-gain excess is largest in mathematics and science & technology. Replacing the LLM judge with exact string matching changes no conclusion, and every scoring discrepancy between the two traces to one model whose free-form answers a parser cannot read. On a binary yes/no benchmark the detectors measurably fall out of calibration, a scope boundary that we measure and report. The audit layer, the prediction artifacts and the generated reports accompany this submission.
benchmarkleaderboard - arxiv:2610.13547 · cs.CVMOSAIC: Multi-Scale Object-Centric Slot Adaptation with Image-Guided Prototype Conditioning for Remote Sensing Image Super-ResolutionLiuqian Wang, Hanyu Xie, Rongzhen Zhao, Qi Ming +5
Pretrained diffusion Transformers provide powerful generative priors for image restoration, yet adapting them to structure-sensitive tasks remains challenging. Existing methods mainly rely on dense low-resolution features as conditions, which often entangle salient objects with dominant backgrounds and provide limited abstraction for recurring structures across scales and samples. We propose MOSAIC, an object-centric representation learning framework that learns compact structural conditions for generative model adaptation. MOSAIC organizes degraded observations into structural slots that capture complementary object-level and layout-level evidence, integrates them across resolutions, and retrieves recurring priors from a shared prototype memory to complement incomplete image-specific information. The resulting representations are injected into selected layers of a frozen diffusion Transformer through lightweight residual modulation, preserving its pretrained generative prior. We instantiate MOSAIC for remote sensing image super-resolution, where small objects, repetitive structures, and large-scale variation provide a challenging testbed. Experiments on UCMerced, AID, and RSSCN7 show consistent PSNR improvements across $\times 2$ and $\times 4$ settings and favorable LPIPS results at $\times 4$. Qualitative results further demonstrate improved preservation of small objects, structural boundaries, and repetitive spatial patterns.
memory - arxiv:2610.13536 · cs.LGDefence against the dark arts of distillation: Unsupervised discovery of subliminal learningJoseph Egan, Ciarán M. Gilligan-Lee, Michael O'Riordan, Yuchen Zhu
When a language model is distilled from a teacher that shares its base parameters, the student can inherit behavioural traits of the teacher---including misalignment---even from data that is semantically unrelated to the trait (Cloud et al., 2026). All existing defences require knowing the trait. We remove this requirement and prove that a subliminally transferred trait can be recovered from the parameter updates alone, without supervision, by exploiting a single asymmetry: the trait is expressed consistently across diverse datasets generated by the teacher, whereas task-specific and shared capabilities vary. The resulting estimator returns a weight-space direction that can be amplified to discover and interpret the trait or projected out to suppress it. Applied to the subliminal-learning benchmarks of (Cloud et al., 2026), our method recovers the transmitted animal-preference traits without any trait labels and suppresses their expression with almost no impact to task performance.
benchmark - arxiv:2610.13534 · cs.ROMAGMA-Bench: Evaluating Long-Horizon Embodied Agents under Dynamic Tasks and Execution FailuresLoan Bernat, Matthieu Grard, Ariane Herbulot, Florent Lamiraux
Long-horizon embodied agents must maintain task-relevant information, coordinate heterogeneous robots, and adapt their decisions as execution unfolds. Existing benchmarks investigate dynamic task execution and embodied multi-agent coordination, but provide limited evaluation of their intersection. We introduce MAGMA-Bench, an architecture-agnostic benchmark for persistent task reasoning in dynamic multi-robot environments. MAGMA-Bench evaluates agents across increasing task horizons and controlled online perturbations, including execution failures, task interruptions, and mission updates, with scenarios requiring coordination across robots with heterogeneous capabilities. It uses a structured skill-level interface to separate task-level reasoning from perception and low-level control. We evaluate locally deployable open-weight planners, multi-agent state-tracking strategies, and frontier models. Even the strongest evaluated models fail on a substantial fraction of clean episodes, and their success rates decrease further under online perturbations. Supervised adaptation greatly improves a small model, but performance remains substantially lower on longer and multi-robot missions. We release the benchmark, 261,646 task-level training examples, and an architecture-agnostic expert-trace generation pipeline.
embodiedmulti-agentembodied agentbenchmark - arxiv:2610.13525 · physics.opticsUV Fluorescence Sensing of Medical-Chemical-and- Biological Analytes by an AlGaN/Si-on-Sapphire Optoelectronic ChipRichard Soref
This paper proposes and analyzes a compact fluorescence-photometer lab-on-a-chip that is simpler than a fluorescence spectrometer, and that does not require spectrum reconstruction by a computer. An on-chip AlGaN VCSEL lasing at 280 nm, or at 310 nm, pumps an on-chip sample in the form of liquid or solid or tissue, thereby exciting signature fluorescence in the 300 to 540 nm wavelength range. This emission signal is detected and read out by an on-chip UV-enhanced Silicon photodiode. The 2 cm x 5 cm chip consists of C-plane (0001) Sapphire, and no lenses, prisms, or mirrors are utilized in the photometer. The chip is opto-electronic and features co-packaged electronics using tiny electronic chiplets that are bonded to the sapphire. These consist of an LD driver and transimpedance amplifier for the UV photonics, together with ASICs, ADC, microcontroller, micro-battery and RF-wireless or Ethernet chiplets. The mission of this self-contained cost-effective chip is sensing targeted medical-chemical-biological (MCB) agents in a local or network setting. Eight significant MCB applications are detailed here.
co-packaged - arxiv:2610.13522 · cs.ROBeyond Successful Robot Demonstrations: Learning from Human Interactions and Modeling Failure DynamicsPeiyan Tu, Cong Wang, Hanxin Zhu, Xin Jin +1
Action-conditioned world models offer a promising foundation for generalist robotic intelligence by predicting the consequences of actions. However, existing robotic datasets provide limited coverage of the diverse interaction dynamics required for generalizable world modeling. Large-scale egocentric human videos offer complementary interaction experience, yet the embodiment gap between human hands and robotic manipulators hinders effective cross-embodiment learning. Meanwhile, the predominance of successful demonstrations leaves failure dynamics substantially underrepresented, limiting the ability of world models to anticipate unsuccessful executions. To address these limitations, we introduce HF-WM, an action-conditioned world model that combines Human interaction learning with Failure-aware post-training. To bridge the embodiment gap, we develop a dual-branch framework that couples video generation with auxiliary pointflow prediction, using stabilized pointflow as a unified motion representation across human and robot interactions while suppressing egocentric camera motion. To improve failure modeling, we further perform Group Relative Policy Optimization (GRPO) post-training on perturbed actions derived from successful demonstrations, guided by action alignment and physical plausibility rewards, enabling the model to learn plausible failure dynamics without paired ground-truth videos. Extensive experiments demonstrate that HF-WM achieves state-of-the-art performance in action-conditioned video generation and exhibits strong utility for policy evaluation in downstream robotic tasks.
manipulatorworld modelaction-conditionedpost-trainingpolicy evaluation - arxiv:2610.13516 · cs.RORESCUE: Is This Alarm Worth Acting On? Counterfactual Evaluation of VLA Runtime MonitorsDavid Ahmedt-Aristizabal, Abdelwahed Khamis, Mohammad Ali Armin, Lars Petersson
Runtime failure monitors for robot policies are typically evaluated by how accurately they distinguish failed from successful executions. Yet an accurate alarm may arrive too late for recovery, while an unnecessary intervention may disrupt an execution that would otherwise succeed. We introduce RESCUE, a counterfactual framework for evaluating whether a monitor's alarms enable useful interventions. By restoring simulator and policy states at execution checkpoints, RESCUE compares alternative actions, identifies the latest checkpoint satisfying a specified recovery criterion, and evaluates whether acting on alarms reduces expected task-completion cost. We evaluate RESCUE with OpenVLA-OFT and $π_{0.5}$ over LIBERO-Spatial and LIBERO-Plus using 128,340 counterfactual branches. Recoverability depends on the state--intervention pair rather than on robot state alone: at $τ=0.5$, 14 of 66 OpenVLA-OFT/LIBERO-Plus failures contain a recoverable checkpoint under continuation, compared with 34 of 66 under continuation or scripted recovery, while recovery reduces recoverability in other conditions. On the primary strong-policy conditions, favourable detection scores do not establish lower intervention cost. Under the evaluated stop-and-reset model, even an idealised detector can afford only a 2.0--3.3% false-alarm rate before unnecessary resets outweigh the savings from stopping failures early. These results show that monitor value depends jointly on the intervention available and the workload in which it is deployed.
vlaopenvlalibero - arxiv:2610.13510 · cs.AIRetrieval-Augmented Multimodal Language Model with Heterogeneous Evidence Integration for Clinical PrognosisHamza Shafiq, Jialu Tang, Ting Dang, Jun Hu +1
Clinical prognosis requires integrating structured measurements, physiological waveforms, longitudinal history, and population context. We introduce PRISM (Population-Retrieved Inference for Structured Multimodal Prognosis), a multimodal language model that combines per-feature numerical tokenization, recency-weighted aggregation of longitudinal ECGs, and a dual-modality population memory bank. Retrieval operates in representation space: the model receives mean-pooled embeddings of similar training-cohort encounters, while no individual retrieved record enters the prompt. On the 1,443-task MDS-ED benchmark, PRISM achieves AUROCs of 86.2% for diagnosis, 93.1% for deterioration, 91.8% for ICU admission, and 92.8% for mortality. These results use a 96-hour pre-arrival window unavailable to reported baselines. With benchmark-window inputs only, PRISM reaches 0.8895 AUROC, compared with 0.8937 for UniPACT and 0.8889 for MDS-ED. A matched-input compact fusion model using the same five evidence streams and frozen encoders reaches 0.7652 AUROC, versus 0.9092 for PRISM. Replacing numerical EHR encoding with text serialization reduces AUROC by 3.66 points; removing pre-arrival history reduces it by 1.97 points; and zeroing retrieval reduces it by 0.99 points. Genuine retrieval outperforms random-neighbor retrieval by 0.97 macro-average points, although a paired task-level sign test does not establish a uniform advantage (p=0.067). On the external MC-MED cohort, supervised fine-tuning reaches 0.8611 AUROC, compared with 0.8227 for locally trained gradient boosting and 0.7841 for source-only PRISM. These results support structure-aware multimodal integration and supervised external adaptation.
memoryretrieval-augmentedbenchmark - arxiv:2610.13508 · cs.LGFedPCD: Priority-Constrained Federated AggregationYousef Irshaid, Dara Varam, Mohamed I. AlHajri
Federated learning (FL) seeks to optimize a shared global model from decentralized client data. While effective for average performance, this process can produce unfair performance across clients, particularly under statistically heterogeneous data distributions. Existing fairness-aware and multi-objective FL methods address this through client re-weighting, gradient correction, or common-descent formulations, but often change the global optimization direction or treat client objectives symmetrically. We propose FedPCD, a priority-constrained federated optimization framework that separates the global optimization objective from client protection. FedPCD preserves the conventional federated aggregate as the primary objective, while allowing only the minimum correction necessary to meet client performance constraints. Across heterogeneous FL benchmarks, FedPCD consistently outperforms state-of-the-art baselines, achieving the highest global accuracy across all configurations and leading worst-10% client accuracy in nearly all. FedPCD further preserves competitive trade-offs between global accuracy and client performance variability. Beyond this trade-off, FedPCD demonstrates faster empirical convergence, reaching matching or superior performance in substantially fewer communication rounds.
benchmark - arxiv:2610.13504 · cs.LGBeyond Temporal Proximity: Explanatory World Models for Credit Assignment in Reinforcement LearningOriol Corcoll, Qiyao Wei, Ciarán Mark Gilligan-Lee
Generative Recommenders increasingly use Reinforcement Learning (RL) to optimize outcomes that may appear hundreds or thousands of interactions after a decision. Standard RL propagates reward according to temporal proximity rather than explicit relevance, attenuating the signal assigned to distant but important actions and creating a source of sample inefficiency. We introduce Explanatory World Models (EWM), an attribution framework that uses explanations to identify the earlier events that plausibly contributed to a realized outcome. We instantiate EWM with a frontier language model and use its explanations as learning signals using a conservative hierarchical operator that recursively redistributes reward while preserving the undiscounted episode return. To investigate what constitutes a useful explanation, we operationalize three complementary variants inspired by Halpern's actual causation, Lombrozo's explanatory simplicity, and Deutsch's hard-to-vary explanations. We evaluate EWM on two controlled long-horizon RL benchmarks, a public sequential-recommendation benchmark, and an industry-scale generative recommender. On Crafter and WordCraft, EWM substantially outperforms PPO and LaRe, with its largest gains when rewards are most delayed. On KuaiRand, EWM outperforms SFT and LaRe offline and A2C online. Finally, in an offline evaluation of an industry generative recommender, EWM considerably improves Recall and increases behavioral proxies. These results suggest that explanations can provide structured and reusable credit for learning from delayed outcomes.
world modelbenchmark - arxiv:2610.13503 · cs.CVSplatQ: Interaction-Aware Pruning of 3D Gaussian Splatting via Quadratic SelectionHongbin Ye, Haixu Liu, Shenwei Kang, Wenxiu Wei +12
Existing 3D Gaussian Splatting (3DGS) pruning methods primarily rely on global Top-K selection based on independent importance scores, lacking regional budget control and ignoring joint deletion effects. Consequently, they cannot ensure balanced reconstruction quality across a scene. We propose SplatQ, a combinatorial pruning algorithm that coordinates regional budget allocation and joint Gaussian selection under a fixed budget. SplatQ partitions Gaussians by spatial proximity and appearance similarity into size-limited blocks, decomposing global selection into subproblems of a specific size. It then smooths importance-based block retention quotas to prevent excessive budget concentration. Finally, it constructs a quadratic approximation of joint deletion effects using the responses of representative pixel colors to changes in Gaussian opacity. Individual responses, pairwise interactions, and quota penalties are incorporated into a quadratic unconstrained binary optimization (QUBO) objective, solved using simulated annealing (SA) or a coherent Ising machine (CIM) to jointly select Gaussians. Experiments on 5 benchmarks demonstrate that SplatQ outperforms state-of-the-art pruning methods in aggregate reconstruction quality, spatial quality balance, and rendering speed. Ablations confirm that budget smoothing improves local detail reconstruction, while interaction modeling improves Gaussian selection quality under a fixed budget.
benchmark - arxiv:2610.13502 · cs.CVStride: Scale-Aware Multi-Agent Evolutionary Refinement for Infographic GenerationYan Zhou, Yang Yang
Infographic generation challenges text-to-image models because a single image must satisfy numerous visual, textual, and semantic constraints. Iterative agentic refinement with a multimodal verifier is a natural remedy, but existing methods face a scale mismatch: local edits cannot correct global composition errors, while full regeneration may destroy already-correct regions. We introduce Stride, a constraint-grounded multi-agent framework that treats refinement over any frozen generator as a history-aware evolution strategy. Stride separates constraint evaluation - whether each requirement is satisfied - from visual grounding - where and how it is violated. It then routes global revisions to a composer subagent and local corrections to a retoucher subagent. Each subagent conducts internal planning and generates multiple candidates, while Stride accepts a candidate only when it improves the verifier score, reducing regression across iterations. Because stochastic generators and imperfect verifiers make any single step unreliable, it is this combination of scale-aware routing, per-step redundancy, and monotonic acceptance that yields stable improvement across iterations. With fully open-weight generator-verifier systems, Stride outperforms proprietary systems including Nano-Banana-2.0 and Seedream-5.0-Pro on BizGenEval, matches GPT-Image-2.0 and surpasses Seedream-5.0-Pro on IGenBench, and achieves a new state-of-the-art score on WISE, while substantially outperforming existing agentic methods across all evaluated benchmarks.
multi-agentagenticagent frameworkbenchmark - arxiv:2610.13494 · cs.AIHumanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent LimitsChangye Li, Zijian Zhang, Muheng Li, Yiduo Pang +11
Existing LLM-based agent approaches for long-horizon machine learning engineering (MLE) often use context engineering, implemented through custom harnesses that manage tools, skills, and accumulated experience. However, we find that as single-session execution lengthens, the agent's reasoning intensity declines alongside slowing progress, summarized as long-horizon deceleration, and the benefits of these custom harnesses vanish as the underlying model improves, summarized as harness staleness. These findings suggest that their benefits may not persist across versions, which motivates a workflow-level approach in which agents build on one another's work across sessions. We model these alternating agent sessions as a context-reset semi-Markov decision process (CR-SMDP) and establish sufficient conditions for alternation to exceed single-agent reference limits, derive an explicit experiment-budget bound, and characterize when session caps preserve this advantage. Guided by this analysis, we introduce Humanize MLE Agents (HMA), which alternates two agents on a shared workspace, limits each session to at most k experiments and resets the context between sessions, without additional task-specific harness or prior knowledge supplements. Across 75 Kaggle tasks in MLE-bench, HMA reaches a state-of-the-art any-medal rate of 78.2%, exceeding the strongest open-source baseline by 8.0 points with a quarter of its time budget. Moreover, among six configurations spanning five heterogeneous agent pairs, HMA improves any-medal rate over the constituent baselines by 6.4 points on average, demonstrating cross-pair generality. A supplementary case on kernel optimization reaches 878 cycles, within 1.6% of the community leaderboard leader, demonstrating applicability beyond MLE.
agentmulti-agentleaderboard - arxiv:2610.13485 · cs.CLProactive Agentic OrchestrationXueyang Feng, Chaozhuo Li, Xiaohe Bo, Jiakai Tang +3
Agentic orchestration delegates tasks to sub-agents with independent contexts, providing a key path to extending the effective execution horizon of large language model agents. However, existing orchestration methods face two limitations: in execution, current methods fix sub-agents' goals and harnesses at creation time, limiting their adaptability to dynamic real-world environments; in optimization, sparse and delayed feedback constrains effective learning of the orchestration policy. To address these limitations, we introduce POrchestra, an on-the-fly proactive agentic orchestration framework. It allows sub-agents to proactively communicate with the orchestrator at any logical point to request harness adjustments while maintaining continuity of local execution. This mechanism not only enables sub-agents to adapt seamlessly to dynamic environments but also naturally inspires On-Policy Orchestration Distillation (OPOD) based on hindsight feedback. OPOD attributes sub-agents' proactive revision requests back to preceding orchestration decisions to derive targeted improvement signals, and leverages these signals as process supervision alongside the final reward to optimize the orchestration policy. We evaluate POrchestra on three long-horizon agent benchmarks spanning deep research, dynamic digital assistance, and software engineering. POrchestra improves task success by an average of 9.1% relative to the strongest baseline; combined with OPOD, it improves small-orchestrator success by an average of 10.0% relative to existing training baselines. POrchestra also achieves a more favorable cost-performance trade-off. Our code is publicly available at https://github.com/XueyangFeng/POrchestra.
agentagenticagent benchmarkbenchmark - arxiv:2610.13481 · cs.AIBranching On-Policy DistillationDongyang Chen, Shudong Liu, Shubo Li, Duoxun Tang +3
On-policy distillation (OPD) provides teacher supervision on student-generated trajectories, but a single trajectory realizes only one continuation at each decision, limiting supervision coverage under a finite sampling budget. We propose BranchOPD (Branching On-Policy Distillation), which selects informative decision points using student uncertainty and teacher-student disagreement, resamples student-policy continuations from shared prefixes, and applies token-level teacher supervision to both main trajectories and branches. BranchOPD operates at token-level decisions in mathematics and within-turn decisions in agent tasks. Shared-prefix reuse reduces student-generated token costs by approximately 19% on ALFWorld and 31% on WebShop relative to seven independent trajectories. We also introduce protocol-boundary repair (PBR), which uses targeted supervision under protocol constraints to mitigate repetition and wasted generation. BranchOPD outperforms Vanilla OPD and Multi-Rollout OPD (n=7) across all evaluated benchmarks, with gains over Vanilla OPD of 18.55 percentage points in mean mathematics accuracy over 16 sampled answers (avg@16) and 13.8 points in mean ALFWorld ID/OOD success. Mechanistic analyses and selection ablations show that branching at uncertain decisions expands subsequent behavior coverage and outperforms random selection and turn-initial branching.
agentbenchmark - arxiv:2610.13480 · cs.LGA Scalable Learned Iterative Solver for Nonlinear MPC via Temporal DecompositionLukas Lüken, Sergio Lucia
Nonlinear model predictive control (NMPC) can be applied to large nonlinear systems with complex objectives while enforcing constraints, but the cost of solving the underlying optimization problems limits real-time application for systems with fast dynamics or many states. Neural networks can reduce this online cost by approximating the control law, but may violate constraints and typically require many precomputed optimizer solutions for training. The learning-based iterative solver for constrained optimization (LISCO) instead learns to predict primal-dual steps toward satisfaction of the Karush-Kuhn-Tucker (KKT) conditions through self-supervised training without precomputed solutions, but its dense, monolithic architecture grows with the prediction horizon. We remove this horizon dependence by exploiting the temporal structure of the problem in the solver architecture, which makes the network size independent of the horizon while leaving the training loss and the solver iteration unchanged. A closed-loop resampling strategy further aligns the training distribution with closed-loop operation at no additional sampling cost. On an economic NMPC benchmark of a CSTR cascade, the proposed solver scales to larger problems than monolithic LISCO and achieves median speedups of up to a factor of four over IPOPT. In closed loop, it achieves comparable control performance to IPOPT with no observed constraint violations.
benchmark - arxiv:2610.13479 · cs.ROA Local Agentic AI Framework to Generate Edge Case Scenarios for Safety AssuranceVictoria J. Hodge, Colin Paterson, Rob Alexander
Generating edge case scenarios is crucial for training, testing and safety assuring autonomous systems. This identifies hazardous failures to increase system reliability and robustness, ensures the system can still function safely on the boundaries of its operational design domain and learns the expected system behaviour for these edge cases. The rapid advancement in the generation and analysis capabilities of language models (LMs) has expanded their applicability and recent work has investigated LM scenario generation. However, many recent approaches rely on human-in-the-loop or rule-based strategies. This restricts the LM's ability to generate diverse and edge case scenarios; the long tail of the distribution. Our work uses local LMs in a laptop-based agentic AI framework for adaptive scenario generation. This is cheap, fully-controlled, ensures data privacy and security. It uses think, act, observe, update, and continue loops with lightweight JSON encoding to generate scenarios. We use the system requirements, system description and environment description as knowledge bases in contextual prompts for an LM to ensure scenario realism. A second, independent LM critiques each scenario using domain specific criteria so it can be refined. The refined scenarios are run in simulation and evaluation metrics collected. These metric scores are analysed and similar scenarios are created for edge cases (exploitation) or novel scenarios are generated to explore the scenario space. Post-hoc clustering using metric scores and thematic-type analysis of the rich-text scenario descriptions produced by the LM pinpoints functional gaps and their triggering conditions. This creates traceable evidence for the safety assurance case. Our work highlights the potential of a flexible and adaptive local agentic AI framework for automating edge case generation and producing traceable safety assurance evidence.
agentichuman-in-the-loop - arxiv:2610.13466 · cs.CVA Real-World CAD Segmentation Benchmark: Comparing Rule-Based and Learning-Based Approaches through Hole DetectionKai Schütte, Edgar Heinert, Matthias Rottmann
CAD segmentation datasets are predominantly synthetic or automatically labelled, leaving it unclear how well existing methods transfer to real-world engineering tasks. Fastener-relevant hole detection represents one such task, requiring human annotation and exhibiting greater geometric complexity than commonly used benchmarks. We address this gap through three main contributions. First, we develop two task-specific rule-based methods, one graph-wire-search and one multi-view based, and complement them with a human-annotated benchmark dataset derived from engineering CAD data that also enables training of UV-Net and AAGNet, representative learning-based approaches for B-Rep segmentation. Second, we conduct an extensive experimental study including parameter optimisation, evaluation on our benchmark dataset, cross-domain generalisation on a synthetic dataset, and an assessment of the feasibility of the approaches at varying dataset sizes and IoU thresholds. Third, we provide evidence-based insights into the strengths and limitations of different approaches: rule-based methods generalise well without training data, with the graph-wire-search method favouring recall and the multi-view method favouring precision, whereas learning-based methods achieve strong performance with sufficient annotations but exhibit reduced robustness under domain shift. These findings highlight trade-offs between data requirements, and robustness, and provide guidance not only for hole detection, but more broadly for real-world CAD segmentation tasks.
benchmark - arxiv:2610.13461 · cs.LGSqueezeBench: Saturation-Resilient Evaluation of Mathematical CapabilityPablo Manrique, Hai Xia, Stefan Szeider
AI systems are making rapid progress in mathematics, but this progress is hard to measure. Benchmarks of solved problems saturate, and in benchmarks of open problems each problem can be resolved for the first time only once. We present SqueezeBench, a benchmark that is resilient to saturation: a success raises the bar instead of removing the problem. Each problem fixes an integer function $f(n)$ whose values are known only for small $n$, and the benchmark keeps a lower and an upper record on it. A record is a computable Lean function with a machine-checked proof that it bounds $f$. A submission proposes a new function and proves that it bounds $f$, that it is no worse than the current record at any $n$, and that it is strictly better at some $n$. Once accepted, it becomes the record that the next submission has to beat. The system thus chooses the bound as well as its proof, and it may improve the record at a single $n$ or its growth rate. At every $n$, the gap between the two records shows how far the certified bounds are from determining $f(n)$. Every proof is checked by two independent Lean kernels, so no referee needs to check the mathematics. The checks also reject a function that computes $f$ by exhaustive search at small $n$, and a maintainer only reads the submitter's report and looks for such a search at larger $n$. We release ten problems from extremal combinatorics with twenty proved initial records and the admission tools. As a baseline, agents based on a frontier language model, with at most one hour per record, had 82 submissions accepted and improved every record, without going beyond the published literature. Agents based on two newer models then started from these records, had 60 more submissions accepted and improved 19 of the 20 records again. For eight of the ten problems, at least one record is still asymptotically behind the best published bound.
benchmark - arxiv:2610.13455 · cs.AIAgentic Large Language ModelsMax van Duijn, Michiel van der Meer, Aske Plaat, Niki van Stein
Large language models (LLMs) have taken the world by storm. Their ability to communicate with us in our own language, and to reason about our world, has made them a favorite tool for writing, answering questions, and much more. Their answers already influence our decisions and our actions. What would happen if LLMs themselves could act in the world directly? What would happen if LLMs could interact with each other? Agentic LLMs combine the power of large language models with the ability to act in the real world. In this book we will discuss how agentic LLMs work, how they act, how they interact, and what this means for us, as users.
agentic - arxiv:2610.13453 · cs.ROReflect-VLA: Internalizing Reflective Guidance via Dual-Path On-Policy Self-Distillation for Autonomous DrivingYuechen Luo, He Chong, Fang Li, Shaoqing Xu +6
Reinforcement Learning (RL) substantially improves planning performance in autonomous-driving Vision-Language-Action (VLA) models. However, existing RL methods rely on scalar trajectory rewards that measure overall quality but fail to identify specific planning errors or provide actionable correction signals. In long-tail scenarios, errors in scene understanding, behavior selection, and trajectory execution are compressed into a single score. We observe that Reflective Guidance turns trajectory evaluation into explicit diagnoses and corrective instructions, substantially improving planning accuracy. Yet such guidance requires an initial prediction and its evaluation results, making it unavailable for direct single-pass inference. We propose Reflect-VLA, which treats Reflective Guidance as training-time privileged information and internalizes its planning benefits through Dual-Path On-Policy Self-Distillation (Dual-OPSD). Unlike scalar-reward optimization, Dual-OPSD uses the driving score only to route student-generated trajectories. It distills dense token-level corrective distributions from the teacher for risky trajectories while applying self-imitation to preserve reliable ones. To provide reliable corrective distributions on student rollouts, the teacher is progressively constructed through Driving-Knowledge Pretraining, Planning-and-Refinement SFT, and Self-Refinement Rejection Sampling. At inference time, Reflect-VLA generates trajectories in a single pass without explicit guidance or iterative refinement. Experiments on NAVSIM v1/v2 and Bench2Drive demonstrate competitive planning performance while reducing training time by over 90% compared with RL.
vision-language-actioniterative refinementself-refinement - arxiv:2610.13448 · eess.SYAdaptive Incentive Design for Linear-Quadratic Dynamic Games: No-Regret Social CoordinationLantian Zhang, Yibei Li, Georgios Vasileiou, Lihua Xie +1
Incentives can align private interests with collective goals, but their design becomes intertwined with learning when agents' preferences are unknown. This paper develops an adaptive incentive-design framework for multi-agent linear-quadratic dynamic games, where a system planner can simultaneously learn agents' private preferences and steer their strategic behavior towards the social optimum. To this end, we first characterize the complete family of affine incentives that implement the social optimum as the unique open-loop Nash equilibrium while ensuring exact budget balance. When agents' preferences are unknown, we develop an online algorithm to estimate their preference parameters and establish strong consistency of the estimates under a weak trajectory-dependent excitation condition, without requiring persistent excitation or i.i.d. trajectories. We then integrate this estimator into an active-learning incentive mechanism that combines certainty-equivalent coordination with decaying random probing. We prove that the probing generates sufficient information through the agents' equilibrium responses and the system dynamics, ensuring consistent preference learning from the resulting closed-loop trajectories. We show that the induced trajectories converge almost surely to their socially optimal counterparts, while cumulative social-cost regret relative to the full-information oracle and cumulative net-budget imbalance grow sublinearly. Simulations of a transboundary pollution game demonstrate the effectiveness of the proposed framework.
multi-agent - arxiv:2610.13439 · cs.AICollective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human DriversAnastasia Psarou, Mikolaj Rams, Blazej Torbus, Rafal Kucharski
Collective Autonomous Vehicle (AV) route choices in real-world traffic networks can create externalities for Human-Driven Vehicles (HDVs), as routes that benefit AVs may increase travel times for other road users. To address this, we introduce a social component, the marginal cost, to the selfish travel time AV reward. Marginal cost captures an AV's impact on other road users by comparing their travel times with those in a counterfactual simulation in which the AV is removed. We study AV route choice in mixed-autonomy traffic settings using Multi-Agent Reinforcement Learning (MARL), where AVs learn routing policies through repeated interactions with the traffic environment. Experiments on the real-world networks of Ingolstadt and Provins show that incorporating marginal cost into the AV reward not only limits the increase in HDV travel times and shortens AV travel times relative to selfish AV routing, but also improves overall system performance. In Ingolstadt, selfish routing of 40\% AVs increases the travel times of other vehicles by 1.7\%, and this drops to 1.1\% when the social reward is included. Interestingly, not only does overall system performance improve, but the AVs are also better off when acting socially.This effect is consistent across tested cities, penetration rates, and replications, yet when the weight of the social component in the reward increases, the system fails to reach the desired performance. For a more scalable approach to social AV routing in mixed-autonomy traffic, we compute the marginal cost only for the AVs whose route choices most affect the traffic system. This reduces the number of counterfactual simulations and achieves similar performance at a significantly lower computational cost. Our results suggest that AV routing should go beyond selfish rewards and, for the benefit of all traffic participants, include a social component in its objective.
multi-agent - arxiv:2610.13438 · cs.AIRollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy LimitsChen Xi, Ding Ruixue, Wang Zhigaoyuan, Zhang Fanrui +8
Reinforcement learning (RL) has emerged as a key paradigm for improving large language model (LLM) agents, enabling stronger reasoning, planning, and tool-use in interactive environments. However, existing agent RL methods remain fundamentally constrained by an on-policy reasoning bottleneck: when tasks exceed the model's current capability boundary, effective trajectories become extremely sparse and training often collapses. We introduce Rollout-Time Intervention (RTI), a technique designed to elicit successful trajectories beyond the policy's intrinsic exploration capacity. RTI operates by leveraging reward-side evidence (i.e., evaluation rubrics) during rollout to convert erroneous trajectories into successful ones, providing effective learning signals for tasks that the policy rarely solves on its own. Although intervention trajectories are inherently off-policy, we find that they can effectively guide policy optimization when trajectories with excessive distributional shifts are filtered out. Extensive experiments across five benchmarks demonstrate that RTI consistently outperforms RL baselines, enabling the post-trained policy to approach the performance of substantially stronger contemporary LLMs and, more importantly, transcend its original capability boundary. The code is available at https://github.com/Alibaba-NLP/qqr.
agentagentictool-usebenchmark - arxiv:2610.13437 · cs.AILocal Diagnostics of Learned Event Representations for Anomaly Detection at the HL-LHCDonatella Genovese, Philip Ploner, Simone Scardapane, Stefano Giagu +1
Anomaly detection, the identification of collision events that deviate from Standard Model expectations, is one of the most promising model-agnostic strategies for new-physics searches at the Large Hadron Collider. Searching for rare events in learned low-dimensional representations removes the need to commit to hand-crafted observables a priori, but sacrifices the immediate physical interpretation those observables provide. For anomaly detection to enter a discovery pipeline, flagged events must therefore be diagnosed locally, both to distinguish potential new physics from mismodeling or detector effects and to identify observables for targeted follow-up searches. We evaluate supervised and self-supervised neural embedding strategies on COLLIDE-2V, a 750-million-event dataset simulated under realistic High-Luminosity LHC conditions, using the reconstruction error of an autoencoder trained in the learned latent space as the anomaly score. Across the configurations and benchmark signals considered, supervised objectives, which exploit simulation process labels during training, generally outperform their self-supervised counterparts and, in their best configurations, improve on an autoencoder trained directly on kinematic features, raising the signal efficiency at 10% background acceptance on all held-out processes. We further introduce a local diagnostic pipeline that fits a Gaussian Mixture Model to the SM latent space, profiles each component through high-level observables without process labels, localizes the flagged events, and ranks observables by their local discriminating power. The ranking recovers the defining kinematics of the held-out processes, while correlating the anomaly score with the same observables quantifies how closely the score tracks them, revealing cases where the most discriminating observable is not the one the score follows most closely.
benchmark - arxiv:2610.13435 · cs.LGPPG-Bench: A Unified Benchmark for PPG Foundation ModelsArvasu Kulkarni, Mahir Jain, Aditya Ray Mishra, Sandeep Singh +1
Photoplethysmography (PPG) is increasingly recorded by wearable and clinical devices at enormous scale, and a growing number of PPG foundation models (FMs) have been developed to compute reusable representations for various downstream tasks. These models are difficult to compare: different evaluations use different datasets, task definitions, preprocessing, downstream heads, hyperparameter tuning, and baselines. We present PPG-Bench, a unifying open-source benchmark evaluating five public PPG FMs across nine open-access datasets and 26 tasks spanning cardiovascular state estimation, activity, sleep, screening, and identification. We evaluate models under four downstream regimes of increasing adaptability (linear probing, random forests, frozen MLP probes, and end-to-end finetuning), with model-specific hyperparameter optimization and subject-disjoint cross-validation. We also evaluate against three controls: random/constant baseline, a deterministic pulse-rate-variability (PRV) feature set, and a generic time-series FM (MOMENT). Across all 68 task-regime combinations, 35.3% show no meaningful FM advantage over the random/constant baseline, and in 83.8% no PPG-specific FM outperforms both PRV and MOMENT. We also find that added downstream head capacity generally improves performance, but can cause significant degradation if the model is performing at chance/constant level. Current PPG FMs therefore cannot yet claim to provide generalised and transferrable representations of PPG signals, and future evaluation in this field should include checks against simple, non-learned controls. Code for the benchmark and instructions to evaluate more models can be found here - https://github.com/mannas-ai/ppg-bench.
benchmark - arxiv:2610.13432 · cs.LGDoes Financial Speech Need Continual Learning Regularization? A Study of EWC and mini-KFAC on Earnings Call ASRThai Quoc On, Homayoon Beigi
Earnings call transcription presents a realistic continual learning scenario where Automatic Speech Recognition (ASR) systems are updated with new recordings but risk catastrophic forgetting of previously learned financial speech patterns. Adapting Whisper-small from a general-domain speech corpus to the Earnings22 benchmark reveals the opposite: all evaluated methods exhibit improvement on held-out financial speech from the same domain during adaptation rather than forgetting. This task complementarity makes regularization counterproductive. Nevertheless, when regularization is warranted, a layer-wise mini-Kronecker-Factored Approximate Curvature (mini-KFAC) approximation seems to achieve lower word error rates (WERs) and more stable optimization than standard diagonal Elastic Weight Consolidation (EWC). The results suggest that task complementarity should be assessed before applying continual learning constraints, and prefer mini-KFAC EWC over diagonal EWC when needed.
benchmark - arxiv:2610.13430 · cs.LGOne Thing Leads to Another: The Essentials of Time Series Causal DiscoveryKurt Butler, Damian Machlanski, Michael P. J. Camilleri, Zhihua Liu +4
Time series causal discovery --- the process of detecting causation between time series --- has its roots in signal processing research from over a half century ago. It has since received active and widespread interest, evolving into different forms across domains such as statistics, dynamical systems and machine learning. Entering this fragmented and constantly evolving research landscape can be daunting. This tutorial provides a unified overview of time series causal discovery across research communities. We introduce the key principles invoked by modern discovery methods, and we discuss their limitations and assumptions. We also discuss how discovery methods are evaluated, benchmarked and fine-tuned. We further discuss how causal discovery for time series is becoming crucial for downstream tasks in agriculture and Earth science, in healthcare, and in artificial intelligence systems. We believe that this tutorial will serve as a valuable resource in navigating the deluge of recent causality research, as well as an invitation to signal processing audiences to contribute to causal problems. To further help readers, we host a companion repository to link to useful code packages and resources at https://github.com/CHAI-UK/Awesome-Time-Series-Causal-Discovery.
benchmark - arxiv:2610.13416 · cs.AIWeb$hell: A Unified Interface for Agentic Web AccessSunghwan Kim, Deogyong Kim, Sangam Lee, Donguk Kwon +1
Large language model (LLM) agents are becoming direct users of the open web. As they take on increasingly complex and information-intensive tasks, effective web access is becoming a core capability for agentic problem solving. Existing approaches have advanced agentic web access through different access models, including search-augmented agents, browser-based agents, and, more recently, filesystem-based agents. Nevertheless, as users expect agents to complete long-horizon, end-to-end tasks, they increasingly need to conduct broad information gathering, perform browser actions, and revisit acquired evidence within a single trajectory. Yet our preliminary analyses reveal that existing access models struggle to meet these demands. They primarily support either information gathering or browser interaction, while combining their capabilities can involve substantial costs or performance trade-offs. To this end, we present Web\$hell, an interface that unifies web access under a single access model. Using a common schema defined by WebContract, WebCompiler compiles live webpages into addressable information and action objects. These objects are maintained in WebCache and handled through a shared set of operations, providing agents with consistent, operable, and persistent web access. Through extensive experiments across web search, web navigation, and deep research benchmarks, we show that Web\$hell achieves strong task performance at lower cost. Our results further indicate the importance of interface design for effective web access, with Web\$hell opening new possibilities for more capable and efficient LLM agents on the web.
llm agentagenticbenchmark - arxiv:2610.13412 · cs.CVTextVBench: Evaluating Text Rendering and Preservation in Video GenerationRuiqiang Zhang, Hengyi Wang, Chang Liu, Guanjie Wang +2
Modern video generators can synthesize convincing scenes while rendering a few characters incorrectly, omitting requested text, or changing it across frames. Measuring these failures is harder than applying OCR independently to each frame: when a scene contains multiple text targets and multiple noisy OCR regions, the evaluator must first determine which observation belongs to which intended text. We introduce TextVBench, a benchmark and evaluation framework that formulates visual-text evaluation as a multi-target, multi-instance spatiotemporal correspondence problem. TextVBench contains two complementary tracks: TextVBench-T2V measures the creation and maintenance of prompt-specified text, while TextVBench-Ref2V measures preservation of text from reference images. Both tracks use target-conditioned candidate selection rather than unconstrained VLM transcription, support one target mapping to multiple OCR regions, and separate frame-level spatial fidelity from cross-frame temporal fidelity. A length-weighted harmonic score summarizes these factors, while extra-text diagnostics expose failure modes hidden by a single OCR score. The benchmark is organized around controlled text, layout, carrier, and motion attributes so that aggregate scores can be traced back to specific capability limits. Across the evaluated model runs, MiniMax-H3 reaches a T2V TextVScore of 68.32, while the strongest Ref2V score is 56.51; attribute slices reveal a pronounced drop as the number of simultaneous reference text regions increases.
benchmarkevaluatorevaluation framework - arxiv:2610.13411 · cs.LGIn-Context Learning for System Identification: Probabilistic Formulation, Long-Sequence Handling, and Benchmark ValidationMatteo Rufolo, Dario Piga, Filippo Pura, Marco Forgione
Traditional system identification typically involves two steps: initially, training data is processed to estimate a model of the system of interest; then, the model is used to predict outputs for new input queries. In contrast, recent in-context learning approaches learn a meta model that maps directly from training data and query inputs to outputs in a zero-shot fashion, bypassing explicit model estimation. This approach leverages a meta model trained offline, on large sets of synthetically generated data, to emulate the behavior of a system identification algorithm. In this work, we advance this meta-learning framework for system identification in three directions. First, we develop a unified probabilistic meta-identification architecture that combines a Transformer-based encoder-decoder with tailored mechanisms for handling long training sequences, enabling calibrated predictions over long horizons. Second, we show how a pre-trained meta model can act as an uncertainty-aware synthetic data generator for classical system identification, providing task-specific data that regularize parametric models when real data are scarce. Third, we systematically evaluate the framework on standard nonlinear system identification benchmarks and on a challenging out-of-distribution scenario, demonstrating competitive accuracy with state-of-the-art methods and strong generalization, including cases where input-only adaptation is sufficient to handle significant distribution shifts.
benchmark - arxiv:2610.13409 · cs.ROManeuverFlow: Maneuver Hypothesis Generation with Future Evidence for Trajectory Evaluation and Refinement in End-to-End Autonomous DrivingYuhao Wei, Yong Chen, Chen Yang, Yingchen Wang +6
End-to-end planning in complex scenes must model diverse driving intentions and select the most appropriate trajectory using scene context and future risks. However, multi-query regression may collapse to one mode, while anchor-based and generative planners share a scaling bottleneck: small candidate sets limit maneuver coverage or discovery of high-quality trajectories, whereas large sets increase generation and scoring costs. We propose ManeuverFlow to generate trajectories for distinct intentions in one step and evaluate and refine them using current and future evidence. The model selects relevant maneuver modes, draws corresponding noise from the Gaussian mixture prior, and maps it to intention-specific trajectories through a maneuver-routed mixture-of-experts MeanFlow field. Current features and future features predicted by the world model are aggregated along each candidate path into trajectory-specific evidence for PDM-factor prediction. Using the same evidence, the refiner predicts local Frenet residuals for selected candidates; refined and retained candidates are then jointly re-scored for selection. With a lightweight TransFuser-style ResNet-34 backbone, ManeuverFlow achieves 90.6 PDMS and 90.1 EPDMS on NAVSIM v1/v2 navtest, respectively. On WorldEngine's recent 3DGS closed-loop benchmark, it attains the highest listed PDMS$^\ast$ scores of 75.19 and 74.58 under logged and IDM-controlled traffic, respectively. Code: https://github.com/wyh-autonomy/maneuverflow.
world modelbenchmark - arxiv:2610.13403 · cs.RORobot-WATCHDOG : failure detection through object-centric graph representationQuentin Rolland, Fabrice Mayran de Chamisso, Jean-Baptiste Mouret
Reliable real-time failure detection is critical for deploying learned robotic policies, yet defining failures explicitly is infeasible in open-world settings. This motivates failure detection from nominal demonstrations alone. Existing methods, however, struggle to balance robustness to benign variations with the ability to capture semantic and interaction-level errors. We introduce Robot-WATCHDOG, a self-supervised framework that models manipulation scenes as object-centric spatio-temporal graphs. Building on this representation, we investigate two complementary failure scores: Trajectory Projection and Correlation (TPC), a non-parametric measure of geometric deviation and relational consistency, and GnnT, a Graph Attention Network with a Transformer that predicts future object states. We evaluate both on a public benchmark and on a new dataset of semantically complex manipulation tasks, across six tasks and ten random seeds. Both scores outperform image-based failure detectors, particularly on semantic and interaction-level failures. TPC provides the strongest performance in AUPR and MCC on both dataset averages, with low variance across seeds. Qualitative results are made available at https://cea-list.github.io/Robot-WATCHDOG/.
manipulationbenchmark - arxiv:2610.13399 · cs.AIRegulaTutor: A Theory-Informed Framework for Long-Term Personalized LearningYonggang Li, Boqian Han, Rui Sheng, Yushi Sun +1
Long-term personalized tutoring requires language models to translate a learner's evolving history into appropriate instructional support. Existing LLM-based tutoring systems use memory and retrieval to personalize responses, but the pedagogical rationale linking historical evidence to teaching strategies is not always explicit. We introduce RegulaTutor, a theory-informed framework for long-term personalized tutoring that connects historical evidence, learner interpretation, and learner-facing instruction. Guided by self-regulated learning (SRL) research, its tutoring harness operationalizes a cognitive, affective, metacognitive, and motivational (CAMM) framework for deriving evidence-supported learner interpretations and teaching policies. The resulting policies retain links to their supporting evidence and are updated as new observations arrive. This staged workflow also supports systematic refinement through PairRoute, an offline procedure that uses intermediate execution records to distinguish harness, model, and mixed failures. PairRoute proposes and evaluates targeted harness revisions, then constructs reviewed stage-level supervision for confirmed model failures remaining under the selected harness. We focus this refinement on historical evidence acquisition, which underpins personalized instruction and allows outputs to be checked against learning records and reference answers. RegulaTutor improves historical-evidence accuracy, learner diagnosis, and judged teaching quality on average across evaluated model configurations. PairRoute results show an endpoint improvement in standalone-model historical-evidence accuracy over the refinement trajectory. Together, these results highlight RegulaTutor's potential to support lifelong personalized education through instructional policies that evolve with learner histories and targeted improvements to the tutoring system.
memory - arxiv:2610.13395 · cs.AIProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction AgentsChengyi Yang, Renxu Bao, Jue Hou, Zongpei Teng +9
Coding agents are increasingly used to build programs from scratch as software engineers do rather than to resolve issues within a repository or to generate a repository from a given requirements document. However, scalable verifiable training environments that force agents to discover what is required and to decide how the system should be designed remain scarce. Moreover, existing agent workflows also cannot sustain long-horizon development in which the agent explores the reference program before implementation. To address these challenges, we introduce ProgramGym, a framework consisting of Program-Env and Program-Agent for scalable training environments of long-horizon program reproduction agents. Specifically, Program-Env constructs verifiable training environments from repositories through a feedback-driven loop that repairs runtime sandbox builds and the quality of black-box tests. Using this novel pipeline, we obtain 1,648 training environments spanning C, C++, Go, and Rust. Program-Agent combines a role-isolated workflow of analysis, implementation, and review with revision management for compilation checks and failure recovery. Experiments on ProgramBench show that both Program-Env and Program-Agent improve performance on program reproduction. Fine-tuning on trajectories with these constructed environments raises the performance of Qwen3.8-27B from 34.87% to 42.84%. Program-Agent further raises the base and SFT models to 55.71% and 56.25%, both exceeding some flagship models. We will release the ProgramGym to support further research on coding agents that build programs from scratch.
agent - arxiv:2610.13390 · cs.LGPlacePulse: Learning Transferable Place Representations from Structural Geographic DataLucía García-Duarte, Miguel Álvarez, Diego Vicente, Javier Pérez Trufero +1
Geospatial machine learning often depends on task-specific feature engineering over large collections of sociodemographic, business, and environmental variables. Geospatial foundation models offer reusable representations of place, but leading approaches typically encode dynamic signals, such as mobility and search activity, or visual signals from satellite imagery. Few models represent the static structural composition of places (who lives and works there, which businesses operate there, and which risks they face) as transferable embeddings at fine spatial resolution. We introduce PlacePulse, a structural geospatial foundation model that compresses 572 attributes, expanded to 2,288 inputs through H3 neighborhood aggregates, into 256-dimensional unit-norm embeddings for 1,055,537 H3 resolution-7 cells in the United States. We also introduce a reusable two-axis benchmark that separates intrinsic representation quality from downstream predictive utility across multiple targets and spatial supports. Intrinsically, the embeddings reconstruct standardized inputs with mean $R^2 = 0.853$, use 251 of 256 approximately decorrelated dimensions, and show strong spatial organization, with Moran's $I = 0.93$ on the leading principal component and autocorrelation persisting beyond the input radius. Extrinsically, across 74 held-out targets from 12 external sources and four spatial supports, PlacePulse outperforms a dimensionality-matched feature-selection baseline on targets unrelated to the training inputs and is competitive with Google's Population Dynamics Foundation Model, leading on health, economic, election, economic-mobility and social-vulnerability outcomes, with relative strengths that vary by domain. These findings position structural composition as a distinct and complementary modality for geospatial foundation models, not simply a fallback where behavioral or imagery data are unavailable.
benchmark - arxiv:2610.13386 · cs.CLMoPrO-SD: Modular Prompt Optimization for Stance DetectionMeysam Sabbaghan, Nikesh Gyawali, Arman Zareian Jahromi, Sebastian Loera-Lozano +2
Stance detection remains challenging for large language models (LLMs) due to implicit opinions, sarcasm, and context-dependent expressions of stance. Although automatic prompt optimization offers an alternative to fine-tuning without updating model parameters, existing structured approaches are not specifically designed around stance-label semantics and class-specific ambiguities. We introduce MoPrO-SD, a stance-specific prompt optimization framework that decomposes prompts into functional semantic modules and refines them sequentially using LLM-based feedback. We study three refinement strategies: instruction-only optimization (I), instruction with reasoning (I+R), and instruction with per-example reasoning (I+R+E), using class-conditioned errors for stance-label refinement. We also introduce VaccineStance, a new human-annotated benchmark for vaccine stance detection. Experiments across four datasets and five open-weight LLMs show that MoPrO-SD improves upon the human-written Base prompt in many settings. On SemEval-2016, class-conditioned feedback achieves higher mean Macro-F1 than pooled feedback for four of five backbones. Both reasoning-based strategies, I+R and I+R+E, achieve strong performance, with their relative effectiveness varying across models and datasets, while remaining competitive with recent prompt optimization methods. The MoPrO-SD code and VaccineStance dataset are available on GitHub.
benchmark - arxiv:2610.13382 · cs.LGBLOKS: Scaling Kernel Solvers with Sketched Block PreconditioningGiordano Vitale, Giacomo Meanti, Marco Rando, Blanca Ayuso de Dios +1
Kernel Ridge Regression (KRR) is a theoretically sound algorithm for nonparametric learning, which is also often used to investigate properties of deep learning. However, the exact KRR formulation incurs time and memory costs preventing applicability to large datasets, motivating the development of approximate solvers. These algorithms rely on (i) iterative methods, to avoid the computational burden of direct solutions; (ii) sketching or batching, to reduce the problem size; and (iii) preconditioning, to accelerate convergence. While crucial for fast convergence, preconditioning incurs memory costs that can be managed by lowering the number of free parameters of the model, potentially at the expense of expressivity and hence accuracy. To address this challenge, we propose BLOKS, a Conjugate Gradient-based solver for Nyström-sketched KRR built around a novel preconditioner that combines a block Jacobi approximation with sketching. The BLOKS preconditioner has memory cost independent of both the dataset size and the number of parameters, allowing scaling to large models. We provide a memory-efficient, GPU-accelerated implementation and show that BLOKS achieves excellent accuracy while retaining favorable time/memory complexity. Indeed, on standard large-scale datasets used to benchmark kernel solvers, BLOKS achieves comparable or better performances than state-of-the-art methods.
memorybenchmark - arxiv:2610.13376 · cs.ROEndoRSI: Physical-Evidence-Driven Recursive Improvement of Endoscopic Robot PoliciesChi Kit Ng, Yidong Zhang, Tianchun Wu, Siu Hing Lui +3
Artificial intelligence is beginning to automate scientific discovery, yet physical robot-policy research still relies on scientists and engineers to interpret experimental failures and decide how controllers should be revised. We present EndoRSI (Endoscopic Recursive Self-Improvement), a human-governed, self-improving robotic research system in which the embedded EndoForge coding agent iteratively develops and refines endoscopic robot policies using evidence from physical experiments. Physical execution remains isolated within a safety-constrained runtime under human authorisation. In motorised endoscopy, validation evidence first caused the agent to reject an initial action representation, while subsequent physical experiments falsified an offline-supported insertion strategy by revealing hazardous closed-loop behaviour absent from the source data. Failed physical rollouts were then incorporated into policy revision; insertion success subsequently increased from 2/21 in the first generation to 17/21 in the fourth. The frozen final policy retained competence across visual and hardware shifts and was the best performing autonomous policy across six independent ex-vivo porcine specimens. These results show that physical robot interaction can serve as experimental evidence for agent-driven robot policy research.
robot policyagentself-improvingself-improvement - arxiv:2610.13375 · cs.CLFrom Structure to Validity: Mechanism-Guided Generation and Refinement of LLM RubricsFeifei Qian, Xuan Chen, Lixin Cui, Chaoyang Mei +5
Rubrics have been widely used to evaluate and optimize language models on open-ended tasks. However, existing work primarily focuses on generating better rubrics, with limited understanding of what makes rubric design effective. In this work, we conduct a systematic mechanistic analysis of rubric design across criterion organization, criterion operationalization, and score aggregation. Our analysis shows that structural organization enables more comprehensive criterion construction, semantic specification alone does not ensure effective criterion-level judgments, and sophisticated score aggregation provides limited additional gains. Guided by these findings, we introduce Adaptive Rubric Tree Search with Hybrid refinement (ARTS-Hybrid), which combines adaptive tree construction with semantic-first, response-calibrated refinement. Experiments across benchmarks show that ARTS-Hybrid improves both end-to-end evaluation performance and intrinsic rubric quality. Further experiments suggest that, beyond evaluation, rubrics generated by ARTS-Hybrid provide effective signals for model optimization.
benchmark - arxiv:2610.13373 · cs.ROPartiGen: Part-Aware Representations for Language-Conditioned Humanoid Motion GenerationChuxuan Huang, Zhanxiang Cao, Tianyue Zhan, Haoyang Li +13
Translating language into humanoid motion requires coordinating body parts, determining motion duration, and producing references suitable for robot execution. We introduce PartiGen, a part-aware latent diffusion framework that incorporates anatomical structure into a shared whole-body motion representation. Part-specific attention processes anatomically masked frame features, and its outputs are fused to combine local limb information with whole-body context. Conditioned on text and motion history, the model generates motion primitives autoregressively. Forward-kinematics supervision encourages kinematic consistency, while a learned end-of-sequence predictor selects a frame-level endpoint after generation. On HumanML3D retargeted to the Unitree G1, PartiGen achieves a segment-level FID of 3.165, a 16.8% reduction over TextOp, and improves R@1 by 1.4 percentage points. In the duration study with 16-frame primitives, endpoint prediction reduces mean absolute duration error from 12.471 to 3.080 frames compared with a fixed-length cutoff. We further evaluate robot execution using a pretrained, frozen GRIT tracker: 409 of 500 generated references (81.8%) pass the posture-based stability screen in MuJoCo. Following simulation screening and manual selection, 26 of 27 attempted motions are judged successful on the real G1.
humanoid - arxiv:2610.13361 · cs.LGAgentSWE: Can Coding Agents Build the Agent You Actually Want?Jiahao Wang, Hongjin Qian, Yuyang Hu, Jiajun Zhang +1
As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their users' own workflows. This delegation carries a quiet assumption, that the delivered agent will faithfully serve the requirement it was built for, rather than merely appear to. No existing benchmark tests that assumption. We introduce AgentSWE, a benchmark for agent software engineering spanning three stages of the agent development lifecycle: Creation of a complete agent from a natural-language requirement, Editing of production agent codebases, and Optimization toward a measurable target. Each of its 25 tasks is framed as a commission rather than an exam: the builder iterates against a handful of illustrative cases, while acceptance exercises the frozen submission on held-out cases designed to span the full requirement, grading behavior against requirement-derived rubrics under hard pass/fail gates or, for Optimization, against the source benchmark's own objective. Evaluating a range of coding agents across models and harnesses, we find that none comes close to delivering what a requirement asks for: the gap between what a builder demonstrates and what it delivers is the norm, not the corner case. An accompanying empirical analysis of the failure trajectories identifies recurring failure modes, among them overfitting to the visible cases, hollow runtimes behind code that looks complete, and unsupported claims of completion, each a signal by which coding agents can learn to build the agents they are asked for.
agentbenchmark - arxiv:2610.13357 · cs.CVECGWmark: Deep Watermarking for Electrocardiogram SignalsKuan-Yu Chen, Kuan-Chen Wang, Yu Tsao, Jian-Jiun Ding
Secure transmission of electrocardiogram (ECG) signals remains a major challenge in telecardiology. While traditional mathematical watermarking can embed patient metadata directly into ECG signals, it is highly fragile against temporal desynchronization such as circular phase shifts. In contrast, existing deep watermarking approaches for temporal signals, such as audio, typically rely on lossy quantization, which compromises the high-frequency micro-morphological details critical for clinical diagnosis. To bridge this gap, we propose ECGWmark, a fully convolutional and quantization-free deep watermarking framework for medical time-series. ECGWmark operates in a continuous, full-resolution latent space and utilizes a localized frame-level mechanism to improve the robustness to severe desynchronization. Crucially, we introduce a differentiable Physiological Loss guided by a clinical classifier to preserve diagnostic semantics. Experiments on the benchmark MIT-BIH database show that ECGWmark maintains channel-bit extraction accuracy above 90% under the evaluated circular temporal shifts. Furthermore, under a rigorous inter-patient diagnostic evaluation, Class-V sensitivity changes from 71.97% to 76.50%, whereas Macro-F1 changes from 35.25% to 34.71% and Class-S sensitivity from 8.89% to 1.39%; these results indicate mixed class-level effects.
benchmark - arxiv:2610.13356 · cs.AISWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent TrajectoriesJiajun Hu, Chun Yong Chong
Coding agents are increasingly deployed for end-to-end software engineering tasks, where a readily available oracle evaluator that defines the success criteria is often absent. This motivates verifications for coding agents that can reliably judge and explain their behavior. However, verification is non-trivial as coding agents are increasingly capable of solving long-horizon software engineering tasks. Their execution trajectories can be extremely long, containing hundreds of iterative interactions with code repositories and external tools. Existing verifiers either rely on general-purpose LLMs without specialized training or train dedicated critics that predominantly focus on producing scalar rewards, highlighting the relatively limited exploration of training-based generalist verification. We introduce SWE-Critix, a post-training pipeline for training generalist verifiers of coding-agent trajectories. Given a task and its execution trajectory, the learned verifier predicts the completion label and generates a natural-language analysis that explains its judgment. Our pipeline combines supervised fine-tuning (SFT) with reinforcement learning (RL) and trains a series of 30B models on trajectories from CodeForge-Preview. On a held-out test set, SWE-Critix improves classification accuracy from 57% for the base Qwen3-30B-A3B reasoning model to 66% after SFT and 78% after RL. We release our models, datasets, and training code to facilitate further research.
post-trainingevaluator - arxiv:2610.13354 · cs.ROAlphaNIST: Emergent Assembly Skills from Binary Task RewardsOcti Zhang, Iretiayo Akinola, Rosario Scalise, Mateo Guaman Castro +11
The NIST Assembly Task Board #1 remains a challenging benchmark for learning-based methods in robotic manipulation. Over short horizons, it demands precise, contact-rich control of small, tight-fitting parts. Over long horizons, it requires recovery and coordination across extended action sequences. Demonstrations, task decomposition, and dense progress rewards have enabled research advances by providing guidance on how to assemble. But how much of the strategy must be specified? The progression from AlphaGo to AlphaGo Zero showed that RL at scale can discover superhuman strategies without prescribing how to win. AlphaNIST asks whether a sparse binary task reward and task diversity admitted by this task-agnostic reward can similarly let a robot discover how to assemble. In simulation, we train a single policy from scratch across all 20 assembly tasks on the NIST Assembly Task Board #1, reaching 98.2% overall training success without demonstrations, progress shaping, scripted primitives, or per-task tuning. The framework also trains policies to complete ten assembly pairs in a single episode without a prescribed order, with task success rewarded only when all ten pairs are simultaneously complete. The learned policies discover dexterous and planning-like behaviors: choosing grasps for later assembly, using surrounding geometry to reorient parts, and preparing one part, assembling another, then returning to finish the first without an explicit planner. For videos, see our website: https://alpha-nist.github.io/
manipulationdexterousgraspbenchmark - arxiv:2610.13348 · cs.CLTest-Time Memory ConstructionZijun Wang, Yifan Ji, Haidong Xin, Zhenghao Liu +5
Large Language Models (LLMs) struggle to answer questions over long interaction histories, where relevant evidence may be scattered across distant sessions. Existing memory systems typically construct and maintain sophisticated memory representations offline, before user queries are observed, incurring substantial overhead and limiting their ability to adapt memory construction to query-specific information needs. In this paper, we propose T$^2$Mem, a Test-Time Memory construction framework that defers memory construction to inference and progressively builds memory along the reasoning process. Specifically, T$^2$Mem extracts lightweight episode-level metadata offline to capture key events and temporal associations as retrieval cues, while retaining links to the original interactions to facilitate the reconstruction of dependencies across episodes. At test time, the LLM adaptively retrieves and organizes metadata and raw interactions, progressively constructing query-specific memory as reasoning unfolds. Experiments on LoCoMo and LongMemEval show the effectiveness of T$^2$Mem by consistently outperforming strong baselines across different backbone LLMs while substantially reducing the overhead of memory construction. Further analysis demonstrates that deferring memory construction to inference enables the memory construction process to dynamically adapt to the information needs of individual queries. All code is available at https://github.com/OpenBMB/T2Mem.
memory - arxiv:2610.13345 · cs.ROEvo-RL: Iterative Robot Reinforcement Learning from Selective ExperienceKai Ye, Yifan Jin, Qianhang Luo, Hongru Zhang +6
Existing real-world reinforcement learning methods improve robot policies by combining human corrections with autonomous rollouts. However, accumulated experience varies in its value for policy improvement, and even successful trajectories can contain inefficient or redundant behavior, motivating more selective experience reuse. To this end, we propose Evo-RL, an iterative reinforcement learning method that combines human interventions with advantage-guided experience selection. Evo-RL uses human corrections and experience with positive estimated advantages from successful trajectories to iteratively refine the policy. To support learning from these different experience sources, we introduce RW-RL-Dataset, which spans over 1,000 hours across four robot embodiments. On a real-world high-precision manipulation task, Evo-RL improves attempt success rate over RECAP by 30.46\%. Our code, model checkpoints, and dataset are publicly available.
manipulation - arxiv:2610.13341 · cs.LGUnderstanding Mamba-3 Through Oscillatory DynamicsShutian Liang, Yue Song
Mamba-3 introduces input-dependent rotations into recurrent state updates, but their contribution beyond state retention remains unclear. We interpret these ro- tations as underdamped second-order dynamics, providing a framework for in- vestigating the role of oscillation in sequence modeling. Controlled comparisons show that underdamped dynamics outperform non-oscillatory damping regimes on state-tracking tasks, while language-model pretraining demonstrates benefits for long-context prediction and length generalization. Interventions in pretrained models further establish the importance of learned phase, and state analysis sug- gests that rotation regulates how retained information combines with incoming up- dates. Taken together, these findings identify underdamped dynamics as a useful mechanism for recurrent computation and suggest that oscillation supports long- context processing by regulating how information accumulates.
long-context - arxiv:2610.13335 · cs.LGAgentTune: A Unified Training Lifecycle for Tool-Using LLM AgentsR E Zera Marveen Lyngkhoi, Abhivansh Gupta, Vidushee Vats, Ram Mohan Rao Kadiyala +2
Tool-using agents increasingly require a common substrate for building, training, evaluating, distilling, and maintaining agentic systems, yet existing tooling typically addresses these stages in isolation. We present AgentTune, a source-available Python library that provides a unified framework for developing and optimizing tool-using agents. At its core, AgentTune introduces a two-tier EventLog representation that preserves agent trajectories while supporting consistent projections for training, evaluation, and auditing. Building on this substrate, the library provides a shared agent runtime, tool-calling reinforcement learning, agentic distillation, retrieval-augmented generation, decision workflows, evaluation utilities, and a designed path toward self-healing agents. These components are exposed through composable interfaces so that agent strategies, training methods, evaluation procedures, and recovery mechanisms can be combined without requiring separate representations or pipelines. We demonstrate the framework across agentic tasks including legal contract search and domain-specific applications, illustrating its use for trajectory-based optimization, tool-use evaluation, and cross-task agent development. AgentTune is released as a source-available library at https://github.com/Lexsi-Labs/AgentTune
retrieval-augmentedagentllm agentagentictool-use - arxiv:2610.13333 · cs.CVLETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity CollapseBoheng Li, Yueming Xing, Yiming Li, Jie Zhang +1
Image-to-video (I2V) diffusion models can animate a single reference image into high-quality, subject-consistent videos, posing threats of misuse as anyone can turn personal photos into fabricated videos without consent. A promising solution is to proactively add an adversarial perturbation to the image before release, such that videos generated from it would be unfaithful or visually corrupted. However, due to an insufficient understanding of what governs how subsequent frames read the reference image in modern I2V models, existing protections struggle to offer strong protection under common perturbation budgets. In this paper, we approach the problem by exploring this underlying reading mechanism. Through a convex geometric analysis, we theoretically identify the spread of the reference value vectors as a key factor governing this reading process, and empirically find that even a mild contraction of this spread can severely degrade the generated video, making it an efficient lever for protection. Guided by this insight, we propose LETHE, a novel protection method that directly disrupts this reading process. LETHE pairs two complementary objectives, where a value collapse objective drives the reference value vectors toward uniformity, while an attention attraction objective draws subsequent frames toward these collapsed tokens to amplify corruption. We further construct two human-centric I2V protection benchmarks and conduct extensive experiments with multiple modern I2V models, which demonstrate the state-of-the-art protection performance and versatility of LETHE.
benchmark - arxiv:2610.13330 · cs.LGMasked Diffusion Language Agents for Tool-Integrated Chemical ReasoningMengdi Liu, Chenghao Jia, Hong Chang, Shiguang Shan
Designing tool-integrated reasoning agent systems for complex chemical tasks remains a fundamental challenge. Although recent chemical agents have demonstrated promising performance through the integration of external tools, they are still built on the autoregressive paradigm, which is inherently constrained by causal attention and left-to-right generation. As a result, they often struggle with bidirectional molecular understanding, global coordinated tool planning and multi-source evidence integration. To address this challenge, we introduce ChemDiffAgent, the first masked diffusion language agent for tool-integrated chemical reasoning. It reformulates chemical reasoning as iterative denoising over interleaved reasoning and tool-use trajectories, enabling tool-use decisions to be jointly determined under full-trajectory context and thereby better aligning the agent's decision boundary with its knowledge boundary. We further analyze how this paradigm benefits agentic reasoning through harder infilling subproblems during training and flexible arbitrary-order decoding during inference. Then we develop a two-stage post-training framework, comprising agentic supervised fine-tuning and variance-reduced preference optimization, to enhance tool-use and reasoning capabilities. We also construct a comprehensive benchmark covering six chemistry tasks across both single-turn and multi-turn tool-use scenarios. Under matched budgets and evaluation, ChemDiffAgent consistently outperforms autoregressive agents, achieving an overall improvement of approximately 20%. Notably, our 8B model achieves performance comparable to, in some cases surpassing, significantly larger frontier models, such as GPT 5.5 and Claude Opus 4.7. Code is available at https://github.com/bilemond/ChemDiffAgent.
agentagenticagent systemtool-usepost-trainingbenchmark - arxiv:2610.13325 · cs.LGTaking Tokenization off the Host for Agentic LLM ServingMohammad Siavashi, Pascal Schwinte, Ali Banaei, Gerald Q. Maguire +2
Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still be tokenized in full before the cache can even be consulted. Tokenization, a CPU stage long treated as negligible, becomes the largest part of time-to-first-token (TTFT), and a frontend that tokenizes for a whole GPU fleet limits how many GPUs it can feed. We present GraphTok, a GPU tokenizer that runs the entire encoding pipeline, from pre-tokenization through byte-pair encoding (BPE) merging to token-ID assembly, as one replayable CUDA graph. GraphTok reproduces the reference token IDs bit-for-bit on GPT-2, Llama 3, Qwen 2.5, DeepSeek-V3, and Gemma 3, hands short inputs to a CPU engine where the GPU cannot win, and plugs into unmodified vLLM and NVIDIA Dynamo. GraphTok encodes one million GPT-2 tokens in 1.7-3.2 ms including data transfers, and on Llama 3 it is 4.7-6.0x faster than gigatoken, the strongest CPU tokenizer. On TokTier's own single-request benchmark, it is 2.6-3.9x faster than gigatoken and up to 18.1x faster than TokTier. In vLLM with a cached prefix, it lowers mean TTFT by 2.1-2.4x. The largest gain is capacity. Within a 2 s P99 target, one Dynamo frontend with GraphTok sustains 518 requests/s of 121k-token traffic, the busiest-hour load of 56 GPUs, against 296 with gigatoken and 18.5 with the default tokenizer. Across 121k to one million tokens, this is 1.75-2.5x the load gigatoken sustains, with a P99 up to 64x lower where gigatoken's tail breaks.
long contextagenticbenchmark - arxiv:2610.13317 · cs.LGSBNO : Schrödinger Bridge Neural Operator for the Forward and Inverse Problems under Missing InformationJaehyeon Park, Inhyeok Jeong, Noseong Park
Partial differential equation (PDE) surrogate modeling often relies on either dense observations or access to governing equations/physics constraints. In practice, observations can be sparse and partial, and the underlying physics may be partially specified or unavailable. We introduce SBNO, an equation-free paired-data diffusion bridge matching framework that learns conditional operators for both forward and inverse PDE problems under partial observations. SBNO uses diffusion Schrödinger bridge matching to learn a pair of time-dependent drifts from a mask-aware endpoint coupling that preserves empirical input-solution pairing during training and supports both PDE-task directions within a single framework. At inference time, SBNO produces a deterministic point reconstruction by integrating the probability-flow ODE constructed from the learned drift pair, without inference-time observation or PDE guidance-weight tuning. On five PDE benchmarks with 5% observations, SBNO achieves superior or comparable accuracy to baselines while demonstrating lower test-instance error dispersion. Furthermore, SBNO is at least $9.7 \times$ faster and reduces GPU memory by at least $4.3 \times$ compared to guided-diffusion baselines.
memorybenchmark - arxiv:2610.13316 · cs.CVThinkDrag: Semantic Drag-Based Image Editing with Visual ReasoningArmando Fortes, Tianyi Wei, Chindanai Trakantannarong, Shangchen Zhou +1
Drag-based image editing provides an intuitive interface for spatially controlled image manipulation by allowing users to specify handle and target points. Existing methods have made substantial progress through optimization-based, one-step, and feed-forward formulations, but they often interpret drag instructions as geometric displacements. This limits their effectiveness when the desired edit depends on interpreting image content and inferring a plausible semantic transformation from sparse point constraints. We introduce ThinkDrag, a unified multimodal framework for drag-based image editing with visual reasoning. ThinkDrag is trained to associate point constraints with meaningful object- and scene-level transformations, and can optionally produce an explicit reasoning trace that interprets the intended edit before image generation. This reasoning trace improves interpretability, particularly for ambiguous drags. Drag Endpoint Markers, motivated by an analysis of cross-image attention, provide an explicit correspondence signal that grounds each drag in image space. To support this framework, we construct a supervised dataset of semantic drag transformations paired with reasoning traces and introduce DragBench++, a benchmark targeting challenging drag-based editing scenarios with reference edit solutions. Experiments show that ThinkDrag achieves state-of-the-art performance, improving generation quality and plausibility while maintaining competitive point-following precision.
manipulationbenchmark - arxiv:2610.13309 · cs.RONovaSplat: Model-Free 6D Object Pose Estimation via 3D Gaussian Splatting Onboarding and RefinementGeorgios Floros, Evangelos Sartinas, Orestis Vangelis, Maria Pateraki
6D pose estimation of novel objects without CAD models remains an open challenge: model-free methods must build the object representation from scratch during onboarding and have long trailed their model-based counterparts. We present NovaSplat, a model-free pipeline that closes this gap. From a short smartphone video captured at onboarding, we train a 3D Gaussian Splatting (3DGS) model that serves both as a template source for detection and coarse pose estimation and as a differentiable backbone for pose refinement. Our refiner optimizes the object-to-camera pose with combined photometric and geometric losses under a continuous rotation parametrization free of gradient singularities. On a household-object benchmark, NovaSplat surpasses all model-based methods. On a challenging industrial benchmark with textureless and specular surfaces, it outperforms all model-free competitors while substantially narrowing the gap to model-based ones. We further introduce NovaSplat-Lite, an inference variant that is $3.1\times$ faster at negligible accuracy cost. Code will be made available at \href{https://github.com/POSE-Lab/novasplat}{https://github.com/POSE-Lab/novasplat}.
benchmark - arxiv:2610.13307 · cs.LGSustainable Cloud-Fog-Edge Systems for Smart Buildings: Algorithmic Adaptation under Memory Constraints and Dynamic Orchestration StrategiesMamadou Sow, Christophe Cerin
The escalating environmental footprint of the Information and Communication Technol- ogy (ICT) sectorwith global Data Center electric- ity usage potentially reaching 3% by 2030 and the imperative for real-time responsiveness in smart buildings demand a foundational shift towards Edge Computing. This article proposes a holis- tic architectural and algorithmic approach for cre- ating autonomous, resilient, and privacy-preserving learning systems within smart buildings, advancing the core concept of the building itself as the data center. Our contributions, demonstrating originality compared to conventional centralized systems, are structured around three main pillars: 1) Validation of resilient data acquisition chains using the af- fordable Arduino ecosystem (Uno R4 WiFi/BME280) and secure persistence solutions including centralized archiving (Node-RED/MySQL) and secure remote transfer (Python/rsync/SSH). 2). The proposal of a lightweight, KOptim orchestration framework, inter- operable with the FIWARE standard, for the dynamic management of Service Level Agreements (SLA). 3) The adaptation and experimental valida- tion of the Generalized Hebbian Algorithm (GHA) for Principal Component Analysis (PCA) on low- power microcontrollers,We introduce and compare an iterative learning strategy using data buffers, featuring sorting and explicit preservation of extreme samples to maintain diversity. Experimental results on the high-dimensional Tour Perret sensor data confirm that this novel method, despite introducing a necessary temporal complexity of O(W log W ) due to sorting, achieves convergence and final result quality that is visually equivalent to processing the entire dataset in full memory, reliably identifying two distinct operational states.
memory - arxiv:2610.13306 · cs.LGStructure-Aware Numerical Stabilization for Half-Precision Proximal Policy OptimizationLinxuan Wu, Liang Chen
Local online training on resource-constrained platforms requires low computational and training-state overhead. We study the numerical stability and computational efficiency of half-precision proximal policy optimization (PPO) on commodity GPUs. Directly converting PPO training to FP16 is unreliable because numerical errors feed back through policy updates and subsequent data collection, while PPO repeatedly compares a current policy with a fixed behavior policy. We propose PPO-FP16 with three structure-aware modules. Global scalar protection stabilizes statistics shared across a minibatch or parameter update. Policy-change residual protection extracts and preserves small differences between the current and behavior policies. Efficient persistent-update protection stabilizes optimizer state and parameter writeback while reducing state storage. These changes preserve the PPO objective, hyperparameters, and training budget. Across six continuous-control tasks and five seeds, PPO-FP16 achieves the lowest mean return-AUC rank (1.90) among the four methods and ranks first in 17 of 30 environment-seed comparisons. Eight of nine performance configurations yield PPO update speedups ranging from 1.16 to 2.03 times. Relative to Full FP32 Adam, optimizer-state memory is reduced by 71.7 to 74.9 percent, and peak allocated GPU memory is reduced by up to 44.5 percent. The results show that protecting a small set of structurally important quantities can deliver stable, efficient FP16 PPO without retuning.
memory - arxiv:2610.13305 · cs.LGMORAD: Reinforcement Learning with Multi-Objective Rewards for RNA Inverse DesignJixin Tang, Ji Guo, Jun Zhao
We introduce MORAD, an online reinforcement learning framework for backbone-conditioned RNA diffusion models that trains a single shared policy across diverse target backbones. Structure-conditioned RNA inverse design seeks nucleotide sequences compatible with a target three-dimensional backbone, yet existing reinforcement learning approaches either optimize a separate policy for each target backbone or rely on offline preference optimization, leaving online post-training of a reusable backbone-conditioned model largely unexplored. MORAD combines backbone-conditioned group sampling, group-relative reward normalization, and a forward-process diffusion objective. Beyond existing RL rewards that primarily target tertiary structural quality, MORAD jointly optimizes six measurements spanning tertiary geometry, base pairing, ensemble behavior, and sequence composition. To aggregate these heterogeneous objectives despite differences in scale and optimization direction, MORAD maps each measurement to a bounded desirability score and combines them with a weighted geometric mean. Compared with a tertiary-structure-only reward, this multi-objective formulation improves 10 of the 11 evaluation metrics that have a preferred direction. Applied to pretrained RIDE, MORAD improves GDT-TS by 16.0% (from 0.3300 to 0.3827) and pairing MCC by 19.4% (from 0.6110 to 0.7295), while reducing normalized ensemble defect by 27.5% (from 0.3906 to 0.2830). On the test set, MORAD outperforms RiboDiffusion, gRNAde, and RDesign across tertiary structural accuracy, secondary-structure pairing, and thermodynamic quality, establishing a new state of the art in structure-conditioned RNA inverse design.
post-training - arxiv:2610.13301 · cs.CVPAGE: Parts-Aware Guidance for Co-Speech Gesture Portrait Video GenerationYabiao Wang, Jiafu Wu, Yicheng Xu, Teng Hu +6
Co-speech gesture video generation aims to synthesize realistic, audio-driven portrait videos from a single reference image and a speech signal. Despite advances in visual quality, diffusion-based approaches still suffer from degraded local details and imperfect audio-visual alignment. We present PAGE (Parts-Aware GuidancE), a general, backbone-agnostic optimization framework for diffusion-based generation that enhances local spatial fidelity and global audio-visual consistency at both the training-objective and denoising-trajectory levels. During training, we propose Parts-Specific Reweighting (PSR), which adaptively increases supervision in semantically important regions such as lips, eyes, and hands, improving visual fidelity in perceptually critical areas. During inference, we introduce Consistency Classifier Guidance (CCG), an audio-conditioned latent classifier that identifies and corrects audio-visual inconsistencies in the generated video. We further design Differential Guidance (DG), an efficient inference strategy that refines facial and body motion separately while avoiding cross-region interference. To enable large-scale evaluation, we construct the Chinese Announcer Speech (CAS) dataset, the first comprehensive Chinese benchmark for co-speech gesture portrait video generation. Compared with the widely used PATS dataset, CAS includes substantially more identities, video clips, and scene diversity. Extensive experiments on both PATS and CAS demonstrate that PAGE achieves state-of-the-art performance in perceptual quality, gesture diversity, and audio-visual alignment. Project page: https://aigc-explorer.github.io/PAGE/.
benchmark - arxiv:2610.13296 · cs.AIPRIME: Pre-Retrieval Index Modeling Enhancement for Structured Document Retrieval-RealCheuk Hei Chung, Li Liu
High-precision retrieval over external knowledge bases is essential for LLM agents to operate effectively. However, existing Information Retrieval (IR) research primarily optimizes query-side retrievers (e.g., ColBERT, BGE) and generators (e.g., Self-RAG, GraphRAG), while reducing corpus-side representation to chunking. This leaves index-side quality an underexplored lever. We propose Pre-Retrieval Index Modeling & Enhancement (PRIME), an index-side optimization framework built on two complementary tracks: an LLM-driven Semantic Restructuring (SR) track that transforms long documents into structured, information-dense sections, and a deterministic Metadata Synthesis (MS) and Hierarchical Retrieval (HR) track that extracts semantic anchors and heading structure for coarse-to-fine section retrieval. Our evaluations show that deterministic metadata matches structure-aware chunking's retrieval quality while cutting embedding computation by 45.8 $\times$ and index vector count by 22.4 $\times$. On top of these gains, Semantic Restructuring (SR) further improves Answer-F1 by 13.7% in full deployment, with characterized quality-fidelity-cost trade-offs. Across QASPER, BRIGHT, and NFCorpus, we further characterize three qualitative regimes that determine whether index-side optimization helps or degrades retrieval, while showing that these index-side effects are neutralized under a strong reranker.
llm agent - arxiv:2610.13285 · cs.AIBoundaryEvo: Data-Model Co-Evolution at the Capability Boundary for Long-Chain Reasoning DistillationJiaming Su, Suorong Yang, Xudong Li, Tengchao Yang +1
Distilling long-chain reasoning trajectories from large teacher models provides an effective way to improve the reasoning ability of small language models. However, existing methods typically select a fixed training set before distillation, overlooking that the usefulness of a reasoning example changes as the student evolves. This mismatch becomes especially costly when only a small number of teacher trajectories can be used for training. Besides, examples already mastered provide little new supervision, while examples far beyond the capability of student may be difficult to learn from. Training data should therefore adapt as model capability evolves, yet reliable data selection is difficult when the student is initially weak. To address these challenges, our key idea is to first establish the basic reasoning capability and then adapt the training data to the evolving capability boundary of the student. We propose BoundaryEvo, a two-stage data--model co-evolution framework. In Capability Priming, we directly distill a small set of teacher-generated long reasoning trajectories without using a separate model to judge and filter them, allowing the student to acquire an initial reasoning capability before capability-aware data selection. In Capability-Boundary Co-Evolution, we repeatedly select questions that the current student has not mastered but the expert can reliably solve, and update the training data as the student evolves. With only 1,000 training examples, BoundaryEvo consistently outperforms static and dynamic data selection baselines across 11 reasoning benchmarks, raising the original Qwen3.5-4B accuracy from 62.9 to 75.3 on IMO-AnswerBench and from 26.8 to 46.0 on AMO-Bench. The code and data will be made publicly available.
benchmark - arxiv:2610.13281 · cs.CVQCLR: A Plug-in Robustification Module via Quantization for Contrastive Learning in Self-Supervised Skeleton-Based Human Action RecognitionNanzhu Chen, Feixiang He, Yunfeng Diao, Duygu Sarikaya +1
Skeleton-based human action recognition has gained increasing attention due to the stability of skeleton data across diverse environments and advances in motion capture technologies. Following the success of supervised learning approaches, self-supervised learning approaches, particularly contrastive learning ones, have achieved impressive performance. However, they remain vulnerable to adversarial attacks. In this work, we propose a plug-in robustification module via quantization for contrastive learning in self-supervised skeleton-based human action recognition (QCLR), which enhances the robustness of representations against adversarial attacks while preserving their representational capability. Specifically, we employ a dual-level quantization scheme across the encoding pipeline, which breaks the gradient propagation and absorbs small adversarial perturbations within the quantization bins. To mitigate the impact of inevitable quantization error, we further design an attention-guided multi-faceted quantization strategy to maintain the representation quality. Experiments on several benchmark datasets demonstrate that integrating QCLR into a progressive lineage of mainstream contrastive learning models substantially improves robustness against both gradient-based white-box and gradient-free black-box adversarial attacks, while preserving highly competitive classification accuracy.
benchmark - arxiv:2610.13277 · cs.CLBeyond the Final Embedding: Retrieving Memories from Token-Level EvidenceHan Luo, Zhan Zhuang, Xu He, Jujia Zhao +4
Memory-augmented assistants retrieve evidence from stored conversations and documents to answer queries. Most embedding-based retrievers compare single-vector representations of queries and memories, even when relevance depends on a small part of the content. Such local evidence can be matched to queries using the contextual token representations already computed by the same embedding models. Our method uses sparse token matching to improve retrieval without additional training. Each query token retrieves a small set of matching tokens across candidate memories. The matching scores are aggregated for each memory and combined with whole-memory similarity to rank memories. An optional low-rank query adapter can be trained with supervision while keeping the encoder and stored memory representations fixed. Our method improves retrieval across eight benchmarks and multiple model families without additional training. Query adaptation further increases the gains to 13.3 and 14.3 percentage points in average Recall@10 and NDCG@10 on Qwen3-Embedding-4B. These retrieval gains translate into higher question-answering accuracy on long-term memory benchmarks.
memorybenchmark - arxiv:2610.13273 · cs.AIAgent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market AnalysisYongjian Tang, Costel Moraru, Doruk Tuncel, Hanya Elhashemy +2
API specifications serve as critical documentation for modern software development, directly impacting integration efficiency and client code generation. While recent advancements have leveraged Large Language Models (LLMs) to generate initial specifications from source code, existing approaches treat this process as a one-time event - overlooking the needs for continuous validation, long-term maintenance, and market-driven evolution of these artifacts. To address this issue, we present Agent4Spec, an autonomous multi-agent framework featuring two distinct pipelines: (1) a validation pipeline that detects and self-corrects OpenAPI syntax errors, and (2) a market analysis pipeline that conducts competitive research, identifies functional gaps against industry leaders, and automatically generates missing API-spec functionalities. We evaluate Agent4Spec on two curated datasets of API specifications spanning both general-purpose and industrial scenarios. Among 9 SOTA LLMs, the top-performer achieves 100% syntax error detection rates and over 95% implementation success for proposed corrections, while securing over 50% adoption rates for suggested endpoint improvements, representing a practical tool for API development.
multi-agentagenticagent framework - arxiv:2610.13272 · cs.CVOWLET: On-Policy Weighted Learning via Evidence Transfer for Video Large Language Model Post-TrainingQitan Lv, Ke Fan, Hong Wang, Wen Wu +4
Post-training has become a key stage for eliciting reasoning capabilities in Video Large Language Models (Video-LLMs). Existing post-training methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). However, they do not fully exploit visual evidence for effective training. RL supervises the policy with a single trajectory-level reward, which is too coarse-grained for video reasoning: the same response-level advantage is applied to every generated token, disregarding that the tokens of a video response are grounded in the visual stream to very different degrees. OPD provides token-level supervision through output-distribution matching, but lacks direct supervision of the spatiotemporal representations that produce those outputs. We observe across extensive experiments that the same model reasons more accurately when its video view combines global temporal context with question-relevant details. Comparing the same student-generated response under this view and uniform sampling reveals changes in token likelihoods and internal representations, providing a training signal for evidence use. Building on this observation, we propose OWLET, an evidence-privileged RL method that derives training signals from a richer teacher view. This view couples uniform global context with question-conditioned local windows, providing visual evidence without requiring a larger model. To better exploit this privileged visual evidence, OWLET introduces (i) \textbf{evidence-aware credit redistribution}, which compares token likelihoods across the two views and redistributes positive response-level advantages according to their relative evidence support; and (ii) \textbf{spatiotemporal state alignment}, which aligns the two views' hidden states on verifier-accepted responses.
post-training - arxiv:2610.13268 · cs.CVConClick: Element-Wise Contrastive Learning Improves GUI GroundingRuotian Zhang, Yuhui Zhang, Junzhe Huang, Yu Xin +2
GUI grounding, the task of locating the interface element specified by a user instruction, is a fundamental capability of GUI agents. However, existing grounding models remain error-prone, often causing downstream task failures. We systematically evaluate 10 grounding models across five datasets and identify a major error pattern: most incorrect clicks hit non-target interface elements rather than the background, with different models repeatedly selecting the same distractors. Motivated by these findings, we propose ConClick, a contrastive learning framework that teaches models to distinguish the target element from plausible distractors. We construct ConClick-Data, a dataset containing 4,292 challenging target-distractor pairs, and train the model using complementary listwise ranking and pairwise margin objectives. ConClick improves the grounding accuracy of Qwen3-VL-8B from 54.71% to 66.03% on ScreenSpot-Pro, from 83.72% to 86.28% on MMBench-GUI L2, and from 63.33% to 70.20% on OSWorld-G, outperforming prior methods built on the same or similarly sized backbones. We further introduce ReClick, an inference-time strategy that revisits promising regions and compares predictions across competing candidates, yielding an additional 2.96 percentage-point improvement in average accuracy across the three benchmarks. Together, our analysis, dataset, and methods provide both empirical insights and practical tools for building more reliable GUI agents. Data and code are available at https://github.com/zhangruotian/ConClick.
benchmark - arxiv:2610.13267 · cs.AIForgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM AgentsLei Liu, Yunji Liang, Xiaowen Zhang, Jingqi Liu +3
Large language model (LLM) agents are highly vulnerable to memory-poisoning attacks. Existing defenses primarily rely on external modules for either static memory isolation or continuous online auditing, resulting in low memory efficiency and high computational overhead. To address these limitations, inspired by neuroscientific mechanisms that weak reactivation can destabilize memories and induce decay in the absence of reinforcement, we propose an agent-intrinsic training-free memory repair framework, DREAM (Dynamic Reactivation for Engram Attenuation in Memory), that enables selective functional forgetting of poisoned memories. Specifically, DREAM implements a three-stage pipeline: perturbation-induced implicit reactivation to reveal the structural fragility of malicious memories, adaptive anomaly diagnosis based on multi-dimensional activation patterns to detect topological anomalies, and a dynamic memory repair module that selectively suppresses harmful memories while reinforcing benign ones. Extensive experiments across diverse attackers and real-world tasks demonstrate that DREAM reduces attack success rates by over 95\% against backdoor poisoning while preserving strong benign utility. DREAM also achieves competitive robustness against injection attacks. In terms of runtime and token consumption, DREAM achieves up to a 2.13$\times$ speedup and a 37.7\% reduction in token consumption compared with A-MemGuard. Furthermore, DREAM also achieves a task success rate of 92.96\% on poisoned multi-agent systems.
memoryllm agentmulti-agentagent system - arxiv:2610.13264 · cs.LGCV-OPD: Contrastive Vision On-policy DistillationHaowei Wang, Hao Lin, Qi Zhu, Jiayi Ji +3
On-policy distillation (OPD) reveals versatility and convenience during VLM post-training, providing dense supervision for student from teacher. However, we observed an anomaly that the distilled VLM could still answer the questions accurately even when the related visual regions were masked or replaced with noise. Building on this observation, our quantitative and qualitative experiments demonstrate that OPD, which uses the answer as a hint, has failed to teach students to genuinely seek out and rely on visual evidence. Our theoretical analysis suggests that this failure arises from a shortcut enabled by the lack of visual constraints during distillation. To address the issue, we introduce Contrastive Vision On-policy Distillation (CV-OPD), which compares teacher distributions induced by positive and negative crops while conditioning on the same student prefix and augments optimization with a margin-based contrastive constraint, which is modulated with discrepancy gating across token and sample level. Specifically, CV-OPD first introduces a negative teacher unrelated to the answer and designs a Contrastive Divergence Loss (CDL) that constrains the feature distribution of student by contrasting the positive and negative teachers, correcting how the student exploits visual regions. The CV-OPD introduces a Discrepancy Aware Gate (DAG) that uses token-level and sample-level discrepancies to select visually relevant tokens for optimization, directing the student's attention toward visual content. Extensive experiments across a broad range of fine-grained visual benchmarks demonstrate that CV-OPD substantially alleviates shortcut and consistently improves the visual reasoning capabilities of existing VLMs.
post-trainingbenchmark - arxiv:2610.13263 · cs.CVSheafPrune: Sheaf-Guided Graph Propagation for Visual Token PruningXiaoyang Ma, Chi Wang, Hong Sun
Multimodal large language models process the complete visual token sequence, increasing prefill cost even when many tokens are irrelevant to the instruction. Token-wise saliency captures limited inter-token dependence; graph-based selection instead depends on how relations govern importance propagation and ranking. We study support-constrained propagation with node-degree correction. Inspired by sheaf geometry, SheafPrune uses modality-specific maps and a sparse text--visual graph to transfer relevance, then propagates scores on a separate visual graph and corrects them for degree. It retains a hard top-$k$ subset once before the frozen language model. The selector has about $4.5$M parameters and is trained end-to-end through the frozen LLaVA-NeXT-8B backbone using only the language-modeling objective. Explicit retention-ratio conditioning lets one checkpoint serve every budget. Across four backbones, ten benchmarks and seven pruning ratios, with all baselines re-implemented under one protocol, SheafPrune achieves the best retention at $22$ of $28$ backbone--budget settings, with monotonically growing margins in the moderate-to-aggressive regime. On LLaVA-NeXT, retaining $10\%$ of visual tokens yields a $5.15\times$ net prefill speedup and an $84.0\%$ end-to-end FLOPs reduction. Together with component ablations, these results support graph-constrained importance propagation and degree correction as a design for visual token selection across the evaluated backbones and tokenization schemes, improving the trade-off between accuracy retention and inference cost. code:https://github.com/Bob0817912/SheafPrune_ICLR_2027
benchmark - arxiv:2610.13262 · cs.RODual-Stream Memory for Vision-Language-Action PoliciesYang Wang, Ping Liu, Ruiyu Wang, Xuhua Chen +2
Memory-dependent manipulation requires a policy to track execution state and recover visual evidence that is no longer observable. We propose dual-stream memory for vision-language-action policies, assigning these requirements to complementary representations. A task-agnostic Gated DeltaNet compresses history into one temporal token, supervised by progress prediction and action-conditioned feature reconstruction. A task-conditioned retriever retains frames above a fixed relevance threshold; linear multi-scale fusion encodes each frame into sixteen spatial tokens. We then freeze the temporal compressor and jointly optimize retrieval and policy learning. Across sixteen RoboMME tasks, the complete model achieves 49.22% mean success versus 44.51% for the published FrameSamp+Modul reference, improving fourteen tasks and all four suite means. On four real-robot tasks, mean success reaches 62.5% versus 37.5%, with the largest gains on repeated actions requiring execution-stage discrimination. These results support combining execution context with selective visual access, while failures under cup swaps expose persistent identity tracking as an unresolved requirement.
vision-language-actionmanipulationaction-conditionedmemory - arxiv:2610.13261 · cs.LGData-Adaptive Mahalanobis Metric Learning for Cross-Head Attention in TransformersZhenke Duan, Xin Li, Jiqun Pan, Dong Xiaofei +2
In this paper, we propose Data-Adaptive Mahalanobis Cross-Head Attention (DAMCHA), a simple and effective attention mechanism that generalizes Multi-Head Attention (MHA) through the lens of metric learning. Standard MHA implicitly learns a static, head-wise Euclidean similarity corresponding to the diagonal blocks of a unified cross-head metric matrix, discarding all off-diagonal interactions across heads. DAMCHA addresses this limitation via two key innovations. First, it learns the full cross-head metric matrix, inducing a Mahalanobis-like similarity that explicitly captures inter-head interactions beyond the restricted block-diagonal structure of MHA. Second, it parameterizes the metric matrix as an input-dependent function, enabling the attention geometry to dynamically adapt to the intrinsic manifold structure of the data rather than remaining fixed after training. We further introduce principled regularization strategies, most notably stack-wise parameter sharing, to ensure computational efficiency and stable optimization. DAMCHA serves as a drop-in replacement for MHA and its variants in various Transformer architectures, delivering superior expressive power and learning performance with comparable or reduced computational overhead. Extensive experiments demonstrate that DAMCHA-based Transformers consistently outperform competing baselines across a range of benchmark tasks. Code is available at https://github.com/erwinmsmith/DAMCHA.
benchmark - arxiv:2610.13259 · cs.CVBeyond a Single Crop: Contextualized Embeddings for Player Re-IdentificationGe Luo, Changhuo Yang, Weisi Fan, Rui Yang +1
Person re-identification is typically addressed by learning identity-discriminative embeddings from individual person crops. However, player re-identification in broadcast sports videos presents a unique challenge: players from the same team often share similar appearances, while video sequences provide repeated observations of the same players under different viewpoints and surrounding contexts. Existing crop-based approaches largely ignore this contextual information, which can be critical for resolving visually similar identities. Here, we propose ContextReID, a contextualized embedding framework that represents a player by jointly considering other players in the same frame and observations from different frames of the broadcast sequence. By incorporating both co-occurring players and cross-frame observations, the model learns identity features relative to the surrounding visual context rather than relying only on isolated appearance cues. We implement this framework with a vision-language model that takes sets of player crops as input and generates context-aware embeddings for individual players. A combined contextual learning and retrieval objective encourages the model to capture cross-frame identity relationships while maintaining discriminative embeddings for player matching. Experiments across three multi-object tracking benchmarks show that ContextReID improves player retrieval over conventional single-crop embedding approaches in both Rank-1 and mAP. These results highlight the utility of spatial and temporal context for reliable player identification in broadcast sports videos.
benchmark - arxiv:2610.13257 · cs.LGCAST: Credit Alignment for Cross-Tokenizer On-Policy DistillationJingru Yang, Jinhang Wu, Minjing Shi, Shengfeng He +3
Cross-tokenizer on-policy distillation (OPD) requires aligning teacher and student sequences before their scores can be compared. Decoded-text alignment provides such correspondence at the chunk level, but leaves a distinct problem unresolved: credit alignment. A chunk-level signal specifies how much a span should change, but not how that signal should be distributed across student tokens, while tokens without teacher correspondence remain unconstrained. We propose CAST (Chunk-aware credit Assignment with Selective Token Anchoring), a shift-or-stay framework that addresses both issues. For aligned chunks, CAST redistributes each chunk's advantage across student tokens using predictive uncertainty and local teacher-signal smoothness, emphasizing learning opportunities supported by locally consistent teacher feedback while preserving the chunk's total advantage. The resulting weights exactly solve a KL-regularized credit-allocation problem. For unaligned positions, CAST selectively anchors the student to its initial policy through a KL penalty, limiting drift where teacher supervision is unavailable. Because credit assignment is separated from chunk construction, CAST also applies to punctuation-defined or fixed-length chunks under shared tokenization. Across six mathematics, science, and code benchmarks, CAST improves the average over the strongest evaluated baseline by $2.45$ and $1.32$ points for cross-tokenizer transfer from Qwen3-8B to Mistral-7B and Llama-3.1-8B, respectively, and by $2.10$ points for shared-tokenizer transfer to Qwen3-1.7B.
benchmark - arxiv:2610.13253 · cs.LGTabular Foundation Models Are Effectively ShallowIrene Cannistraci, Julia E. Vogt
In-context-learning Tabular Foundation Models (TFMs) are uniquely suited to scenarios with limited resources or privacy constraints, as they solve new tasks without additional training. However, their architecture consists of multiple transformer blocks, resulting in high computational and memory footprints. Meanwhile, traditional alternatives like Gradient-Boosted Decision Trees (GBDTs) remain highly competitive and run efficiently on CPUs, suggesting that tabular tasks may not inherently require deep architectures. This contrast raises a fundamental question: can TFMs be simplified by removing architectural redundancies without sacrificing performance? To answer this, we introduce a closed-form, label-free affine translator that replaces a contiguous window of up to 96% of the blocks, leaving the rest unchanged. Evaluating eight frontier TFMs on 171 classification datasets, we reveal that tabular transformers are vastly overparameterized: replacing half of a model's blocks costs at most $0.002$ median AUROC across all architectures, with the half-depth TabFM still outperforming every other full-depth TFMs and tuned GBDTs. Furthermore, different model families are overparameterized in different ways: TabPFN-3 relies on its encoders, maintaining performance regardless of which single block is retained. Other single-axis models spread computation thinly, needing only their first block, while dual-axis models concentrate it in one critical block. Ultimately, removing depth saves up to 1.5B parameters, speeds up GPU inference by up to $6\times$ at a median cost of $0.03$ AUROC, while a single-block TabPFN-3 serves cached queries $2.4\times$ faster using $6\times$ less memory at negligible cost.
memory - arxiv:2610.13239 · cs.CVJag: Direct Box Prediction for Efficient Visual GroundingXiuyuan Zhu, Ke Lu, Hao Wu, Zijin Du +2
Visual grounding combines image--language understanding with geometric prediction, yet autoregressive multimodal models often express a box as a coordinate sequence. Sequential decoding adds computation to the multimodal processing needed for localization. Adapting these representations to box geometry offers a route to direct prediction. We present Jag, which adapts a compact pretrained multimodal model for direct continuous box prediction. A lightweight regression head reads the last valid input-token state, conditioned on the image and referring expression, and predicts all four box coordinates together. Geometric supervision jointly adapts the language backbone, visual merger, and regression head, allowing localization losses to shape both the multimodal representations and the coordinate mapping. Inference retains image--language processing and returns the box in one forward pass, without coordinate generation or text parsing. Across benchmarks, Jag consistently improves grounding accuracy over its base model across the observed target sizes and expression groups. Component ablation show that jointly adapting the representations and head substantially improves accuracy over training the head alone. Against existing specialized grounding models, it achieves competitive accuracy with lower single-request latency and GPU memory use. These results show how supervision tailored to the geometric answer can specialize a compact pretrained multimodal model for accurate grounding and efficient direct prediction. Project page: https://xyzzzh.github.io/Jag/
memorybenchmark - arxiv:2610.13238 · cs.LGState-OPD: State-Grounded On-Policy Distillation for Multi-Turn AgentsZhentao Zhang, Yanzhao Zheng, Yanlin Liu, Yuanqiang Yu +8
On-Policy Distillation (OPD) has emerged as a powerful paradigm for transferring reasoning capabilities from frontier models to smaller models, while extending its success to multi-turn agentic environments remains challenging. We study agentic OPD through interaction states, distinguishing the objective task and executed action-observation record from the internal semantic trajectory of student reasoning. Through this lens, we identify two roles of student reasoning in multi-turn OPD: prior reasoning distorts teacher supervision, while current reasoning shapes the action alternatives sampled at the same state. Specifically, at matched interaction states, removing prior student reasoning improves teacher continuation success and changes the teacher's token-level targets, with larger continuation gains at later turns. Meanwhile, resampling complete reasoning-action responses yields greater action diversity at the same state than resampling actions under a fixed reasoning trace. We introduce State-Grounded On-Policy Distillation, a framework that grounds teacher supervision in interaction states and reallocates the sampling budget to generate multiple complete reasoning-action responses at states with high response entropy, while retaining full-history student generation. Comprehensive evaluations across ALFWorld, ScienceWorld and WebShop demonstrate that State-OPD achieves the highest macro-average success rate among the evaluated methods for both Qwen3-1.7B and Qwen3-4B students. Notably, for Qwen3-4B, State-OPD raises macro-average success from 26.07\% with the strongest baseline to 31.74\% and surpasses its Qwen3-32B teacher on ALFWorld Seen. Further analyses reveal that State-OPD achieves higher task success with fewer supervised turn responses and substantially reduces persistent failed-action repetition; qualitative traces illustrate decision revision based on interaction feedback.
agentic - arxiv:2610.13232 · cs.CVFPD-Drive: Future Policy Distillation for End-to-End Autonomous DrivingLi-Heng Chen, Qifeng Chen, Chengwei Wu, Yingjie Zhang +3
End-to-end autonomous driving models are typically trained on real-world driving logs, which record only the trajectory actually executed in each scene. This provides limited supervision for learning alternative valid behaviors. Multi-target supervision can mitigate this limitation, but broader trajectory coverage makes safe candidate selection more challenging. We propose FPD-Drive, an end-to-end planner that distills privileged future knowledge into a visual driving policy to improve both multi-trajectory supervision and safety selection. Specifically, we introduce Future-Privileged Multi-Target Distillation to transfer diverse, high-quality trajectory targets from a teacher with access to recorded future observations to the student. These targets extend supervision beyond the single recorded human trajectory. For candidate selection, we further introduce Safety-Aware Score Correction to correct ranking errors between nearby safe and unsafe candidates and raise underestimated safety scores of safe candidates. At deployment, the student requires neither future observations nor teacher inference. Our base model achieves 94.9 PDMS on NAVSIM v1 navtest and 55.9 EPDMS on NAVSIM v2 navhard. The scaled FPD-Drive-Pro improves these scores to 95.5 PDMS and 58.1 EPDMS, respectively, achieving SOTA performance among the compared methods on both benchmarks. Zero-shot closed-loop evaluation on HUGSIM further yields an HD-Score of 45.1 and RC of 55.3.
benchmark - arxiv:2610.13224 · cs.CVAutomated Detection and Encoding of Cartographic Signs in Historical MapsRemi Petitpierre
Symbols and icons in archival maps represent an expansive source of evidence for historical geography. In this paper, we present a two-stage framework for (1) detecting cartographic signs in historical maps and (2) generating interpretable sign embeddings that capture both semantics and stylistic variations. We also introduce CaSiDD, an open benchmark dataset spanning multiple sign categories and diverse cartographic styles, designed for generic sign detection. Using YOLOv10-X, we demonstrate the practicality of automated sign detection on historical maps. We then present strategies for creating contrasted, informative embeddings of cartographic signs. We approach embedding design systematically, maximizing expressiveness while suppressing digitization or background material confounders. Our final method, based on an adapted RADIOv4 backbone, effectively encodes both sign form and semantics, while producing interpretable representations. This work lays a foundation for scalable evidence extraction for the comparative study of map signs within cartographic culture and geohistorical research.
benchmark - arxiv:2610.13221 · cs.LGTensor-based Fusion of Multi-modal Data for Predicting Cancer Risk LevelsAli Anaissi, Yuanzhe Jia, Qishun Peng, Weidong Huang +2
Cancer diagnosis and treatment increasingly rely on multi-modal diagnostic technologies that generate high-dimensional datasets. Although these datasets are rich in pathological information, they pose considerable challenges in interpretation, dimensionality reduction, and clinical applicability. Conventional machine learning approaches often fail to extract meaningful cross-modal features, thereby limiting predictive accuracy in patient risk stratification. To address these limitations, this paper proposes an unsupervised machine learning framework that integrates feature extraction, tensor decomposition, and clustering to improve cancer risk prediction. The framework employs tensor decomposition to fuse heterogeneous genomic and clinical data, enabling the extraction of latent, biologically meaningful features that outperform unimodal feature sets. Multiple feature extraction strategies are investigated, and the resulting features are subsequently clustered using a range of clustering algorithms. Comparative evaluations based on internal and external metrics are then used to identify the most effective configurations. The framework is validated on LinkedOmics data comprising 11,158 patients across 32 cancer types. For patient risk stratification, clinically relevant attributes such as tumor purity, pathological stage, and survival outcomes serve as ground-truth indicators. Experimental results demonstrate the superiority of tSVD+GMM, which consistently outperforms other configurations across clinical benchmarks.
benchmark - arxiv:2610.13217 · cs.LGGolden Anchor for Video GenerationJinyuan Xu, Shitong Shao, Lichen Bai, Zikai Zhou +3
Video generation supports digital content creation, with applications in virtual avatars, AI-driven filmmaking, interactive game engines, and world models. State-of-the-art systems achieve controllability primarily through image-to-video (I2V) generation, in which an injected anchor image determines the identity, composition, and style of the resulting video. In modern pipelines, this anchor is synthesized by a text-to-image (T2I) generator. This raises a largely overlooked question: Are images obtained directly from the T2I model truly suitable for current video models? Our analysis shows that anchor aesthetic and quality scores are weakly correlated with downstream video quality. The structure-and-texture score is negatively correlated with I2V video quality in both the visual and motion dimensions. Fine-tuning the T2I model on an image reward accordingly yields anchors with visibly denser structural and character detail: they score higher on image metrics, yet lower the video reward on every I2V model we test and change downstream motion unpredictably. We therefore introduce Golden Anchor Learning (GAL), to our knowledge the first framework for learning golden anchors by optimizing a T2I generator with downstream video feedback. GAL evaluates candidate anchors through the videos they induce under a frozen I2V model and converts video rewards into image-level preferences for DPO fine-tuning of the T2I generator. On all four I2V models, GAL raises the VBench average by $2.97\%$--$8.46\%$ over the untuned generator. The rendered clips also score higher under VideoReward-Overall, and their extracted frames under HPSv3 and UniPercept. GAL yields consistent motion gains across all four I2V models, as measured by a $5.62\%$--$38.24\%$ increase in VBench dynamic degree. Although GAL is trained only on HunyuanVideo-1.5 renders, these gains extend to the other three I2V models.
world model - arxiv:2610.13215 · cs.LGMonarch-MoE: Structured Experts for Multimodal Continual Instruction TuningXi Zhang, Boyu Diao, Zesen Chen, Ruiqi Liu +2
Learning new tasks in multimodal continual instruction tuning can cause catastrophic forgetting of previously acquired knowledge. Although multi-expert LoRA distributes learning across experts, updates to a dense low-rank expert can still affect many output features. We introduce Monarch-MoE, which replaces the dense factors in LoRA experts with block-diagonal factors connected by a fixed permutation. This structure provides blockwise gradient isolation: individual block-pair updates affect only one output block, while connections between all input and output blocks are maintained. To make these compact experts practical on memory-limited hardware, we combine batched computation, fused forward operators, and an optimized backward pass. Across three continual-learning methods evaluated on MLLM-DCL and UCIT with LLaVA-1.5-7B, Monarch-MoE improves first-task retention while reducing adapter parameters by approximately 75% and 50%, respectively. In the main comparison, first-task forgetting is as low as 0.52 percentage points on MLLM-DCL and 0.10 on UCIT, with method-dependent trade-offs in final performance. Our implementation supports fine-tuning and inference on a single 24 GB RTX 4090, with lower measured memory use and competitive runtime in the evaluated settings. Together, these algorithmic and systems improvements make structured experts a practical option for continual adaptation on memory-limited hardware.
memory - arxiv:2610.13212 · cs.ROBeyond Actions: Learning Future Operation Targets for Vision-Language-Action ModelsMin Lin, Bokai Zhou, Jianqi Lin, Kaiyuan Yang +7
Actions specify what a robot should execute, but do not describe what those commands will achieve. Vision-language-action (VLA) policies nevertheless learn primarily by predicting action chunks from images, language, and state. We introduce Action--Future Coupled Effect Learning (AFCE), which makes a future-grounded physical Effect the policy's primary prediction target. An offline tokenizer constructs temporally ordered Effect tokens from demonstrated actions, realized robot responses, and sparse visual transitions. Reconstruction objectives encourage the representation to retain executable detail and observed physical change. A flow-matching VLA predicts Effects from current images, instruction, and robot state, while a state-conditioned decoder converts them into action chunks. Embodiment-specific interfaces allow single- and dual-arm tasks to share the Effect model. On DexJoCo, AFCE achieves $50.97\%$ overall success, improving over $π_{0.5}$ and UVT by 11.82 and 15.21 percentage points, respectively. It leads on all five bimanual tasks, highlighting the value of Effect supervision for coordinated dexterous manipulation. The project page is available at https://afceproject.github.io/AFCE-Web/.
vision-language-actionvlamanipulationdexterous - arxiv:2610.13211 · cs.LGVerifiable Sampling for Delegated Generative Quantum Machine LearningMatteo Inajetovic, Anna Pappa, Petros Wallden
Generative machine learning has shown remarkable results across a wide range of interdisciplinary tasks, motivating significant efforts toward Quantum Generative Models as a path to beyond-classical performance, given their capability of generating classically intractable distributions. However, comparatively little attention has been paid to securely delegating such computations to a powerful remote quantum server. In this work, we propose a blind and verifiable protocol for sampling that can be used for the inference phase of such quantum models. Such a protocol inherits blindness from Universal Blind Quantum Computing and achieves verifiability by exploiting known approaches based on trapification schemes. Alongside, to delegate the training phase, we discuss an extension of the previously proposed verifiable end-to-end Delegated Variational Quantum Algorithms (Inajetovic et al., Phys. Rev. Research, 2026). Beyond the usual Accept/Abort outcome characterizing verification protocols, the sampling protocol for inference also provides, even against a malicious server, an estimation of the amount of corrupted generated samples, i.e., a fine-grained feature describing the quality of the outcome connecting verification protocols and application-level benchmarking.
benchmark - arxiv:2610.13207 · cs.CLSharP: Soft and Hard Prompt-Guided Augmentation with LLM for Low Resource Fake News DetectionZiyu Luo, Wei Li, Haoping Huang, Kecheng Liu +1
Fake news detection under low resource conditions is challenged by the scarcity of labeled data and the difficulty of capturing subtle deceptive patterns. In this work, we focus on low resource fake news detection, where only a small labeled set is available for training, while evaluation is performed under a fixed and unchanged test protocol. This setting is motivated by costly, ambiguous fact-checking and emerging topics and domains that are poorly covered by existing benchmarks. Existing data augmentation methods, such as synonym substitution, generative adversarial networks, and large language model (LLM)-based generation, often produce fluent but overly generic content, lacking the task-specific relevance needed for accurate detection. To address this, we propose SharP, a boundary-aware text generation framework guided by soft and hard prompts, which leverages LLMs as tools adapted to produce task-specific synthetic samples. SharP employs a dual prompt mechanism: hard prompts provide structured guidance and factual constraints, while soft prompts introduce learned semantic patterns from the data. These two types of prompts are combined to guide the generation process, enabling the model to produce samples that closely align with the characteristics of news. To further enhance detection performance, we incorporate a boundary-aware strategy that steers generation toward areas where the classifier is less confident, helping to clarify subtle distinctions between real and fake content. In addition, we adopt a dual objective optimization that balances semantic alignment with the source data and classifier feedback. This encourages the generation of samples that are both domain-consistent and helpful for refining decision boundaries, ultimately improving model robustness and generalization in low resource fake news detection.
benchmark - arxiv:2610.13202 · cs.LGS$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative DecodingYuhang He, Hongyu Ge, Zihan Lin, Siyi Liu +1
Fast rollout generation for long-context reinforcement learning with verifiable rewards (RLVR) requires reducing KV-cache traffic without changing the response groups used for policy optimization. In our profiled RLVR workloads, attention accounts for 72--76\% of autoregressive decoding kernel time. Sparse attention reduces these reads, but sampling directly from a sparse policy changes the response groups used for learning. For group-relative optimization, we show that even exact response-wise reweighting does not generally recover the expected dense-policy update because the advantage of each response depends on the rewards of other group members. We propose Self-Sparse Speculative Rollouts (S$^3$R). It uses sparse attention to propose tokens, then generates responses through full-attention verification and exact speculative sampling. Drafting and verification share the same policy parameter, eliminating the need to train or update a separate drafter. The resulting response groups follow the dense-policy distribution. Under S$^3$R, we characterize speedup conditions and the costs of drafting and verification. We found that dense verification still requires the complete historical KV cache. A KV-aware scheduler therefore limits KV-cache repeated offloading and restoration while maintaining rollout parallelism. % OR thrashing In a matched ablation with an aggressive sparse drafting budget, S$^3$R maintains stable training while direct sparse sampling with training-side correction becomes unstable. On long-context mathematical reasoning, S$^3$R achieves $1.39\times~1.35\times$ the end-to-end training throughput of autoregressive rollouts on Qwen3 model, with comparable task performance.
long-context - arxiv:2610.13197 · cs.LGDoes Learning Recurrent Networks Matter in Partially Observable RL?Zekang Wang, Zhe He, Gaojie Jin
Reinforcement learning (RL) under partial observability typically re- lies on recurrent networks to encode temporal information, with the recurrent module trained jointly with the policy or value function. This raises a natural question: is learning the recurrent network actually necessary? In this paper, we investigate whether a frozen recurrent network can provide sufficient memory for solving par- tially observable Markov decision processes (POMDPs). Motivated by the theoretical foundations of Reservoir Computing (RC) and Generalized Reservoir Computing (GRC), we study a simple archi- tecture that combines a fixed recurrent network with a trainable nonlinear output module. We evaluate this approach across tasks with varying memory demands, observation modalities, and action spaces. Surprisingly, frozen recurrent networks support recall over hundreds of steps and achieve competitive control performance across diverse POMDPs, while using less than half the number of trainable parameters required by their fully trainable counterparts. These results suggest that learning the recurrent memory module is not always necessary for solving POMDPs. Frozen recurrent networks therefore provide a simple, parameter-efficient, and sur- prisingly strong baseline for partially observable RL. Our source code is available at https://github.com/Aphlios/FRN-POMDP
memorymemory module - arxiv:2610.13195 · cs.ROPATACON: GPU-Parallel Tangent-Bundle RRT-Connect for Constrained Motion PlanningGahyun Oh, Junho An, Suhyun Jeon, Suhan Park
Fast whole-body motion planning enables continuous replanning for humanoid robots in dynamic environments while satisfying collision avoidance and kinematic constraints. However, constrained motion planning incurs substantial computational cost due to repeated constraint projection in addition to collision checking and nearest-neighbor search. Recently, GPU-based massively parallel planners have been proposed to reduce computational cost. Nevertheless, these planners still steer in the ambient configuration space, so projecting candidates that deviate from the manifold remains a significant source of overhead, particularly in highly constrained, high-dimensional problems. In this work, we introduce PATACON, a GPU-parallel bidirectional planner that explores tangent space to exploit the local manifold geometry induced by known constraint functions. Experiments on dual-arm closed-chain and humanoid whole-body constrained planning tasks show that PATACON outperforms the prior work as configuration-space dimension and constraint codimension grow, achieving up to an 11.25 times speedup. These results suggest that GPU-parallel tangent-space exploration brings constrained whole-body motion planning closer to real-time performance.
humanoid - arxiv:2610.13194 · cs.AIJANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World ModelsMengdi Liu, Chenghao Jia, Hong Chang, Mingjie He +2
Long-horizon autonomous research has shown promise in accelerating scientific progress through sustained cycles of hypothesis generation, implementation, and validation. However, this Generate-Execute-Feedback paradigm relies on reactive trial-and-error, where costly and time-consuming executions introduce severe feedback delays, throttling evolutionary progress under explosively expanding search space. To address this challenge, we propose JANUS, a framework that unifies future outcomes forecasting and past experience reflection through a Predict-Verify-Evolve loop driven by a co-evolving world model. Within an evolving graph, the research agent proposes candidates while world model scores them by forecasting value improvement, information gain, and exploration utility, then accordingly selects, refines, or prunes branches prior to execution. After receiving ground-truth feedback, JANUS distills experience into evolving skills: hierarchical skills for research agent, exploration-strategy skills for world model, and their coordination protocols. This mechanism enables continual co-evolution: the research agent sharpens candidate generation while the world model refines its predictive judgment over extended horizons. Extensive evaluations on MLS-Bench-Lite and real research tasks demonstrate that JANUS significantly outperforms state-of-the-art baselines, achieving both higher evolving efficiency and ceiling.
world modelagent - arxiv:2610.13187 · cs.CVDestination-Conditioned Adaptation with Semantic-Geometric Alignment for Generative InbetweeningZhiyu Xu, Wei Shang, Yushen Xu, Wenwen Li +3
Generative inbetweening aims to synthesize temporally coherent intermediate frames between a start frame and a target frame. Although pretrained image-to-video diffusion models provide strong priors for large-motion inbetweening, they are not explicitly designed to reach a specified target frame. They may therefore generate realistic individual frames while drifting from the target or producing unstable motion under large displacements and non-rigid dynamics. We propose DSG-GI, a framework that adapts pretrained latent video diffusion models through \textbf{D}estination-Conditioned Adaptation and \textbf{S}emantic-\textbf{G}eometric Alignment. Destination-Conditioned Adaptation treats the target frame as the destination of the sequence and provides temporally progressive guidance along the generated trajectory. Semantic-Geometric Alignment aligns the token-wise spatio-temporal relational geometry of backbone features with that of a frozen video foundation encoder and applies a flow-matching-aware latent flow constraint to samples near the data endpoint of the probability path. Together, these components strengthen destination guidance and preserve coherent semantic-geometric motion structure. Extensive experiments on standard and large-motion inbetweening benchmarks demonstrate improvements in temporal stability, target-frame faithfulness, and perceptual quality. Our code will be made publicly available.
benchmark - arxiv:2610.13184 · cs.AIAdaC-GRPO: Towards Mastering Long-Horizon Visual Sudoku Puzzles via Adaptive Curriculum LearningSida Li, Yuanxin Liu, Linli Yao, Shicheng Li +3
While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks remains underexplored. Visual Sudoku puzzles pose a representative challenge, requiring multi-step deductive reasoning over both local constraints and global dependency chains. To this end, we introduce FG-Sudoku, a fine-grained benchmark categorized by grid size and required deductive steps. Evaluations reveal that frontier MLLMs fail on complex long-range dependencies (e.g., 9*9 puzzles). During post-training, this near-zero success rate causes severe reward sparsity, halting standard RLVR. We propose Adaptive Curriculum Group Relative Policy Optimization (AdaC-GRPO) to overcome this. Unlike rigid or prior-based schedules, AdaC-GRPO dynamically constructs training batches by tracking the model's "Zone of Proximal Development" via online rollout accuracy. Experiments demonstrate that AdaC-GRPO enables Qwen2.5-VL-7B to approach the performance of Gemini-2.5-Flash while bridging 62.2% of the overall accuracy gap to Gemini-2.5-Pro, with its generalizability further validated across InternVL-3.5 and Qwen3-VL.
post-trainingcurriculum learningbenchmark - arxiv:2610.13179 · cs.CVHigh-Throughput Generative Video Super-Resolution on a Single Consumer GPUGeorgios Panaretou, Sotirios Chatzis
Generative video super-resolution (VSR) can recover visually compelling high-frequency detail by leveraging diffusion priors, but iterative sampling and heavy spatio-temporal coupling make practical deployments difficult. We study a different operating point: practical HD generative VSR on a single high-end consumer GPU without end-to-end retraining. To this end, we present a zero-shot framework built entirely from pretrained components. The proposed system decouples spatial enhancement from temporal stabilization. A time-distilled one-step diffusion backbone handles spatial upscaling, while temporal coherence is promoted by a lightweight pretrained flow-based interpolator that synthesizes intermediate frames between super-resolved keyframes. To further improve scalability, we introduce a resolution-aware hybrid attention scheme that, in a zero-shot manner, replaces selected high-resolution global-attention layers with neighborhood attention while preserving global attention in semantically critical low-resolution layers, while also improving temporal consistency. Experiments show that the proposed framework reaches up to ~32 FPS at 720p resolution under interleaved inference on a single NVIDIA RTX 4090. At 4K, the proposed attention substitution can yield up to a 44% speedup over the original attention implementation. Across standard VSR benchmarks, the method consistently shifts the speed-quality trade-off decisively toward runtime efficiency, trading reconstruction fidelity for strong no-reference perceptual quality, while remaining reasonably competitive against generative approaches in temporal consistency. It also exposes clear limitations in handling more challenging motion, which a simple motion gate partially mitigates. Code will be released upon acceptance.
benchmark - arxiv:2610.13177 · cs.CVCompactSplat: Spatially Adaptive Gaussian Distribution for Feedforward Scene ReconstructionBing He, Jingnan Gao, Yunuo Chen, Zhengxue Cheng +3
Reconstructing 3D scenes from sparse views without per-scene optimization remains highly challenging, especially for recovering accurate geometry and fine textures. While recent feedforward approaches leverage generalizable 3D Gaussian Splatting (3DGS) for scene generation, they typically assign one or multiple Gaussians to each pixel. Such uniform allocation not only produces highly redundant representations by wasting primitives in homogeneous areas, but also fails to exploit the inherent geometric priors of planar surfaces, often resulting in sub-optimal structural modeling. To address these limitations, we present CompactSplat, a novel feedforward framework that enables a content-aware allocation of 3D Gaussians. By integrating texture-guided spatial partitioning with hierarchical sampling, CompactSplat adaptively distributes primitives - concentrating dense Gaussians in complex regions while tiling flat areas with expanded, scale-modulated primitives. Moreover, our framework inherently supports dynamic sparsity control at inference time, enabling seamless trade-offs between rendering fidelity and memory footprint without requiring network retraining. Extensive experiments on RealEstate10K, DL3DV, and ScanNet demonstrate that CompactSplat consistently outperforms prior methods on both standard metrics and high-resolution rendering consistency, achieving high-fidelity reconstructions with significantly fewer primitives.
memory - arxiv:2610.13176 · cs.CVFix the Match, Not the Solver: STITCH -- a Self-Supervised Compatibility Measure for Eroded Visual PuzzlesNadav Alali, Ohad Ben-Shahar
Unlike the clean and pixel-aligned complete pieces of standard jigsaw benchmarks, real-world puzzle fragments lose their boundary regions to erosion, destroying the signal that classical compatibility measures (CMs) rely on. We first re-establish, via oracle experiments, that the CM, not the solver, is the performance bottleneck: with a perfect CM, even a simple greedy solver achieves perfect reconstruction. This motivates STITCH, a self-supervised CM that sidesteps missing boundaries by comparing frozen ViT patch tokens from piece interiors via a lightweight cross-attention head (~249K trainable parameters), trained without manual annotation. Plugged into unchanged compatibility-based solvers, STITCH reaches .992/.954 Abs/Perf on JPwLEG-5 (+.629 Perf over the best prior method), nearly saturating the benchmark. On a new ImageNet 7x7 benchmark, it outperforms all alternatives, including inpaint-then-match pipelines built on modern generative models. Importantly, performance remains robust across erosion levels and generalizes to puzzles with over 40% missing pieces without retraining. Trained on the recent GAP datasets of irregular, heavily eroded fragments, the same CM recipe enables compatibility-based solvers to surpass recent learning-based solvers on GAP-3 and GAP-5. Since this leap in performance is achieved by a pluggable CM module, the takeaway is clear: fix the match, not the solver.
benchmark - arxiv:2610.13172 · cs.AIRoleWorld: Knowledge Transfer in World Modeling with Functional Role AbstractionsBoyuan Xiao, Pu Wang, Ji Feng, Yao-Xiang Ding
World models enable large language model (LLM) agents to anticipate action effects and make informed decisions. For generalization, it is desirable for such world models to transfer efficiently to new environments with similar interaction structure and underlying dynamics. Recent approaches encode world dynamics as symbolic rules or executable programs, whose compositional structure in principle affords transfer, but still organize such knowledge around environment-specific objects. To address this limitation, we introduce RoleWorld, a symbolic world modeling approach which uses reusable prototypes and environment-specific parameter values as functional role abstractions to represent how objects behave in interactions. From interaction trajectories, a teacher LLM extracts role prototypes and executable transition rules defined over role instances, together with a skill that guides the actor LLM to use role information in decision making. In a target world, without the teacher, the actor uses this skill together with its current role assignments and parameter estimates, and actively tests a role instance hypothesis through interaction when its uncertainty affects the current decision. Feedback from each action refines role assignments and estimates parameter values online, with no LLM parameter updates and the transition rules held fixed. Experiments on MARS benchmark show that RoleWorld enables robust generalization across environments with significantly altered object behavior, suggesting that functional role abstractions can serve as an effective component for knowledge transfer in world modeling. Project Page: https://future-item.github.io/RoleWorld.
world modelbenchmark - arxiv:2610.13166 · cs.CLScaling Agentic Data for Long-Horizon Terminal IntelligenceShun Zou, Ziyu Ma, Yi Zou, Yong Wang +5
Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool calls, but they do not fully show how agents accumulate evidence through exploration, use it to inform judgments, continually adjust strategies based on feedback, and turn intermediate results into final deliverables. High-quality long-horizon trajectories capture these agentic behavioral patterns and their connections within a single problem-solving process, providing richer experience for sustained autonomous work. However, environment synthesis may complete or simplify the key work underlying these patterns in advance and thus remove the need for exploration, implementation, and verification that the agent was meant to perform. To address this, we introduce TerminalHorizon, a fully automated data synthesis engine for long-horizon terminal agents. Starting from real-world professional work, it uses independent execution to identify key work omitted during construction and uses the resulting evidence to guide environment reconstruction. To extend these patterns across stages, it progressively expands tasks under the same goal, introducing new requirements that build on prior results and call for further exploration and improvement. Using this engine, we construct 1.5K task environments and perform supervised fine-tuning of Qwen3.5-27B on the resulting dataset to obtain TerminalHorizon-27B. We achieve substantial performance gains on all 12 benchmarks spanning coding-agent tasks, agentic tasks in real-world production settings, and general reasoning. Multiple RSI case studies, each with a 12-hour research budget, further demonstrate the model's ability to continue experimenting beyond an initial solution, improve its methods based on feedback, and retain effective improvements in its final deliverables.
agentagenticbenchmark - arxiv:2610.13164 · cs.ROGrounded-Dreamer: Robot Learning from World Model Synthetic Data with Physical GroundingFeng Jiang, Shu Chen, Yuanfei Wang, Yuan Li +6
Scaling robot manipulation policies requires large amounts of diverse, action-labeled data, yet collecting such data in the real world remains expensive and difficult to scale. Existing methods either depend on human teleoperation, rely on simulation with limited visual realism, or use human videos that lack embodiment-specific annotations. In this paper, we introduce Grounded-Dreamer, a framework for synthesizing physically grounded robot manipulation data with video world models while avoiding human teleoperation demonstrations. Grounded-Dreamer combines the visual realism of generative video models with simulator physics engines. Starting from a small set of real images depicting robot task initial states, our method automatically reconstructs task-relevant objects and camera geometry, aligns them in simulation, and collects physically valid trajectories. These trajectories are used to post-train both a video world model and an inverse dynamics model, enabling the generation of visually realistic robot manipulation videos and corresponding robot actions from real images. To filter physically implausible rollouts, Grounded-Dreamer replays generated trajectories in the reconstructed simulation and retains only those that successfully complete the tasks. The real-world robot policies are trained solely on the grounded synthetic trajectories without any human demonstrations. Empirical results in real-world tasks demonstrate that Grounded-Dreamer can synthesize physically grounded data and substantially facilitate policy learning without requiring human teleoperation effort.
manipulationteleoperationworld model - arxiv:2610.13158 · cs.ROLow-Latency Mapless ESDF Queries for MAV Reactive Collision AvoidanceLeonard Freißmuth, Cedric Le Gentil, Helen Oleynikova, Stefan Leutenegger
Reactive collision avoidance in unknown, cluttered environments must perceive obstacles and correct motion within milliseconds. Existing methods rely on maps for high-rate collision queries, but their acceleration structures require pre- processing. That cost is amortized in long-horizon planning, where a map serves millions of queries; reactive planning, however, is a near-field, short-horizon problem with potentially only hundreds of queries per measurement, where building a map may not pay off. We propose a mapless, Graphics Processing Unit (GPU)-accelerated Euclidean Signed Distance Field (ESDF) query with negligible pre-processing that operates directly on posed depth images, with resolution set by pooling the image rather than by a voxel size. On an embedded GPU it is simultaneously more accurate and lower in total latency than every voxel-grid configuration we measured between 2 cm and 20 cm, at one to two orders of magnitude less memory at matched resolution. With our query integrated into a Model Predictive Controller (MPC), simulated runs in laser-scanned forests at up to 9 m/s collide in 0.4 % through dense branches, against 5.9 % with the best voxel grid and 5.5 % with the best mapless baseline at our resolution, whose failures we attribute to voxel resolution and total latency respectively. We deploy the system onboard at two forest sites and fly at commanded speeds of up to 4 m/s.
memory - arxiv:2610.13157 · cs.CLSOAR: Source-Aware Reinforcement Learning with Precise Credit Assignment for Search AgentsShengze Huang, Zihao Tang, Jinluan Yang, Xin Yu +10
Reinforcement learning (RL) for search agents often suffers from evidence fabrication, a failure mode where agents bypass external information ($E_{ext}$) and fabricate an incorrect answer. We argue that this fabrication arises from an over-reliance on unreliable internal knowledge ($E_{int}$) as shortcuts due to the inherent opacity of reasoning trajectories. To address this, we propose SOAR (SOurce-Aware Reinforcement learning), a paradigm that transforms monolithic reasoning into source-explicit trajectories. SOAR (i) disentangles $E_{ext}$ and $E_{int}$ into parallel, observable streams via a Source-Aware Workflow, and (ii) incorporates Source-Consistent Reward to guide the policy evolution. By making information-source attribution explicit, SOAR enables precise credit assignment between different knowledge streams. Evaluations show that SOAR outperforms baselines on 3B and 7B backbones by 7.3% and 5.4%, while reducing evidence fabrication by 74.8%. These confirm that SOAR significantly improves performance on knowledge-intensive benchmarks while effectively mitigating evidence fabrication, fostering more faithful and grounded reasoning with enhanced robustness.
benchmark - arxiv:2610.13154 · cs.CVFrom Glance to Focus: Mitigating Recognition Laziness in MLLMs for Fine-Grained RecognitionYutong Yang, Zhuqi Liu, Mouxing Yang, Xi Peng
Multimodal Large Language Models (MLLMs) generally fall short of expectations in Fine-Grained Visual Recognition (FGVR), although they exhibit promising FGVR foundations, i.e., visual perception and broad category knowledge. Most existing studies seek to remedy this deficiency by adopting domain-specific post-training, at the risk of compromising generalization to unseen domains. Different from these efforts, in this paper, we revisit the FGVR mechanism underlying MLLMs from both the empirical and theoretical perspectives and uncover an inference-time phenomenon termed FGVR Laziness. In brief, FGVR Laziness refers to the insufficient association between visual cues and category concepts under certain candidate category lists and recognition guidance, leaving the FGVR foundations of MLLMs largely under-utilized. To mitigate FGVR Laziness, we propose Laziness-resIstant Visual rEcognition (LIVE), a training-free framework which jointly refines candidate lists and recognition guidance to elicit the latent FGVR capability of MLLMs. Specifically, LIVE first performs query-adaptive candidate inference to derive a compact yet reliable candidate list. Meanwhile, LIVE constructs category-specific FGVR skills by mining the intra-category characteristics and inter-category differences. Finally, LIVE selectively invokes detailed skill guidance according to recognition uncertainty and category confusion, shifting MLLM-based FGVR from a cursory glance to a focus on associating discriminative visual cues with category concepts. Extensive experiments on 13 benchmarks against 24 state-of-the-art methods spanning fine-grained category recognition, action recognition, and general category recognition, verify the effectiveness and generalizability of LIVE across different MLLM backbones. The code will be released upon acceptance.
post-trainingbenchmark - arxiv:2610.13152 · cs.AIQuality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-TuningSida Li, Yuanxin Liu, Shicheng Li, Linli Yao +3
Open coding agents are commonly trained through supervised fine-tuning on interaction trajectories whose final patches pass the benchmark test suite. However, this outcome-level filtering criterion ignores process quality: trajectories that eventually succeed may still contain inefficient interaction patterns such as repetitive file inspection, unstable tool usage, or delayed modification behavior, all of which become part of the imitation target. We propose TQS (Trajectory Quality Score), a structural scoring framework for coding-agent trajectories that operates directly on trajectory structure, requires no LLM judge, and runs in linear time. TQS characterizes trajectory quality through structural signals organized around structured convergence: information focus, intent--action alignment, and policy dynamics. Using 155,144 successful trajectories from a public open-license corpus, we rank trajectories by TQS and fine-tune coding agents on filtered subsets. Models trained on top-ranked trajectories consistently outperform those trained on random or bottom-ranked subsets on SWE-Bench-Verified. Our results suggest that process-level trajectory quality is an important factor in coding-agent supervision and that structural trajectory filtering provides an effective and scalable alternative to LLM-based data selection.
benchmark - arxiv:2610.13148 · cs.CLLes Misérables Dialogue: A film-based network representation of social communicationTheodora Moldovan, Georgios Panayiotou, Davide Vega
In this work, we revisit the classic Les Misérables benchmark network from the perspective of social communication. Using the 1998 film adaptation of the novel, we construct the publicly available Les Misérables Dialogue temporal text network, which explicitly distinguishes speakers, addressees, and other recipients of each utterance, along with its content and timing. Using the ten social dimensions model, we also derive multilayer network representations of the network, in which layers correspond to distinct relational dimensions. Beyond the network dataset, this work offers a general methodology for building similarly rich communication datasets from similar narrative sources.
benchmark - arxiv:2610.13146 · eess.SYExtended Neighborhood Message Passing for Inference in Loopy Factor GraphsKuilong Yang, Zengfu Wang, Hua Lan
Belief propagation (BP) is widely used for inference on probabilistic graphical models but often suffers from non-convergence and poor accuracy on loopy factor graphs, yielding inexact variance estimates in the Gaussian case. Generalized BP (GBP) improves accuracy but relies on manual design or application-specific heuristics for region-graph construction. We propose extended neighborhood message passing (ENMP), which automatically constructs extended neighborhoods of variable nodes from the bipartite factor graph topology, capturing loop-induced correlations without manual region design. The framework applies to general distributions on factor graphs with a tunable accuracy-complexity trade-off. In the exact regime, message updates converge to the unique fixed point of the ENMP equations in finitely many iterations, yielding exact marginals; in the approximate regime, ENMP provides approximate marginals. For Gaussian factor graphs, we derive closed-form update rules enabling exact variance estimation in the exact regime, addressing the long-standing inaccurate variance estimates of loopy Gaussian BP. We evaluate ENMP on densely loopy Gaussian factor graphs from power-grid benchmarks and on a discrete Ising factor graph. Results show accuracy improves with neighborhood size, with exact marginals achieved on several systems in both settings. On larger Gaussian systems, ENMP outperforms regularized Gaussian BP (sGaBP-m) in both mean and variance estimation accuracy.
benchmark - arxiv:2610.13144 · cs.AICompetence-Aware Orchestration for LLM-Based Multi-Agent SystemsSongmiao Wang, Yuchen Wang, Chenglin Yu, Hongxia Yang +1
LLM-based multi-agent systems (MAS) have emerged as a promising paradigm for enhancing complex reasoning through role specialization and collaboration, yet a key challenge remains: how can collaboration be adapted to a backbone's competence on the current query? This problem matters because more collaboration is not always better--richer coordination may help on difficult cases, but it also incurs additional token cost and redundant interactions. We propose a two-stage competence-aware framework for automatic MAS orchestration. It first models the LLM backbone's task-conditioned competence for the current query, and then uses this signal to adapt role activation and the communication graph. Across six benchmarks, our method achieves an average score of 93.81%. Experiments with six LLM backbones of varying competence levels further show that our method adjusts collaboration according to the inferred competence: for higher-competence backbones, it improves average accuracy from 87.22 to 89.97 while reducing token cost by 36.26%; for lower-competence backbones, it yields a further average gain of 4.58 points over existing methods. The same trend also holds on unseen backbones.
multi-agentagent systembenchmark - arxiv:2610.13134 · cs.LGNeurograf v1: An End-to-End Romanian-First Language Model FamilyIonut Adrian Rotaru
We present Neurograf v1, an experimental end-to-end Romanian-first language-model pipeline developed to investigate the feasibility of training language models from scratch for a lower-resource European language. The pipeline comprises RoSfera, a 635 GB Romanian corpus containing 175.7 million documents; an 80k byte-level BPE tokenizer; five decoder-only models ranging from 160M to 6B parameters, trained on 131 billion tokens; three instruction-tuned assistants; and two contrastively trained embedding models. Training and evaluation were conducted using computing infrastructure at ELI-NP/IFIN-HH. The model family exhibits consistent scaling of validation loss and increasing Romanian factual and cultural knowledge with model size. On the 1,000-question WWTBM benchmark, Neurograf-6B achieves 69.89% accuracy on Romanian-context questions, while Neurograf-3.2B reaches 67.38%. Compute-optimal analysis yields a parameter-scaling exponent of approximately 0.423. Neurograf v1 serves as an experimental demonstrator rather than a production system. The study identifies practical challenges involving diacritic preservation, corpus quality, data composition, and tokenization efficiency, while demonstrating the feasibility of developing Romanian-first base models, instruction-following assistants, and semantic embedding models within a unified training pipeline.
benchmark - arxiv:2610.13133 · cs.MAThe Limits of Manipulation within Personalized Incentive PoliciesAndrea Araldo, Alessa Mayer, Ravi Seshadri, Amir Brudner
Demand management policies aim to shift individual behavior toward sustainable choices (e.g., goods, transport modes). Personalized incentive policies tailor subsidies to agents' needs and constraints, but personalization also exposes the regulator to agents' strategic manipulative behavior. The extent to which agents can profitably manipulate such policies remains poorly understood, which limits their applicability. This paper establishes analytically the conditions under which manipulation benefits the agent. We formalize a Stackelberg game in which an agent may simulate a different profile to extract higher incentives from a regulator. Previous work typically assumes that the regulator would instantaneously classify agents into the simulated user profile. In contrast, we explicitly model the regulator's process of learning the agent profile, based on observed past behavior. This makes manipulation harder, since it forces the agent to consistently behave according to a simulated profile, thus renouncing following their true preferences. Manipulative agents thus incur a Cost of Manipulation, which has typically been neglected. By accounting for it, we get a counterintuitive finding: although classification uncertainty reduces personalization accuracy, it may benefit the regulator by deterring manipulation. We establish an upper bound on the agent's gain from manipulation, which becomes stricter as profiles become harder to distinguish for the regulator. Simulations on the London Passenger Mode Choice dataset illustrate this deterrence effect. The framework can therefore be used to stress-test the robustness of personalized incentive policies before deployment.
manipulationagent - arxiv:2610.13132 · cs.AIDP-MIND: Differentially private memory-guided Long context InferenceZhihao Liu, Yitian Cheng, Shuang Liu, Rui Wen +2
LLM-as-a-Service has become a dominant paradigm for accessing large language models without requiring local deployment. However, the process raises severe privacy concerns when user queries may include sensitive or confidential contexts. Differential privacy (DP) provides a principled approach to protecting such inputs, but existing DP inference methods are primarily designed for short- or moderate-context settings and struggle with million-token-scale inputs due to limited context capacity and severe utility degradation under DP perturbation. In this paper, we propose DP-MIND, a memory-guided framework that scales differentially private inference to million-token contexts. DP-MIND enables private long-context inference by locally perturbing the input and processing it chunk by chunk with a compact memory that preserves task-relevant information across the sequence. To make this memory robust to DP noise, we optimize the memory construction policy directly on perturbed inputs using reinforcement learning, guided by both final answer correctness and memory consistency. We further recover perturbation-corrupted answer spans through a local denoising module without exposing the original context to the external model. We provide theoretical privacy analysis of DP-MIND and further conduct extensive empirical analysis across multiple long-context benchmarks with context lengths up to the million-token scale, demonstrating that DP-MIND consistently outperforms existing DP and long-context inference baselines in both scalability and utility.
memorylong-contextlong contextbenchmark - arxiv:2610.13128 · cs.AILocate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QAWenlin Lin, Fanzhe Wei
Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-augmented agents give one model both kinds of tools and let it schedule itself. We present KnowForge, a pipeline separated by job: a hybrid-retrieval knowledge-point index; a Locator agent that can only search; a code-scheduled bridge judge that forces the missing second hop; a typed, size-bounded evidence pool that merges every search's ranking; a Deep Reader agent that can only read text, images and tables; and a synthesizer with a format checker. With a self-hosted Qwen3.6-35B-A3B (3B active), KnowForge reaches F1 47.5 on the full open-domain M3DocVQA (2,441 questions, 3,368 PDFs), +11.0 over the published M3DocRAG system and +7.1 over one-shot retrieve-and-answer on the same index and model, and 53.5 with DeepSeek-V4-Flash. On MultiHop-RAG it reaches 73.5 accuracy, above the strongest published RAG and GraphRAG results (71.2); on the single-document MMLongBench-Doc it lifts the same model from 34.8 to 47.0, level with GPT-4o reading page images (46.3). Per-job ablations on the full benchmarks attribute the gain: the Deep Reader is worth 3.8, 9.8 and 0 points on the three corpora, tracking how visual each is; merging both agents into one with all tools and twice the rounds loses 1.9 F1 because it keeps searching instead of reading; a round-budget sweep shows a step at four Locator rounds and a plateau beyond; query latency scales with model calls rather than corpus size. We serve the three indexed benchmarks as read-only knowledge bases (free registration) and release all prompts and the runner code: https://github.com/metask-ai/knowforge-bench
retrieval-augmentedragagentbenchmark - arxiv:2610.13122 · cs.CVGuidedNav: Shaping Vision-Language Navigation Representations through Pre-action Attention and Spatial GuidanceJingyu Guo, Jiaxin Huang, Chengxing Lin, Xiaoyu Luo +5
Vision-and-language navigation (VLN) requires an agent to track progress through an extended instruction, identify landmarks relevant to its current objective, and understand the surrounding spatial structure to act. End-to-end navigation policies typically rely on action supervision to implicitly learn these capabilities. Without explicit guidance on the evidence underlying each decision, however, policies can overfit to correlations predictive of training actions rather than learn the task-relevant grounding and geometry needed for generalization. Our insight is to guide the representations that connect instructions to actions: identifying what remains to be done determines which visual evidence matters, while understanding the geometry around that evidence informs how to move. We introduce GuidedNav, a unified framework that explicitly shapes these representations through training-time guidance. Subtask and landmark guidance steer native pre-action attention toward the active instruction segment and relevant visual regions, grounding action prediction in the current objective. Spatial guidance aligns the policy's internal representations with geometric features that capture long-horizon context and local spatial structure. Together, these objectives strengthen navigation capabilities while avoiding the inference overhead of intermediate textual reasoning and online geometric encoding. We also introduce Guided-R2R and Guided-RxR, two annotation-enriched navigation datasets that support more interpretable VLN research. GuidedNav establishes state-of-the-art performance among the compared monocular RGB policies, improving success rates by 8.1% and 13.1% relative to the strongest prior results on R2R-CE and RxR-CE val-unseen, respectively, while achieving faster inference. Extensive experiments further demonstrate the effectiveness and real-world transferability of our approach.
agent - arxiv:2610.13120 · cs.CVReplaying the Movie in Your Mind Decoding Dynamic Visual Perception and Recall from EEGZikai Fang, Tian-Yi Zhou, Xuan-Hao Liu, Yixi Li +4
Decoding dynamic visual content from EEG has advanced rapidly for visual perception, yet it remains unclear which aspects of neural representations are preserved when people internally replay dynamic scenes. We introduce PAIR, an EEG benchmark collected from 20 participants using an interleaved, clip-wise paradigm that pairs naturalistic video viewing with immediate visual recall. This design enables a comparison between externally driven perception and internally generated recall for the same stimulus content within a fixed trial sequence. We benchmark multiple decoding models on hierarchical semantic classification at both fine-grained and coarse-grained levels, meta-feature decoding tasks covering motion, color, object number, face, and human presence, and a state-decoding task that discriminates perception from recall. Within-subject validation results show numerically similar performance for several model--task combinations, alongside higher perception accuracy in two coarse-grained comparisons after multiple-comparison correction. In contrast, perception and recall are highly separable at the state level under the present validation protocol. State accuracy remains high after alpha-band ablation, although this does not exclude ocular or other task-related contributions.
benchmark - arxiv:2610.13119 · cs.ROHuman2Dex: Dexterous Robot Learning from Wrist-Centric Human DemonstrationsJiachen Zhang, Yuanyuan Li, Shaqi Luo
Collecting dexterous manipulation demonstrations for each robot hand requires repeated task-specific data acquisition. We ask whether one shared corpus of natural human demonstrations can instead serve as a reusable data interface for different dexterous hands, without collecting task demonstrations on each target robot. We present Human2Dex, a wrist-centric human demonstration interface that separates shared human observation and motion semantics from embodiment-specific execution. It aligns observations through local hand-appearance adaptation and a shared 21-point hand representation with consistent structural semantics across human and robot observations. It constructs executable supervision by retargeting fused human hand motion to each target hand, and introduces the Grasp-Pocket Interaction Representation (GPIR) to express tracked objects relative to a hand-centered Functional Grasp Pocket. The corpus is converted into separate training sets for Linker O6 and Wuji, while action labels, normalization, training, and diffusion-policy checkpoints remain hand-specific. Across six real-world tasks, Human2Dex achieves 109/120 (90.8%) successes on Linker O6 and 97/120 (80.8%) on Wuji. Across both hands, Human-Raw achieves 63/240 (26.3%) successes, whereas the complete Human2Dex configuration achieves 206/240 (85.8%). These results support the use of wrist-centric human demonstrations as a reusable interface across calibrated dexterous hands while retaining embodiment-specific policy learning. The project website is publicly available at https://human2dex.pages.dev/.
manipulationdexterousgrasp - arxiv:2610.13118 · cs.ROThe value of information and the emergence of communication in evolved e-puck robotsFernando Montes-Gonzalez
We study when communication emerges between autonomous agents and what role an innate action selection architecture plays. Two e-puck robots, reconstructed in PyBullet from their Webots model and validated against it, must find a feeding zone that can only be detected when a robot passes over it. Each robot can emit a one-bit signal whose direction is detected by the receiver. Control is provided by a GRU recurrent network with a residual path, either operating alone or as a channel within an Embedded Action Selection Architecture (EASA). Fitness measures only the time the robots spend over the food. When the robots receive a compass pointing to the food, use of the signal disappears completely. Without a compass, in a small arena, three independent runs achieved similar performance using different strategies: a referential signal, a permanent beacon, or no use of the signal. As the arena expands, the strategy based on a referential signal generalizes best. In contrast, evolving directly in the large arena does not increase the frequency of communication, but it does separate the strategies, and the referential signal clearly outperforms solitary searching. Within EASA, innate reflexes constrain the network and reduce performance. As its priorities evolve, evolution consistently weakens those reflexes. The results suggest that communication emerges in proportion to the value of the information it transmits, and that an innate scaffolding designed for isolated agents can be an impediment in a social task.
autonomous agentarena - arxiv:2610.13117 · cs.ROForward Dynamics ModelsZipei Ma, Junzhe Jiang, Jiahui Zhang, Juntong Zhang +5
Vision-language-action (VLA) models and world action models (WAMs) have advanced robotic policy learning by building on pretrained vision-language models (VLMs) and video generative models (VGMs), respectively. Yet VLAs learn without explicit supervision from future world states, while WAMs that condition actions on predicted futures incur extra inference cost and let visual prediction errors propagate into actions. We present Forward Dynamics Models (FDM), a family of robotic action models that couples action and future world-state prediction through an action-to-future paradigm. Future prediction is conditioned on action features, never the reverse: end-to-end training lets ground-truth future states supervise the policy through these features, while prediction errors cannot propagate into actions. At inference, FDM skips future generation entirely, avoiding its computational cost. The paradigm is backbone-agnostic, and we instantiate it with both VLM and VGM backbones. Experiments in simulation and on real robots demonstrate the effectiveness of FDM across both backbone families, achieving a state-of-the-art 99.4% average success rate on LIBERO and absolute gains of up to 13% over VLA and WAM methods on real-world tasks.
vision-language-actionvlalibero - arxiv:2610.13116 · cs.AIDRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation DesignYuzhen Wang, Chunxiao Li, Baichen Le, Lewen Yan +5
As large language models (LLMs) acquire advanced biological design capabilities, they offer substantial research benefits but simultaneously introduce severe dual-use risks, such as engineering enhanced pathogens or drug-resistant bacteria. While biosecurity frameworks recognize these threats, the actual risk of LLMs executing dangerous biological modifications remains unquantified, particularly when augmented with specialized biological design tools (BDTs). Existing evaluations primarily assess hazardous knowledge possession rather than practical application, overlook risk amplification from BDTs, and rely on unreliable, expensive, or hazardous validation methods. To address these gaps, we introduce DRYLAB-Bench (Design Risk Yielded by LLM Agent in Biodesign), the first comprehensive benchmark evaluating the high-risk biological mutation design capabilities of LLM agents. Moving beyond basic question-answering, DRYLAB-Bench tasks agents with 30 genuinely hazardous mutation-design scenarios distilled from biosecurity guidelines. It evaluates models in a multi-round, tool-augmented environment where LLMs orchestrate BDTs to iteratively refine candidates. Crucially, it scores designs directly against 187,695 empirical wet-lab measurements from ProteinGym and ViroGym using our proposed Biosecurity Risk Score (BRS), quantifying risk-associated effects while enabling scalable and safe ground-truth verification. Evaluations of 15 frontier models reveal substantial baseline threats: without tools, 67.6% of one-shot designs exceed the average measured variant, and 21.4% reach the highest-risk decile. Equipping models with BDTs significantly amplifies this risk, raising the pooled risk by \(ΔBRS=+0.116\) and the top-decile share to 23.5%. Code: https://github.com/drylab-bio/DRYLAB-Bench
agentllm agentagenticbenchmark - arxiv:2610.13113 · cs.LGContinually Post-training Small Models via Synthetic Self-distillationWoosung Koh, Hyunsoo Lee, Kyungjae Lee, Haeju Park +3
Continual post-training faces a dual challenge of acquisition and retention: models must learn new capabilities while preserving prior knowledge. While Self-Distillation Fine-Tuning (SDFT) mitigates this using self-supervision with in-context demonstrations, it relies on strong in-context learning and instruction-following abilities. Consequently, SDFT fails on smaller models critical for low-latency, on-device use. To enable continual learning at smaller scales, we first identify the root cause of failure. We show that poor acquisition and forgetting correlate linearly with the post-trained model's distribution shift, revealing the necessity of in-distribution learning. We thus introduce Synthetic Self-Distillation (SynthSelf), imitating SDFT's in-distribution rewrite by outsourcing the task to a minimally larger, same-family aligner. Coupled with off-policy supervision and rejection sampling, this provides the high-quality supervision small models require without breaking their original distribution. Evaluations spanning 4 acquisition datasets (including a mixture) and 14 retention benchmarks show SynthSelf consistently outperforms 6 methods (including off- and on-policy distillation) across 3 small model scales. Extensive further analyses confirm SynthSelf paves the way toward effective small-model continual learning.
post-trainingbenchmark - arxiv:2610.13106 · cs.LGScaling RNA Foundation Models through Iterative RefinementPengan Chen, Liang Hong, Xinyuan Liu, Han Huang +5
Biological function in RNA is encoded across scales, from local sequence motifs to long-range structural dependencies. Conventional RNA foundation models couple parameter capacity and inference depth within a fixed architecture, prescribing a fixed computation graph for each inference. Here we present Eco-RNA, an 80M-parameter RNA foundation model that makes inference depth adjustable through learned iterative refinement. Its shared, input-conditioned Transformer core refines sequence representations through repeated application. The iteration count is selected after training and controls effective depth at fixed model parameters. We train across recurrent depths with masked reconstruction, state regularization, and a one-sided loss that anchors deeper reconstruction to a shallow reference. On the 70-assay RNAGym fitness benchmark, increasing refinement from one to four iterations raises aggregate absolute Spearman correlation from 0.242 to 0.286, with the gain retained through eight iterations. At four iterations, Eco-RNA surpasses the current SOTA Evo 2 40B on all three aggregate fitness metrics despite 500x fewer parameters. Its iteration configurations advance the compute-performance Pareto frontier among the evaluated models. It also outperforms the evaluated baselines in non-coding RNA family classification, RNA secondary-structure prediction, and chemical probing profile prediction. These results establish internal inference computation as an effective scaling dimension for RNA foundation models.
iterative refinementbenchmark - arxiv:2610.13105 · cs.LGCan Failed Trajectories Reveal Where Agents Go Wrong? Agentic Failure Attribution Without Step-Level LabelsDo Nguyen-Thanh, Junlin Fang, Bing Li, Zhen Fang +1
Failure attribution for LLM agents aims to identify decisive steps responsible for task failure, which is critical for debugging and improving agentic systems. Existing methods rely on costly LLM prompting, step-level error annotations, or verified successful trajectories that lack failure signals for assistance. In this paper, we study failure attribution from step-unlabeled failure trajectories, where each trajectory is known to have failed but its decisive step is unknown. We propose SOAP (Spectral scOring with Attention-guided Propagation), an effective framework requiring neither step-level training labels nor a separate success-only reference set. SOAP first constructs a spectral reference space from LLM representations and assigns each step a base error score according to its projection behavior. Importantly, later steps may exhibit stronger failure signals because they inherit an earlier mistake, causing independent scorers to favor downstream consequences over the decisive error. To address this downstream contamination, SOAP derives soft step dependencies from attention patterns and propagates downstream error evidence toward its likely upstream sources. Extensive experiments show that SOAP consistently improves attribution performance over competitive baselines.
llm agentagentic - arxiv:2610.13104 · cs.CVRobust Vision-Language Navigation with Awareness of Instruction-Execution ProgressJiagan Huang, Zikun Zhou, Hongpeng Wang, Guangming Lu +2
In Vision-Language Navigation (VLN) tasks involving multi-step instructions as guidance, an agent must associate its observations with the relevant instruction content at each decision point. Most graph-based methods commonly match candidate trajectories with the entire instruction, allowing already executed content to interfere with subsequent decisions. Although instruction-execution progress provides a direct cue for separating executed and pending content, existing progress estimation approaches often rely on explicit progress supervision, sophisticated progress-learning stages, or costly online reasoning with LLMs. In this paper, we propose a robust VLN framework with Awareness of Instruction-Execution Progress (VLN-AIEP), which couples progress estimation with navigation decision-making. VLN-AIEP associates the visited trajectory with the instruction to suppress embeddings corresponding to executed content, and then matches candidate locations with the pending content. This coupling makes correct navigation decisions depend on accurate progress estimation, allowing the progress estimator to learn directly from navigation decision labels without explicit progress annotations. To support progress estimation, we construct a landmark-anchored trajectory representation that encodes the semantic labels and viewpoint-relative geometry of instruction-referred landmarks. These landmarks serve as spatial references for associating the visited trajectory with executed instruction content. Extensive experiments on R2R, RxR, CVDN, and R2R-CE demonstrate that the proposed method achieves favorable performance across multiple metrics.
agent - arxiv:2610.13098 · cs.AIVETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics ReasoningYingbo Ma, Kuangshi Ai, Gordon Dai, Chenglong Yu +2
Visual agents for symbolic graphics reasoning depend on executable world representations, yet continued improvement remains bottlenecked by ambiguous supervision from final renders. Recent agentic systems refine scenes through repeated interaction, but they lack mechanisms to recursively extract actionable evidence from execution traces, overlooking which proposed symbolic edits survived, disappeared, or interfered during program execution. To address this, we propose VETR (Verified Execution Trajectories for Refinement), a framework that enables agentic recursive self-improvement over executable world representations for symbolic graphics reasoning. Within each task, VETR retains aligned program/render records with bounded runtime observations and introduces an execution refiner that compiles observed writes and state changes into constrained alternative programs. The refiner validates their endpoints and preservation conditions against captured runtime state; the ordinary visual verifier then assesses goal relevance. Repair construction makes no additional language-model calls, but can require additional executions. Evaluations on BlenderGym (280 tasks) and BlenderBench (27 released tasks) with GPT-5.6-luna and Qwen3.8-27B show that VETR consistently outperforms existing refinement strategies, including BlenderAlchemy and VIGA. Controlled ablations evaluate the contributions of execution refinement and role-asymmetric evidence organization under fixed generator-interaction caps.
agentagenticself-improvingself-improvement - arxiv:2610.13093 · cs.ROReAT: Residual Action Tokenization for Autoregressive Robot PoliciesDijia Zhan, Zhuo Li, Xuemiao Xu, Sun Zheng +3
Autoregressive robot policies rely on action tokenizers to convert continuous action chunks into compact sequences of discrete prediction targets. Existing tokenizers can reconstruct action chunks from discrete codes, but often leave implicit what each individual token contributes to the reconstructed action. We introduce Residual Action Tokenization (ReAT), which gives each token an explicit role in refining the current action reconstruction. It uses the decoded reconstruction as feedback to construct the next token from the remaining action error. This closes the loop between encoding and decoding, making each new token responsive to the errors left by the actual decoded prefix. Across 19 manipulation tasks spanning three simulation benchmarks and real-world settings, 8-token ReAT policies outperform the evaluated baselines in task success; on LIBERO, even 4-token ReAT surpasses the evaluated 8-token action-tokenization baselines at half the token budget. These results suggest a path toward action tokenization that supports self-corrective policy learning, helping autoregressive policies learn to progressively refine their own action plans.
manipulationliberobenchmark - arxiv:2610.13092 · cs.AIWhen Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent WorkflowsYuchen Ling, Shengcheng Yu, Zhenyu Chen, Chunrong Fang
AI agents depend on repeated decisions to accomplish tasks, with large language models (LLMs) commonly serving as their core decision makers. The recent emergence of Jev offers an opportunity to make these decisions faster and at lower cost. However, it remains unclear whether such local savings can be translated into efficient and reliable task completion. In this paper, we investigate this efficiency transfer across five agents in two representative application settings, embodied tasks in ALFWorld and mobile app use in AndroidWorld. Across 4,500 task executions, we jointly evaluate task effectiveness, decision-level and task-level resource use, and execution behavior. Experimental results show that Jev integration substantially reduces decision cost and latency across all five agents, with task-level gains varying by workflow. Task success remains close to baseline levels on ALFWorld and declines more substantially in two mobile agents. Auxiliary reasoning and additional interactions absorb decision savings, while failed recovery and premature completion limit successful delivery. Mean cost per successful outcome increases in one agent even as spending per attempt falls. These findings highlight the importance of preserving progress, supporting recovery, and verifying completion when integrating efficient decision models into agent workflows. Their practical value should be assessed through successful task delivery, recovery behavior, and resources per delivered outcome.
embodiedagentai agent - arxiv:2610.13087 · cs.ROBelief-Overlap Partial Inversion: Object-Centric Flow Replanning for Humanoid Loco-ManipulationChen Yu, Sudarshan S Harithas, Juan Borbon, Dingqi Zhang +1
People often learn how an unfamiliar object moves through a small exploratory push, using its response to guide their next motion. Inspired by this behavior, we study humanoids pushing carts whose mass and caster stiffness are initially unknown. Our object-centric framework closes online estimation, flow-based planning, and whole-body control into a loop, creating a tension: replacing the plan whenever the belief shifts disrupts the maneuver under way, while keeping it strands the robot on a path its evidence has ruled out. Belief-Overlap Partial Inversion (BOPI) scales revision to agreement, inverting the flow under the old belief only as far as the beliefs disagree before reconstructing under the new one. Across 18 simulated goals it lowers pooled final position and yaw error by roughly 33% and 47% against fixed-depth replanning, and on hardware it translates and turns a non-holonomic cart.
manipulationhumanoidwhole-body control - arxiv:2610.13079 · cs.ROVICAR: Video Imitation with Contact-Aware Retargeting for Humanoid Interactive SkillsDvij Kalaria, Bike Zhang, S. Shankar Sastry
Third-person human videos offer a scalable alternative to task-specific reward engineering, teleoperation, and manually scripted demonstrations for humanoid loco-manipulation. Recent video-to-humanoid systems have shown that noisy human motion, object trajectories, and contacts can be extracted from unstructured videos and refined into deployable skills. However, a key gap remains for contact-rich imitation: the task is often defined by world-frame contacts whose poses, timing, and speed must survive embodiment mismatch and runtime scene changes. Towards this, we present VICAR (Video Imitation with Contact-Aware Retargeting), a pipeline for learning humanoid interactive skills from third-person human videos. The system first recovers human motion, reconstructs task-relevant obstacles from monocular video, and then retargets the motion to a humanoid while preserving global contact poses, motion speed, and collision clearance. Unlike retargeting methods that only remove penetration or preserve local interaction geometry, our formulation represents user-specified contact poses and collision clearance as high-priority Lagrangian penalty terms and optimizes the full motion to remain smooth through contact-rich transitions. The resulting motions are used to train a contact-conditioned motion generator whose inputs include movable contact points enabling runtime adaptation to new contact positions. We demonstrate the framework on ten diverse third-person video skills, including six table-tennis serves, three object-pickup tasks, and ladder climbing, and deploy the learned skills on hardware. These results suggest that contact-preserving retargeting is a practical step toward humanoids that learn useful interactive behavior by watching humans.
manipulationhumanoidteleoperation - arxiv:2610.13078 · cs.AIAttention Sees, MLP Refuses: Tracing the Attention-to-MLP Safety Pathway in LLMsZixuan Weng, Haoqi He, Weifei Jin, Yue Huang +1
Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires distinguishing harmfulness recognition from the computation that writes refusal. We reframe this as a pathway question and make it measurable on residual-stream updates in decoder-only Transformers, separating the harmfulness information a module update exposes from the change it produces in readable refusal evidence. Across 18 Base-Instruct pairs spanning Qwen, Llama, and Gemma, harmfulness is decoded more readily from attention updates, particularly in early layers, whereas MLP updates contribute more strongly to harm-selective refusal writing in aligned models. Post-training strengthens MLP refusal writing in all 18 pairs without systematically improving harmfulness decodability, while positive MLP writing becomes more concentrated in deeper layers after post-training. Across six reasoning-enabled models, harmfulness remains decodable during reasoning while strong refusal writing concentrates at answer onset, a pattern that persists with reasoning disabled. Causal interventions further support this pathway: resetting downstream MLP updates to their clean values substantially reduces the refusal shift caused by upstream attention interventions. Building on these findings, we introduce Sentinel, which combines an attention-derived perception score P with an MLP-derived decision score D. Their joint profiles characterize jailbreaks and over-refusals, and conditional routing with both signals achieves a lower aggregate error rate than single-signal routing and evaluated fixed reminders across eight models.
post-training - arxiv:2610.13075 · cs.AILongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence ManagementSongtao Huang, Zhijie Zhong, Xiaohan He, Shuaiyu Zhang +7
Corpus-level long-context reasoning requires agents to acquire and integrate evidence across document collections that exceed their context windows. Existing agent harnesses enable incremental access to these corpora, but acquired evidence and evolving conclusions often remain entangled in a growing interaction history. This implicit state management can lead to two coupled failure modes: unbounded exploration, where retrieval expands the interaction history without resolving decision-relevant information gaps, and evidence-state drift, where previously acquired evidence or subsequent corrections fail to inform the current conclusion. We present LongHarness, a model-agnostic harness that makes the interaction between acquired evidence and evolving conclusions explicit. Its core mechanism, Evidence-Conclusion Coevolution, uses unresolved conclusions to guide exploration toward missing information, while newly acquired evidence strengthens or revises the conclusions that directed the search. LongHarness couples this process with Evidence Lifecycle Management, which keeps accumulated evidence current and traceable throughout the interaction. Together, these mechanisms focus retrieval on remaining information needs and keep conclusions aligned with current evidence. We evaluate LongHarness on OfficeQA Pro V1 and V2, AA-LCR, and LongBench v2 using GLM-5.3-Flash and Qwen3.8-Flash. Compared with direct reasoning using the same backbone, LongHarness improves GLM-5.3-Flash exact match on OfficeQA Pro from 15.8% to 60.2% on V1 and from 4.4% to 61.1% on V2. Against state-of-the-art agent harnesses, it surpasses Claude Code by 12.0 percentage points on V1 and Codex by 18.9 points on V2. With Qwen3.8-Flash, LongHarness reaches 61.7% on V1, outperforming Claude Code by 8.3 points and Codex by 12.0 points.
long-contextagentagentic - arxiv:2610.13073 · cs.LGDouble-Take: Improving Capacity, Binding, and Selectivity In Long-Context Within Bidirectional MemoryVakul Raghavan, Utkarsh Grover, Mingyang Mao, Chengwen Wang +1
Processing a long sequence does not guarantee that distant information remains usable. As context grows, a fixed-size memory must retain many associations, connect information across positions, and preserve relevant structure without being overwhelmed by everything it observes. These are distinct requirements: a memory may store more information without representing the relationships needed for retrieval, and it may transport those relationships without preserving the ones that matter. Thus, the challenge is not simply extending context length, but constructing a memory that remains usable as context grows. We study this problem in large-chunk test-time training (TTT) and identify two basic failures: single-step writes accumulate interference, limiting capacity, while self-associative writes cannot form cross-position bindings. We introduce Double-Take (DT), which repairs these failures with multi-step unpinned updates and cross-position mixing, and adds bidirectional change-sensitive writes for selective retention. Capacity alone leaves end-to-end recall at the $0.10$ chance floor; adding binding raises it to $0.92$. Trained only on $32\,\mathrm{kb}$ genomic contexts, DT reaches $0.927$ AUROC at $131\,\mathrm{kb}$ and $0.856$ near $1\,\mathrm{Mb}$, while transferring zero-shot from human to mouse. Together, these results identify capacity, binding, and selectivity as three requirements for usable long-range memory.
memorylong-context - arxiv:2610.13064 · cs.LGCB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual BanditsJiahang Sun, Zhiwei Shang, Zhipiao Liu, Hongwei Yang +3
Large Language Model (LLM) agents have demonstrated remarkable capabilities in tackling complex tasks through agentic workflows. However, manually designing these workflows is labor-intensive and lacks flexibility to adapt to diverse queries. While automated workflow optimization is a promising direction, existing methods often incur expensive API costs during training-phase feedback collection. Furthermore, they fail to adaptively reuse high-quality workflows, which creates a bottleneck for both performance and cost-effectiveness. To address these limitations, we propose CB-Orchestrator, an adaptive framework that decouples workflow generation from selection. In the first stage, we construct a diverse pool of candidate workflows via evolutionary search. In the second stage, we formulate workflow selection as a Contextual Bandit problem, which enables sample-efficient learning by balancing exploration and exploitation, thereby significantly reducing the feedback required for training. During inference, the model adaptively selects the optimal workflow tailored to each query. Evaluations across five diverse benchmarks demonstrate that CB-Orchestrator consistently outperforms all baselines. Notably, on the MATH dataset, CB-Orchestrator achieves better performance than strong recent baselines while reducing training-phase API token overhead by no less than 40.55% and total end-to-end training (including workflow pool generation) token overhead by no less than 29.73%.
llm agentagenticbenchmark - arxiv:2610.13060 · cs.CLKV-Repurpose: A Testbed for Evaluating Non-Prefix KV-Cache ReuseTaiga Ikeda, Daisuke Miyashita, Jun Deguchi
KV-cache reuse in large language model serving is commonly limited to exact prompt prefixes, preventing reuse when the same retrieved document appears after different system prompts, conversation histories, or dynamic metadata. We present KV-Repurpose, an open-source, vLLM-based system for developing and evaluating segment-wise KV-cache reuse beyond exact prefixes. The system combines cache-aware segment scheduling, prompt construction, capacity management, workload generation, and runtime monitoring. Experiments on long-context benchmarks show that naive segment reuse largely preserves output quality for single-document question answering and summarization, while exposing clear limitations in cross-document reasoning. Under a Zipfian RAG-style workload in which 20% of requests share a fixed prefix, KV-Repurpose achieves a substantially higher token-level cache hit rate than prefix caching at the same 30 GB cache capacity, 63.9% versus 3.3%, resulting in lower TTFT. Even with 1 TB of cache capacity, prefix caching reaches only a 17.9% hit rate in this workload. Source code is available under the Apache-2.0 license at https://github.com/taiga333/eval-kv-repurpose.
long-contextbenchmark - arxiv:2610.13059 · cs.CLCliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual-Textual Alignment for QA-Style Radiology Report GenerationChandravardhan Singh Raghaw, Shahid Shafi Dar, Arnav Nishith Sharma, Shrey Modi +1
Radiology reports are essential for diagnostic reasoning and patient care, yet their manual preparation is time-consuming and cognitively demanding. Automatic radiology report generation (RRG) offers a scalable alternative, but existing models often produce lengthy, unstructured narratives that overlook diagnostic cues and multi-view information. We present Clinical-Knowledge Guided Disease-aware Visual-Textual Alignment for QA-Style Radiology Report Generation (CliQ-RRG), a unified two-stage framework for interpretable and clinically grounded reporting. In Stage 1, CliQ-RRG employs a Disease-aware Visual-Textual Alignment module that aligns image and text representations using predicted disease embeddings, reinforced by a Prior-Guided Attention Module (PrAM) to capture multi-view dependencies across current and prior scans. In Stage 2, GraphRAG-guided retrieval augments intermediate textual representations with graph-grounded clinical evidence, and a large language model restructures them into concise, interpretable question-answer (QA) pairs with diagnostic summaries. Experiments on two public chest X-ray benchmarks demonstrate that CliQ-RRG consistently outperforms prior methods across both lexical and clinical metrics, generating accurate and clinically coherent QA-style radiology reports. Code is available at: https://github.com/chandravardhan-singh-raghaw/CliQ-RRG.
benchmark - arxiv:2610.13058 · cs.AITravel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon AgentsZiang Ye, Wentao Shi, Lei Chen, Zhengzhou Cai +6
Large language model agents increasingly operate in long-horizon environments where early mistakes can trigger cascading failures and trap agents in dead-end trajectories. Agents must therefore be able to proactively recover from such states and turn their exploratory experience into guidance for subsequent decisions. We introduce ReTRAIL, a framework that enables agents to rewind the environment to earlier states while preserving valid progress and carrying forward knowledge learned from abandoned exploration. The environment state moves backward while the agent's knowledge continues to move forward. ReTRAIL trains a shared policy with two complementary signals: State-Anchored GRPO compares alternative continuations from revisited states to improve execution, while a branch-advancement reward guides reflection through the progress of subsequent exploration. Experiments across four interactive benchmark MineSweeper, Sokoban, ALFWorld and ScienceWorld show that simply adding a rewind primitive provides limited benefit and can even degrade performance. In contrast, ReTRAIL enables agents to rewind from unproductive states and use insights from abandoned branches to guide subsequent exploration. These results demonstrate the value of coupling environment rewinding with experience reuse within an ongoing task for long-horizon task solving. The code is available at https://github.com/whi497/ReTRAIL.
benchmark - arxiv:2610.13057 · cs.LGCoBe: A Benchmark For Conversational Counterfactual Text EditingArvind Raghavan, Inwoo Hwang, Shreyas Havaldar, Kai-Zhan Lee +5
Counterfactual text editing is the ability to revise a given text in light of a hypothetical change while preserving facts not causally affected by that change. When asked what would have happened if a doctor had not recommended surgery, the model output should retain the patient's medical history and modify only the consequences of the decision. This requires causal understanding: a model must determine, without being explicitly instructed to, what events are affected by the hypothetical change and what should remain fixed. This skill is central to human reasoning, especially in safety-critical domains like healthcare or law. By contrast, the task of associational text generation merely generates text statistically associated with the altered condition. In the medical example, an associational response might make the patient's symptoms less severe because milder cases correlate with no surgery. Such responses produce a plausible scenario, but not the counterfactual version of the given one. Prior counterfactual-text datasets do not clearly separate these modes of reasoning. We introduce the Counterfactual Benchmark (CoBe), a testbed for models' zero-shot ability to counterfactually edit a given textual scenario when prompted to do so in a conversationally natural way. CoBe contains 2000 questions spanning healthcare, science and engineering, business, and everyday scenarios. We test a suite of frontier and smaller models, with frontier systems achieving an average score of $58.05\%$. Our findings indicate that models frequently default to associational generation rather than preserving the causal structure of the original scenario. Moreover, performance does not scale consistently with either model size or output token length, suggesting that the failure may reflect model training objectives rather than insufficient model capacity.
benchmark - arxiv:2610.13053 · cs.CVUniMergeTrack: Hierarchical Model Merging for General RGB-X Visual Object TrackingShiao Wang, Xiao Wang, Yuhe Ding, Jiarui Xu +4
RGB-X tracking leverages complementary modalities, such as thermal infrared, event, or depth, to improve robustness under challenging conditions. Existing general-purpose RGB-X trackers typically follow two paradigms: independent task-specific training and joint training across modality combinations. However, the former suffers from knowledge isolation and model redundancy, while the latter introduces optimization interference across heterogeneous tasks. In this work, we present UniMergeTrack, a new model merging paradigm that preserves task-specific optimization while enabling effective cross-task knowledge integration. UniMergeTrack first trains modality-specific trackers independently and then performs hierarchical model merging. Specifically, transferable backbones are merged across RGB-X tasks via high-pass-filtered merging, and complemented by lightweight task-specific experts that preserve modality-specific cues. Tracking heads are merged within each task using optimal transport-guided channel alignment to mitigate hidden channel mismatch. A subsequent distribution alignment fine-tuning stage further improves compatibility between the unified backbone and task-specific heads. Extensive experiments on the LasHeR, RGBT234, VisEvent, VOT-RGBD22, COESOT, and CDTB benchmarks demonstrate that UniMergeTrack achieves state-of-the-art or competitive performance across RGB-Thermal, RGB-Event, and RGB-Depth tracking tasks, while exhibiting strong generalization to unseen datasets. The source code will be released upon acceptance. The source code of this paper will be released on https://github.com/Event-AHU/OpenEvTracking.
benchmark - arxiv:2610.13050 · cs.CVNOFACE3D: NOise-scheduled Focused Anchoring and Controlled Enhancement for 3D GenerationJames Rose, Jingwen Liang, Wenchao Ma, Oren Jacob +1
Recent image-to-3D models generate complete, high-quality assets from a single image, with global shape and appearance that are already convincing; what remains is the fine scale, where small, thin, elongated, or detail-rich regions are reconstructed softly and under-resolved. This gap can arise in generators with fixed-resolution spatial grids: the same spatial sampling density is used for a large, smooth, low-curvature surface and for a thin, high-curvature structure that carries most of the perceived detail. To this end, we introduce NOFACE3D, a training-free framework that refines these detail-critical regions while preserving the rest of the asset. Given a generated mesh, its input image, and a refinement box, NOFACE3D extracts the selected submesh, scales it up to fill the generator's input volume, and re-encodes it into the full-resolution latent grid. Conditioned on the image crop, it refines the region through flow-based sampling with a spatially varying noise schedule that anchors boundary latents. The refined region is then integrated back into the original asset, preserving the surrounding geometry and appearance. We implement NOFACE3D on TRELLIS.2 and its sparse voxel representation; all of it operates purely at inference time on the frozen pretrained generator. We evaluate NOFACE3D on PAniC-3D, TexVerse and BigDetail, a new benchmark of 339 assets with annotated detail-critical regions. On all three, it generates sharper geometry and finer texture detail than the baselines. Project page: https://idkcouscous.github.io/NoFACE3D/
benchmark - arxiv:2610.13041 · cs.CLRAMP: Recurrent Adaptive Mixed Precision for Efficient Prefill in Recurrent-Depth Language ModelsKe Wan, Chen Chen
Recurrent-depth language models improve inference-time reasoning by repeatedly applying a shared network to refine internal representations, but the additional recurrent computation also increases inference cost. This overhead is particularly pronounced during long-context prefill, where the full input sequence is repeatedly processed across recurrent depth. Weight-and-activation quantization offers a natural way to accelerate this computation through lower-precision arithmetic, yet repeatedly applying quantized computation introduces numerical perturbations that accumulate along the recurrent trajectory. We systematically analyze how such errors propagate across recurrent depth and show that quantization errors introduced earlier are attenuated by more subsequent recurrent steps and therefore have a smaller effect on the final representation. Matched-budget experiments strongly support this prediction, showing that placing quantized computation earlier in recurrent depth consistently yields the best fidelity. Based on this insight, we introduce RAMP (Recurrent Adaptive Mixed Precision), which performs early recurrent refinement using low-precision weight-and-activation computation and restores high precision for terminal refinement. Across context lengths up to 4K, RAMP preserves near-full-precision prefill quality while achieving up to 1.16x end-to-end first-prefill speedup on an NVIDIA H100, corresponding to a 13.9% latency reduction.
long-context - arxiv:2610.13040 · cs.LGLightweight Time-Frequency Vibration Sensing for Consumer Device Condition MonitoringPo-Heng Chou, Jen-Yu Chiu, Chun-Yu Yeh, Wei-Lung Mao +1
Consumer rotating devices, including washing machines, air conditioners, electric fans, robotic vacuum cleaners, and home fitness equipment, increasingly rely on vibration sensing for intelligent condition monitoring and predictive maintenance. Ensuring reliable operation in these resource-constrained appliances requires efficient, lightweight artificial intelligence (AI) solutions capable of processing non-stationary signals under real-world operational interference. This paper proposes a lightweight AI-assisted vibration sensing framework that employs continuous wavelet transform (CWT) and Hilbert-Huang transform (HHT) to convert one-dimensional (1-D) vibration time-series signals into two-dimensional (2-D) time-frequency representations. These representations are subsequently analyzed using lightweight deep learning architectures, specifically MobileNetV3-Small, ConvNeXt-Tiny, and the You Only Look Once version 11 classification model (YOLOv11-cls). Public bearing benchmark datasets, including Case Western Reserve University (CWRU), Paderborn University (PU), and Intelligent Maintenance Systems (IMS), are utilized as representative rotating components to investigate model generalization. The proposed framework is designed with eventual embedded deployment in consumer electronics in mind. Experimental results demonstrate that CWT combined with YOLOv11-cls achieves high diagnostic accuracy, while MobileNetV3-Small provides an attractive low-latency alternative for computationally constrained edge platforms. Conventional random splitting is also compared with dataset-specific structured isolation. The results highlight the importance of avoiding data leakage and quantify tradeoffs in classification accuracy, parameter count, floating-point operations (FLOPs), model footprint, preprocessing cost, and central processing unit (CPU) inference latency.
benchmark - arxiv:2610.13036 · cs.LGTowards Easier-to-Tune Training Algorithms: New Results from AlgoPerfPriya Kasimbeg, Ahmed Khaled, Aahlad Chandrabhatta, Yifan Wang +8
Evaluating deep learning optimizer is challenging because confounding factors such as hyperparameter tuning and optimizer-model co-design often obscure true algorithmic performance. We present results of the updated AlgoPerf V1 benchmark, in which we evaluate a new set of training algorithms on wall-clock time-to-target across nine workloads on fixed hardware. This report focuses on the results of the benchmark's self-tuning ruleset, which requires submissions to use a single configuration across all workloads. Out of the 13 submissions in PyTorch and JAX, Schedule-Free AdamW ranked first. In addition to the wall-clock scores, we also analyze the trade-offs between step efficiency and wall-clock execution, revealing that matrix-preconditioned and two-loop methods achieve good sample efficiency but require more aggressive computational optimizations to be competitive in runtime. Finally, our hyperparameter saliency and retention analyses show that the learning rate and momentum are highly sensitive across domains and algorithms, highlighting the need for methods that are more robust against hyperparameter tuning and can generalize well to new tasks.
benchmark - arxiv:2610.13035 · cs.CVGeoGR: Spatial-Semantic Token Compression and Group Routing for Efficient 3D VLMsYongxin Zheng, Hao Wu, Fang Li, Hu Fu +7
Multi-view representations enable pretrained image and video vision-language models to understand 3D scenes, but their long visual token sequences make inference costly. Redundancy arises both from repeated observations of the same scene regions across views and from processing all visual tokens at every LLM layer, regardless of their relevance to the current computation. We propose GeoGR, a two-stage framework that jointly compresses scene representations and visual computation. At the projector level, GeoSemZip consolidates cross-view observations into 3D voxel tokens and combines semantic saliency with spatial coverage to construct a compact scene representation. Unselected voxel features are aggregated into contextual anchors to retain scene information that would otherwise be discarded. At the LLM level, we identify an effective visual computation window and observe that query-conditioned token relevance remains locally stable but changes over longer layer intervals. Guided by these findings, GroupRoute combines late entry and early exit with recoverable group-wise skipping. Low-relevance tokens bypass complete LLM layers while retaining their hidden states and can rejoin the active group at subsequent anchor layers selected under a computation budget. For compression-aware post-training, we construct a compact dataset of 67K samples by retaining 30% of the original training pool. With this protocol, GeoGR retains 95.2% and 96.8% of the dense post-trained models' performance on LLaVA-OneVision-7B and Video-3D LLM-7B, respectively, while accelerating LLM prefill by $6.8\times$ and $6.1\times$. These results demonstrate the consistent effectiveness of GeoGR across 3D VLMs with and without explicit 3D spatial encoding, highlighting a favorable performance-efficiency trade-off. The code is available at https://github.com/EIT-NLP/GeoGR.
post-training - arxiv:2610.13028 · cs.LGLow-Rank Kolmogorov-Arnold Generator Flows for Interpretable Operator LearningMinjong Cheon
Neural operators that learn physical laws from data should generalize beyond their training distribution and expose the learned law in closed form. The Kolmogorov-Arnold neural operator achieves both for position-dependent dynamics by learning a dense pseudo-differential symbol over all positions and frequencies, at a cost that grows with the square of the resolution and with closed forms that must be read out by hand. This dense symbol is unnecessary: a finite-order variable-coefficient differential operator has a symbol whose separation rank is bounded by the number of its coefficient functions, independently of the resolution, and the symbols that this network learns on its own benchmarks have rank two. We introduce the Kolmogorov-Arnold flow (KAFlow), which learns the generator of a physical operator as a low-rank symbol built from univariate Kolmogorov-Arnold functions, fixes the gauge of these functions so that every term has a unique place, integrates the dynamics with exact exponential integrators, and distills its closed form automatically. On the synthetic benchmarks of the Kolmogorov-Arnold neural operator, KAFlow lowers the out-of-distribution loss by 3.4 to 11 times and recovers every coefficient to within 10^-4 without symbolic templates, reaching the precision floor of the data. On long-horizon quantum dynamics, it lowers the state infidelity by up to 6 orders of magnitude, and by 30 times when trained only on position and momentum measurements. KAFlow also learns a variable-order fractional operator 15 times more accurately than existing operator networks and discovers nonlocal, fractional and non-polynomial dispersion relations on which sparse regression fails.
benchmark - arxiv:2610.13025 · cs.CLEvo$^2$: Evolving the Evolver through Weight-Harness Co-EvolutionChejian Xu, Shujian Zhang, Wenxuan Zhou, John Lambert +4
Self-evolving agents are increasingly used to improve language model systems without human intervention through either weight updates or harness improvements. Existing approaches typically pursue these directions separately: some methods update model weights using self-generated experience, while others rewrite the harness that defines how an agent uses prompts, tools, context, and execution feedback. However, these approaches overlook the relationship between model weights and the agent harness. To connect these processes and ensure effective and smooth agent self-evolving, we propose Evo$^2$, a framework for weight-harness co-evolution. For harness updates, we design a unified dual-role pipeline that a single policy serves as both a Proposer, which writes harness edits, and a Reflector, which diagnoses their effects and guides revision. For weight updates, harness modifications and their execution outcomes guide the training of both the Proposer and the Reflector. We further develop EvoTIDE, a training pipeline that recovers usable trajectories through edit extraction and prefix continuation, then combines SFT with interleaved GRPO across the two roles. Extensive experiments across three coding benchmarks demonstrate that Evo$^2$ significantly outperforms existing self-evolution methods. It achieves 82.1% on Polyglot and 48.3% on SWE-bench Verified, compared with 62.6% and 41.0% for the strongest baseline, respectively. We also show that the evolved harnesses transfer to different tasks without further evolution and rank first in cross-benchmark evaluations. Our dual-role harness improvement framework is also able to extend to self-evolution with proprietary models, improving a GPT-5-mini agent's performance from 24.4% to 48.3%. These results demonstrate the applicability of the framework Evo$^2$ across domains and its broad transferability across models and tasks.
agentself-evolvingbenchmark - arxiv:2610.13024 · cs.ROWhat Visual Representations Do World Action Models Need?Kai Liu, Jiangran Lyu, Tingyu Deng, Yixin Zheng +8
World Action Models (WAMs) inherit powerful priors from pretrained video generation models, but their variational autoencoder (VAE) representations are optimized for visual reconstruction rather than manipulation. External visual representations can improve manipulation, but existing methods couple representation choices with different integration mechanisms, obscuring their individual effects. We systematically compare visual representations, five integration mechanisms, and feature combinations under controlled settings. Our study yields three main findings. First, strong general-purpose visual representations provide broader robustness gains and can match or outperform representations pretrained for specific visual capabilities. Second, channel-wise joint prediction achieves the highest average success rate; further analyses suggest that future-feature prediction and the action expert's effective use of added visual information contribute to its gains. Third, additional sources should be selected for the task-relevant information they contribute beyond existing representations, as the same source can help one combination but harm another. However, even the best evaluated composition provides a smaller additional gain than the initial improvement from adding a strong general-purpose representation to the VAE-only baseline. We instantiate the resulting Representation Recipe as R$^2$-WAM. It achieves state-of-the-art performance on RoboCasa GR1 Tabletop with an 84.7% success rate and reaches 92.8% on RoboTwin 2.0, improving over the VAE-only baselines by 5.9 and 2.2 percentage points, respectively. Taken together, these findings suggest that future work should prioritize stronger general-purpose visual representations and more effective mechanisms for integrating them into WAMs, with feature composition serving as a supplementary route to improvement.
manipulationrobotwin - arxiv:2610.13023 · cs.CVUnified Generative Video Compression with Autoregressive and Bidirectional Video DiffusionTianyu Zhang, Shuai Huo, Dengchao Jin, Hewei Liu +6
Video diffusion models can reconstruct visually compelling content from severely compressed representations at ultra-low bitrates, but they impose a rigid deployment trade-off. Bidirectional (BI) models achieve high quality through dense full-sequence attention, yet require the entire sequence before reconstruction and incur substantial latency. Autoregressive (AR) models enable low-delay streaming, but their restricted temporal context reduces compression efficiency. This tension is particularly relevant when a video stream must be decoded in real time yet is also stored for later, quality-oriented playback, making AR and BI models natural choices for the live and replay stages, respectively. To support both stages, we present UniGVC, a Unified Generative Video Codec that supports two decoding modes from a single bitstream. UniGVC-BI employs a BI-DiT with dense attention for quality-oriented random-access decoding, whereas UniGVC-AR uses windowed AR-DiT for low-delay streaming. Both paths share a hierarchical latent codec that recurrently produces the same conditions with ultra-low bitrates, allowing UniGVC-BI to serve as a conditional teacher for single-step distillation of UniGVC-AR. A tiny conditional video decoder further reduces streaming latency while preserving most of the reconstruction quality. On standard 1080p benchmarks, UniGVC-BI achieves the best overall rate-distortion-perception trade-off among the evaluated methods and produces temporally stable video at rates as low as 0.0005 bits per pixel. Meanwhile, UniGVC-AR remains competitive while decoding 1080p video at 36.85 FPS, over $250\times$ faster than UniGVC-BI. Code and models will be released later.
benchmark - arxiv:2610.13022 · cs.AIDon't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software DevelopmentMingyu Chen, Zhiqing Zhong, Manyi Wang, Linxi Liang +2
As LLMs become increasingly capable of implementing software, a critical bottleneck emerges: whether they truly understand what users want. Users often begin with vague intent, leaving important requirements to be clarified through interaction. In repository-level development, misunderstandings can propagate and cause costly rework. However, existing benchmarks typically evaluate implementation from complete specifications or underspecified requests, overlooking pre-coding requirement clarification. Prior clarification studies mainly focus on function-level tasks. It therefore remains unclear how well LLMs can transform vague intent into clear requirements through interaction and how this capability affects subsequent code generation. We introduce ReqClarifyBench, an interactive requirement clarification benchmark for repository-level software development. It contains 341 tasks spanning game, miniapp, and web development, each with a vague user intent, a human-validated requirement document, and code evaluation artifacts. We employ LLM-based user simulators with diverse personas derived from real-world conversations. We evaluate six LLMs in terms of clarification effectiveness and generated requirement document quality. Results show that stronger clarification effectiveness does not necessarily translate into higher document quality, and performance varies substantially across user personas. We also find that coding-agent harnesses do not further improve requirement document quality compared with their base LLMs. These findings offer insights for building LLM-based end-to-end software development systems.
benchmark - arxiv:2610.13021 · cs.CVEmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied AgentsJie Huang, Yanan Chen, Ruixun Liu, Kaichen He +5
Continual learning requires models to accumulate past experience and transfer it to new tasks. Despite substantial research on continual learning, existing work remains largely confined to non-embodied settings, without extending to embodied environments. To address this gap, we introduce EmbodiedCLBench, the first benchmark in embodied simulation for evaluating the continual learning capability of self-evolving agents. With compositional generalization as the core evaluation principle, our benchmark evaluates whether agents can first learn from basic tasks and then recombine the acquired skills to solve complex, unseen advanced tasks. Based on EmbodiedCLBench, we conduct extensive experiments across multiple agent harnesses and learning methods, revealing consistent limitations and distinctive behaviors. Our results show that while advanced tasks can be hardly solved under zero-shot setting, the experience from basic tasks enables consistent improvement. Such benefit from the experience remains stable even if the task complexity increases. However, this improvement does not scale accordingly with the number of learning samples, and current agents cannot extract meaningful information from additional experience. Collectively, our findings highlight continual learning as a fundamental yet underexplored capability, and our benchmark offers valuable resources for designing effective self-evolving agents in embodied environments. Our code and dataset are available at https://pku-value-lab.github.io/EmbodiedCLBench-homepage.
embodiedagentembodied agentself-evolvingbenchmark - arxiv:2610.13020 · cs.LGTrajectory-Aware Policy Optimization: Closing the State Distribution Gap in Long-Horizon LLM RLZhicheng Cai, Weinan Dai, Yuyan Zhou, Wei-Ying Ma +2
Reinforcement learning (RL) has become a dominant paradigm for enhancing LLMs' reasoning capabilities. Yet long-horizon autoregressive rollouts introduce a fundamental limitation: local policy mismatch can compound into severe state distribution shift over trajectories. Existing LLM RL methods, such as GRPO and GSPO, control policy mismatch at the token or sequence level, but overlook this trajectory-induced shift, causing training instability and eventual collapse as the horizon grows. To close the state distribution gap, we propose Trajectory-Aware Policy Optimization (TAPO), a principled framework that theoretically derives the state-distribution correction from the off-policy policy gradient and incorporates it into the RL objective. TAPO further employs a geometric-mean estimator for variance reduction, together with a length-aware dynamic clipping that prevents overly deviated updates across the trajectory. Extensive experiments demonstrate that TAPO significantly surpasses existing LLM RL algorithms across eight competition-level benchmarks, achieving up to 48% and 12% improvement over GRPO on mathematical reasoning and algorithmic coding, with substantially enhanced training stability.
benchmark - arxiv:2610.13015 · cs.LGGeneralized Proximal Policy Optimization: Unifying LLM RL Algorithms from the Perspective of DivergenceZhicheng Cai, Xinyuan Guo, Hanlin Wu, Weinan Dai +4
Reinforcement learning has become the foundational paradigm for enhancing the reasoning capabilities of LLMs. Yet the dominant approach, Proximal Policy Optimization (PPO), relies on a geometrically degenerate clipping proxy that cannot adapt its resistance to policy shifts, leading to premature clipping and degraded exploration. Subsequent variants alleviate these issues through fragmented and heuristic modifications. We propose Generalized Proximal Policy Optimization (GPPO), a principled and unified framework for understanding and designing LLM RL algorithms through the lens of divergence. We establish a generalized $f$-divergence trust-region theory with a monotonic performance improvement guarantee, and show that different $f$-divergences induce distinct geometries and policy update dynamics. We further introduce novel estimator topologies that provide more faithful divergence estimates than the conventional single-sample Monte Carlo estimation. Under this framework, PPO and recent variants such as DAPO, DPPO, and RIPO emerge as special cases, establishing a principled two-dimensional design space of {Divergence $\times$ Estimator}. Extensive experiments on eight competition-level math and coding benchmarks show that both dimensions are critical. The best-performing GPPO instantiation surpasses standard GRPO by up to 50% and 14% on math and coding, delivering SOTA performance.
benchmark - arxiv:2610.13013 · cs.LGEvidential Multimodal Transformers with Dempster-Shafer Fusion for Emotion RecognitionMuhammad Usama, Yeoreum Jung
Softmax-based multimodal emotion recognition methods often assign high confidence even when sensor data are corrupted or contradictory, for example when facial expressions suggest positive valence while vocal prosody indicates negative arousal. We present an Evidential Multimodal Transformer with Dempster-Shafer Fusion (EMT-DS) that addresses this problem through formal uncertainty quantification. EMT-DS models predictions as Subjective Opinions (Dirichlet distributions), separating epistemic uncertainty (lack of evidence) from aleatoric uncertainty (sensor noise). Modality-specific transformer encoders produce belief mass distributions that are fused with Dempster's Rule of Combination, which normalizes the joint belief mass by a conflict coefficient 1/(1-c), so that contradictory evidence is explicitly quantified as conflict and the fused prediction becomes diffuse rather than being forced into an unjustified consensus. Under subject-independent and speaker-independent evaluation on four benchmarks, EMT-DS achieves 84.3% accuracy on IEMOCAP versus 81.7% for the best baseline (p < 0.01), 82.4% on DEAP under leave-one-subject-out evaluation versus 78.1%, and 96.8% on the highly imbalanced KEMDy20, and it improves accuracy on CMU-MOSEI by 2.4 points over the strongest evidential baseline. In controlled ablation, it reduces Expected Calibration Error from 0.153 (softmax transformer) to 0.042. It maintains 71.2% accuracy under severe Gaussian noise on audio features (sigma = 1.0), where attention baselines drop to 45.3%, and degrades gracefully when entire modalities are absent. The fusion step has O(MK^2) complexity, compared with O(M^2 d^2) for cross-modal attention. The learned conflict metric also flags likely errors: reviewing 20% of samples captures 80% of misclassifications, which supports selective prediction in clinical and safety-critical systems.
benchmark - arxiv:2610.13008 · cs.AIProvenance-Aware Belief Updating in Human-AI Feedback LoopsTianyi Huang, Eric Liu, Jay Chong, Emily Yin +1
In repeated human-AI interaction, a single observation can be quoted, summarized, and returned to a model as multiple reports, making repetition look like independent corroboration. We study whether language models can use supplied report lineage to update according to evidence provenance rather than report count. We introduce Latent Quotient Evidence Training (LQET), a relational objective that combines sparse Bayesian supervision with constraints that encourage stable predictions when reports add no new evidence and consistent updates to the same new evidence across relay histories. On a controlled binary benchmark, LQET reduces new-evidence update RMSE by 41-44% and log-odds drift after eight relay steps by 89-91% relative to task-only training across Qwen3-4B and Phi-4-mini, with three paired training seeds per backbone. The gains extend to a closed-loop simulation in which model confidence controls how many relayed reports re-enter the model's context in later rounds. By grounding belief updates in supplied provenance, LQET offers a route toward dynamic human-AI systems in which influence follows new evidence, not the number of times the same evidence returns.
benchmark - arxiv:2610.13002 · cs.LGScaling Empowered AgentsCatherine Ji, Vivek Myers, Joshua Lin, Alexandra Wingate +2
Empowerment measures the capacity of an agent to actively control its environment. In this work, we explain the connection between skill learning and empowerment. While skill learning is not empowerment, we introduce a simple scalable recipe for empowerment maximization: empowerment corresponds to the number of executable skills from a state, so maximizing empowerment corresponds to reaching states that are good starting points for many skills. Our recipe applies to arbitrary underlying skill learning methods. Whereas most prior work on empowerment looks at tabular settings, this recipe enables us to study empowerment at a scale where we can realize theoretically-predicted but empirically-elusive properties of empowerment (e.g., gathering resources, environment modification, survival). Experiments show that empowerment maximization unlocks interesting emergent properties, such as building a house in Crafter. Website and code at \href{https://empowerment-geometry.github.io/scaling-empowerment/}{this https url}.
agent - arxiv:2610.13000 · cs.AIHindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task CharacteristicsO. Ozan Koyluoglu
Language-model agents are used for specialized work such as financial research, healthcare and law. Such agents are often capable enough for a task but still miss its details. In finance, for example, these details include which filing reports a figure or how a company discloses a metric. Retraining the agent to learn these details is expensive, and often impossible when the agent is a closed or shared system. Writing the missing know-how into the agent's prompt makes the prompt long and identical for every input, although different inputs need different guidance. We propose to learn to generate this guidance instead. A small advisor model reads each input and writes structured advice, which is appended to the prompt of a frozen executor. The advisor is trained with hindsight, following work on distillation with privileged information. On a training pool with graded answers, we analyse the executor's failures, run it under several strategies to see which one worked on each input, and let a teacher that sees the grades and the traces write the advice that would have helped. The advisor then learns, by supervised fine-tuning, to write that advice from the input alone. Because the student is a separate small model rather than the executor, it is cheap to train and adds little latency. We call this approach hindsight structured advice distillation (HSAD). On FrontierFinance, a public benchmark of expert-written financial research queries, an 8B advisor raises the qualification rate of Samaya's proprietary research agent, which already leads the benchmark's leaderboard, from 52.9% to 56.6%. This is above the agent's own high-effort configuration, at 37% lower cost per query. We study the generalization of the proposed approach, and in particular show that HSAD also improves results on WebShop, BIRD text-to-SQL and ExpertLongBench.
agentbenchmarkleaderboard - arxiv:2610.12999 · cs.ROEgoReveal: Learning Active Vision and Object Manipulation under Partial Occlusions from Egocentric DemonstrationsHiromu Kurihara, Kazutoshi Tanaka, Masashi Hatano, Tadashi Kozuno +2
Learning from Demonstrations (LfD) enables robots to learn object manipulation directly from human demonstrations. In contrast to resource-intensive and labor-intensive teleoperation, egocentric demonstrations are easy to collect, enabling scalable data collection. Manipulated objects are often partially occluded in everyday environments, yet prior egocentric demonstration-based methods that require no robots or specialized teaching devices do not explicitly address occlusions. To fill this gap, we propose EgoReveal, a framework that learns viewpoint-repositioning together with manipulation actions from egocentric human demonstrations to reposition the viewpoint and obtain target visibility under partial occlusions. EgoReveal instantiates this as two imitation policies: one predicts the future camera-arm pose sequence from the current view and camera-arm pose, and the other predicts the future control commands from object keypoints and a history of control commands. EgoReveal switches between the two based on target visibility. In experiments where the manipulated object is partially occluded initially, EgoReveal repositions the camera to obtain visibility and completes the task more reliably than fixed-camera baselines.
manipulationteleoperation - arxiv:2610.12998 · cs.CLEvaluating LLM Creativity through Long-Tail PerformanceYichen Wang, Tenghao Huang, Vishakh Padmakumar, Mina Lee
Creativity benchmarks for large language models (LLMs) vary widely in task and metric design. This raises the question of whether they capture a common notion of creativity. We propose that this shared target can be formalized as task-specific performance in the long tail of a reference input-output distribution, which describes how common input-output pairs are relative to a chosen source of text. We ground this proposition in the novelty-quality product formulation and evaluate it empirically across 15 benchmarks and 26 open-weight models, using n-gram absence from the pretraining data as a novelty proxy. Our results show that creativity benchmarks lie further in the tail regions than standard benchmarks. Moreover, on both creativity and standard benchmarks, model rankings from higher-tail subsets of each benchmark align more closely with human creativity judgments in LM-Arena. Building on these findings, we introduce q@Tail($α$), a lower-cost creativity diagnostic that measures mean task quality on the tail fraction of an existing benchmark. Applying it to creativity-promoting methods reveals substantial room to improve LLM creativity through stronger tail performance.
benchmark - arxiv:2610.12997 · cs.AIBenchmarking Embedding Geometries and Clustering Algorithms for Unsupervised Patent Claim ClassificationSujith Subramanian, P N Bhargav Teja, Susen Sarkar, Rajasekhara Reddy Duvvuru Muni
Prior-art retrieval systems are structurally organized around classification codes, making cross-code discovery difficult. This paper asks if an unsupervised representation trained on patent text can recover relevant connections that code-restricted search cannot, and if hyperbolic space helps. We trained a hyperbolic and a matched Euclidean Variational Autoencoder (VAE) on 45,000 US patents (96 runs, 6 seeds). The hyperbolic model retrieves genuinely cross-category prior art 52% more often than the Euclidean model (18.76% vs. 12.34% of top-10 results, 3,000 queries). This represents a practical gain for the motivating search problem. The hyperbolic model agrees less with official classification (NMI 0.2392 vs. 0.3206), which we explain geometrically: the two measures capture different goals, and only one aligns with prior-art search needs. In a study of 10 technology domains (50,000 more patents), we find that a domain's classification breadth--the number of distinct CPC subgroups spanned--predicts approach performance (Pearson r=-0.642, p=0.045, N=10), and that patents per subgroup is an even stronger predictor (r=0.715, p=0.020). This provides a checkable signal for practitioners to determine where the method is most valuable. We report all findings with statistical transparency and release a complete, 91-test automated implementation.
benchmark - arxiv:2610.12995 · cs.LGWhat Should SFT Learn? Conditional Information Gain for Generalizable Post-TrainingYuxuan Gu, Kequan Niu, Xiaocheng Feng, Yun Li +2
Supervised fine-tuning (SFT) remains a widely used approach for post-training large language models, because fixed demonstrations can directly introduce desired reasoning strategies and behavioral patterns. Yet forcing a model to imitate externally provided trajectories may also interfere with behaviors already supported by pretraining, limiting generalization beyond the training distribution. Recent dynamic SFT methods mitigate this issue by reweighting token-level supervision according to model-side signals such as predictive probability, prior support, or distributional compatibility. However, model compatibility is not equivalent to learning value: a token that is weakly supported by the current model may either be an undesirable mismatch or precisely the task-specific decision that the demonstration is intended to teach. We propose CIG-SFT, an information-theoretic framework that estimates the task-conditioned information carried by each demonstrated token. Under teacher forcing, we compare the token likelihood from a frozen reference model with and without access to the task input while keeping the gold solution prefix fixed. The resulting conditional information gain quantifies how much the task itself reduces uncertainty about the demonstrated decision. We then convert this information into a KL-regularized projection of the current policy and derive an equivalent scalar-weighted SFT objective whose logit gradient exactly matches that of the projected target. Across mathematical reasoning and code-generation benchmarks, CIG-SFT consistently outperforms standard SFT and recent adaptive fine-tuning baselines, with particularly strong improvements in generalization to challenging evaluation distributions, while requiring neither additional training data nor online rollouts.
post-trainingbenchmark - arxiv:2610.12990 · cs.LGGaussian-Width Bounds for Offline-to-Online Linear BanditsKushagra Chandak, Volodymyr Tkachuk, Xiaoqi Tan, Csaba Szepesvári
We study how offline data can help online learning in stochastic linear bandits. We focus on partially covered offline data, where only $k$ of the $d$ feature directions are poorly covered. Existing analyses of algorithms based on phased elimination and optimism give regret bounds of order $\widetilde O(\sqrt{dkT})$ in this regime. We show that this dependence arises from loose control of the reward prediction error, and obtain tighter bounds using concentration of Lipschitz functions of Gaussian vectors. Based on this analysis, we develop a phased elimination algorithm with regret $\widetilde O(k\sqrt T)$. For the unit Euclidean ball, we prove a matching regret lower bound under partial coverage, as well as matching upper and lower bounds under uniform offline coverage. We also study pure exploration with offline data, providing algorithms and matching upper and lower bounds on simple regret for fixed-design algorithms and also for adaptive algorithms under partial and uniform coverage of offline data.
online learning - arxiv:2610.12989 · cs.CLLanguage Models Have Interpretable Narrative MechanismsDavid Yiyang Liu, Aditya Joshi, Paul Dawson, Andrew Piper
We investigate whether language models contain internal components that contribute to representing narrativity, the degree to which a text exhibits narrative properties. Across GPT-2-Small, Gemma-2-2B, and Llama-3.1-8B, we identify attention heads, MLP neurons, and sparse autoencoder features whose activations correlate with narrativity. Ablating selected neuron and feature sets increases next-token prediction loss more for high-narrativity than for low-narrativity texts, and reduces the narrativity of open-ended generations. On downstream benchmarks, the largest effects occur in story completion and narrative question answering, although they vary across models and languages; results on confabulation and hallucination benchmarks are mixed. These findings provide causal evidence that selected sets of narrative-associated components contribute to model behaviour, while their internal organisation, relation to narrative theory, and broader functions remain open questions.
benchmark - arxiv:2610.12988 · cs.MASwingGuard: Risk-Conditioned Multi-Agent Swing Trading with Dual-Timescale GovernanceJunzhou Su, Yichen Luo, Yebo Feng, Teng Li +1
Cryptocurrency swing trading spans mismatched timescales: positions remain active while market and event risk can change within minutes. However, many predictive and large language model (LLM)-based trading systems assess risk after strategy generation or run both functions at the same cadence, leaving proposals unconditioned by current risk and exposure weakly governed between revisions. We propose SwingGuard, a dual-timescale, long-only multi-agent framework for risk-conditioned strategy generation. At the strategy timescale, specialized analysts synthesize point-in-time technical, sentiment, on-chain, and macroeconomic evidence through bullish-bearish deliberation. The resulting evidence and current risk context are then combined by a Portfolio Architect to form a target position. At the governance timescale, a five-minute Risk Controller performs conditional diagnosis, maintains persistent risk states with staged recovery, audits the proposal, and constrains execution until the next strategy revision. This design allows risk to shape the feasible strategy before proposal finalization while continuing to govern the active position afterward. Evaluations on Bitcoin (BTC) and Ether (ETH) show that SwingGuard preserves positive returns after transaction costs while maintaining shallow drawdowns and strong risk-adjusted performance on both assets. The exposure-capped joint portfolio achieves a Sharpe ratio of 2.98, compared with 2.79 for an otherwise identical Post-hoc Risk variant. Structured traces further link risk evidence and state transitions to strategy constraints and executed position changes, providing an auditable framework for asynchronous cryptocurrency swing trading. Overall, the results indicate that conditioning strategy formation on current risk, together with persistent high-frequency governance, improves risk-adjusted performance without sacrificing auditability.
multi-agentagent framework - arxiv:2610.12986 · cs.LGScan-Parallel Variational Inference for event-driven Latent Jump ModelsVansh Bansal, Min Chen, James G. Scott
Continuous-time latent state-space models are widely used for irregularly observed time series, typically representing uncertainty through a random initial state followed by smooth ordinary differential equation (ODE) dynamics, or Brownian perturbations accumulated by a stochastic differential equation (SDE). While these constructions are natural for smooth or diffusive systems, they do not directly encode a finite set of unobserved shocks whose timing, magnitude, and effect on memory are themselves uncertain. We instead introduce latent jump models (LJMs): the latent state follows closed-form deterministic dynamics between Poisson-driven event times and undergoes a learned instantaneous jump at each event, with state-dependent intensity and mark distributions. This defines a time-homogeneous Markov process whose jumps are intrinsic state transitions rather than numerical integration steps. For training, we derive a tractable event-augmented path-space evidence lower bound (ELBO) and introduce Scan-Parallel Variational Inference (SPVI): an observation-conditioned variational posterior samples the complete latent event configuration before the state recurrence is evaluated using triangular affine scans. This enables fast and scalable training for LJMs in logarithmic temporal depth. Across synthetic stochastic systems and real irregular time series, LJMs remain competitive with continuous-time latent baselines in forecast accuracy, often with fewer latent updates than numerical solver evaluations, while training one to two orders of magnitude faster than the sequential baselines.
memory - arxiv:2610.12985 · cs.LGNucleoNet: A Nuclear-Aware Determinant Ansatz for Multi-Geometry Neural Variational Monte CarloQiao Gao, Yang Huang, Enze Hou, Yuzhi Liu +2
Neural-network variational Monte Carlo provides an accurate route to solving the electronic Schrödinger equation, but many neural wavefunctions are optimized for a single nuclear geometry, requiring separate calculations to map out a potential energy surface. We introduce NucleoNet, a nuclear-aware determinant ansatz in which electrons and nuclei form a unified particle set propagated through a shared electron--nucleus backbone that jointly evolves one-particle and two-particle representations. Nuclei carry learned representations that evolve alongside the electronic representations and condition orbital construction, while antisymmetry is imposed only by electronic determinants. On equilibrium small-molecule benchmarks, NucleoNet achieves accuracy comparable to established neural-wavefunction baselines with substantially fewer parameters. For each molecular system, a single model optimized jointly across geometries describes the N$_2$ dissociation curve, Li displacement in LiCN, and the ethane and formamide minimum-energy paths for bond dissociation. Sparse-geometry training generalizes to unseen geometries for N$_2$ and LiCN without further optimization, and N$_2$ ablations show that nuclear streams substantially improve this interpolation. These results show that a compact wavefunction with jointly evolved nuclear representations can describe the geometries of a molecular system with a single set of parameters.
benchmark - arxiv:2610.12984 · cs.AIWork2Skill: Capturing Human GUI Experience for Reusable Agent Skill InductionYuqi Huang, Hui Li, Yifei Cao, Zikun Cai +8
Computer-use agents can perform increasingly complex GUI tasks, yet unfamiliar software and workflows requiring human domain knowledge remain challenging. Human demonstrations convey procedural knowledge through the same GUI interaction space, but reuse requires interpreting actions in context and separating workflow rules from task-specific details. We thus introduce Work2Skill, a framework that captures human GUI experience for reusable agent skill induction. WorkRecorder provides the framework's infrastructure for collecting this experience, aligning screen recordings, mouse and keyboard events, and available accessibility-tree information. Using WorkRecorder, we construct WorkDemo-350, the first synchronized multimodal dataset of human desktop GUI demonstrations for reusable agent skill induction and downstream evaluation. Its 350 demonstrations are screened for completeness and task success. We then propose an agentic skill-induction method that inspects evidence on demand to produce reusable skills capturing workflow rules, step dependencies, and completion checks. When the same four execution models are equipped with skills induced by each method under shared execution settings, Work2Skill achieves the highest scores and success rates. Mean score improvements over the corresponding No Skill baseline are 4.67--10.54 points on MyPCBench Bounded Action and 3.11--7.50 points on a 286-task subset of OSWorld-Verified. Our code and data are available at https://github.com/china-qijizhifeng/Work2Skill.
agentagentic - arxiv:2610.12975 · cs.AISmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales AgentsP N Bhargav Teja, Velpula Lokesh Reddy, Madhu Basumata, Susen Sarkar +1
We present SmartSalesBench, the first multi-turn conversational benchmark explicitly designed to evaluate large language model (LLM) sales agents against psychologically grounded, resistant buyer personas. Existing task-oriented dialogue benchmarks assume cooperative users and measure task completion; SmartSalesBench inverts this assumption, placing agents against personas programmed to resist and challenge across conversations of up to twenty turns. The benchmark includes five agent profiles, twelve buyer personas, fifteen smartphone products across six price tiers, and four controlled experiments with 3 iterations totaling 13,680 sessions. Both sales-agent and buyer persona generations are grounded through retrieval-augmented generation (RAG). We introduce nine evaluation metrics grouped into three tiers: primary outcome metrics (CR, BRS, RIR), secondary quality metrics (SMS, PFS, ETI), and exploratory metrics planned for future reporting (ITS, ARI, SPI). Our evaluation combines automated LLM-as-judge scoring with internal human assessment (n = 50, \k{appa} = 0.71, Pearson r = 0.81 with BRS).
retrieval-augmentedagentbenchmarkllm-as-judge - arxiv:2610.12972 · cs.ROAdaptive Whole-Body MPC with Optimal Posture Planning for Humanoid Robots under Unknown PayloadsManh Cuong Nguyen, Duc Cuong Vu, Viet Anh Vu, Duc Tuan Pham +4
Humanoid robots performing lifting and material-handling tasks must maintain balance despite unknown and varying payloads. However, payload uncertainty significantly affects whole-body dynamics and may destabilize conventional controllers. We propose an adaptive whole-body control architecture that integrates three components: (i) a centroidal model predictive controller (MPC) that generates dynamically feasible reference motions, (ii) an adaptive fuzzy balance controller that compensates for payload-induced model mismatch by generating corrective torques distributed across the supporting-leg joints, and (iii) a waypoint-based optimal posture planner built on a triple-integrator model that produces smooth sit-to-stand and stand-to-sit trajectories satisfying center-of-mass (CoM) stability constraints, joint limits, and whole-body feasibility requirements. Together, these components enable stable lowering, grasping, lifting, carrying, and placing behaviors under significant payload uncertainty. Extensive simulation and hardware experiments demonstrate that the proposed framework improves balance robustness and reduces tracking degradation during posture transitions and lifting tasks compared to non-adaptive baselines.
humanoidwhole-body controlgrasp - arxiv:2610.12963 · cs.CVMotionCoach: Constructing Multimodal Guidance for Video Professional Motion EditingSiyi Qian, Hanqing Yang, Weihuang Lin, Zihao Yang +3
Video editing models achieve strong performance in modifying appearance, backgrounds, styles, and motions, empowered by large-scale training data. Beyond general scenarios, professional motions are significant in performance, sports, and martial arts. This paper focuses on professional motion editing, which involves fine-grained motion technique and temporal structure. Given professional motion names but lacking detailed descriptions, existing models often fail to generate professional motions, such as incorrectly lifting the front wheel under a Stoppie instruction. To address this challenge, we introduce MotionCoach, a trained multimodal agent that uses multi-turn tools and performs self-verification, producing a grounded prompt and a reference clip as reliable and sufficient multimodal guidance to inject external professional motion knowledge into video editing models. To supply training data, we build a data pipeline to construct trajectories. We cold-start the agent on MotionCoach-SFT-10k and apply Group Relative Policy Optimization (GRPO) on MotionCoach-RL-2k with rewards on the motion guidance prompt, the motion outcome video, and the format. For evaluation, we introduce VPMEBench, comprising 314 professional motion editing tasks with fine-grained references and annotations. Extensive experiments show that MotionCoach improves the overall score from 55.1 to 65.6 on Seedance 2.0 and from 51.2 to 64.5 on MiniMax-H3. Learning to construct multimodal guidance enables precise professional motion editing without retraining video editing models.
agent - arxiv:2610.12961 · cs.CVMVGraph: Benchmarking LVLMs on Evidence Composition across Multi-View Visual GraphYingjie Zhu, Han Cheng, Xuefeng Bai, Youcheng Pan +2
We introduce MVGraph, a benchmark for evaluating large vision-language models (LVLMs) on multi-graph reasoning where the evidence required by a query is distributed across multiple interrelated visual graph views. Although such evidence commonly resides in source-specific graphs, temporal snapshots, or local observations, existing graph reasoning benchmarks remain confined to a single self-contained structure, assessing only graph perception and reasoning while leaving the alignment and composition of evidence across views underexplored. MVGraph comprises 8k instances spanning 8 \textit{graph-theoretic} tasks, abstracted from two multi-graph scenarios (partial and temporal graph views). Each problem is programmatically constructed and verified to be unsolvable from a single view. Beyond end-to-end evaluation, we decompose multi-graph reasoning into four complementary capabilities---Perception, Alignment, Composition, and Reasoning---and design 29 diagnostic tasks with 64k instances to probe each one, along with golden intermediate representations for evaluating the intermediate process. Across 15 LVLMs, we reveal the difficulty of multi-graph reasoning and identify cross-view edge alignment and relation-level composition as prominent bottlenecks through stage-oriented diagnostics. Meanwhile, temporal constraints and increasing view counts expose further capability boundaries. Code and data are available at https://github.com/AAAndy-Zhu/MVGraph.
benchmark - arxiv:2610.12959 · cs.CVVideo Codec-Guided Training-Free Token Compression for Video Large Language ModelsXihua Sheng, Ruijie Liu, Chang Wen Chen
Video large language models (VLLMs) rely on long visual token sequences to understand complex temporal content, which makes visual token compression important for efficient inference. Existing training-free compression methods mainly reduce the number of tokens sent to the language model, but the compression process itself can still require many visual feature comparisons, especially for intra-frame token protection and inter-frame temporal token merging. This paper proposes a video codec-guided training-free token compression method for VLLMs that uses coding information already available in compressed video as a low-cost search prior. The method aligns reference-frame dependencies, motion vectors, and residuals with the visual token grid. Residual information forms compact candidate pools for token protection, while motion information is propagated along reference-frame chains to construct localized candidates for temporal token merging between sparsely sampled frames. Local visual feature similarity comparison is then used within these candidates to make the final compression decisions, without modifying the base VLLM. Experiments on three representative VLLMs and four video-understanding benchmarks show that the proposed method achieves performance comparable to the state-of-the-art training-free baseline FlashVID, and in some settings surpasses it, while substantially reducing the feature comparisons required by token protection and temporal matching. These results demonstrate that codec information can effectively improve the accuracy-complexity tradeoff of video token compression.
benchmark - arxiv:2610.12957 · cs.ROJoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied AgentsGangyi Li, LuYao Wang, Jingfu Sun, Jingyi Yuan +6
Embodied agents must translate multimodal observations and user requests into executable actions while adapting to product constraints, changing goals, and execution feedback. We present JoyInside-VLM-Agent, a ReAct-style multimodal agent developed through product-conditioned trajectory construction and staged policy learning for robotic platforms and smart hardware. A closed-loop sandbox generates multimodal interaction trajectories covering goal revisions and failure recovery, which are checked against execution outcomes and semantic criteria. Supervised fine-tuning and multi-teacher on-policy distillation precede reinforcement learning with DPER (Dual-Source Privileged On-Policy Self-Distillation with Token-Level Evidence Routing). DPER routes token-level evidence between a frozen privileged teacher and a privileged student sharing the rollout policy's parameters, modulating reward-derived token advantages while preserving their signs. Training rewards combine generative process evaluation, multi-judge rankings, and task-queue consistency. JoyInside-VLM-Agent achieves a BFCL v4 overall score of 77.44, exceeding the evaluated baselines; results on the other public benchmarks are mixed. On JoyInside-Devices and JoyInside-Robotics, the evaluated system, which includes domain-specific skill refinement, leads the baselines on all reported metrics. Two real-world quadruped case studies illustrate visually grounded search, replanning after execution failure, and explicit failure reporting.
embodiedquadrupedagentembodied agentbenchmark - arxiv:2610.12954 · cs.AIMathVis: Can AI Reason through Drawing? A Benchmark for Mathematical Figure GenerationJingjing Wei, Hao Zhao, Xinke Li, Linxi Yu +2
This paper introduces MathVis, a benchmark designed to evaluate LLMs' ability to visualize frontier mathematical problems and perform diagram-assisted reasoning. The benchmark consists of 512 tasks, each comprising a mathematical statement, a reference diagram, executable TikZ or SVG code, a Gold Intermediate Representation (IR), atomic rubrics, and error codes. Through rigorous evaluation, GPT-6-Astra, Claude Fable 5, and Gemini 3.1 Pro Preview achieve pass@1 scores of 31.25%, 26.56%, and 22.85%, respectively. We found that although the tasks require visualization, LLMs produce outputs dominated by formal languages, symbols, and graphics programs, rather than explicit diagram-mediated reasoning. Furthermore, while the solutions generated by LLMs may contain all the necessary elements, they are often visually confusing to humans. Ultimately, this benchmark aims to visualize mathematical problems and promote research on enabling LLMs to simplify their reasoning via visual diagrams.
benchmark - arxiv:2610.12941 · cs.CVUniDeblur: Unified Motion Deblurring via Fourier Convolution LearningXintian Mao, Jiansheng Wang, Huaiyuan Wang, Qingli Li +1
Image deblurring is a fundamental task in computer vision, yet existing methods mainly specialize in isolated scenarios. Consequently, the deblurring performance of these models drops significantly across scenarios with different cameras and image contents. This motivates the development of a unified motion deblurring framework that can handle diverse blur patterns. To this end, we construct a multi-source dataset and develop a data pruning and quality control pipeline. Then, to restore blur images with various motion blur kernels across different scenarios, we propose a unified motion deblurring framework via Fourier Convolution Learning. Existing deblurring networks usually rely on pixel-level mappings and overlook the convolutional nature of blur. Thus, the network mostly fits the image content itself rather than learning the convolution process, making it difficult to handle multi-source blur images. Instead of relying on spatial mapping, we perform blur-adaptive global filter learning in Fourier space, which avoids the limited spatial support of kernel estimation. Extensive experiments demonstrate that our unified model effectively handles motion blurs across diverse sources and scenes, achieving competitive performance across both in-domain and OOD benchmarks. Code will be released at github.com/DeepMed-Lab-ECNU/Single-Image-Deblur.
benchmark - arxiv:2610.12936 · cs.ROEvo-World: A Lightweight Vision-Language-Action Model with Future Motion Prediction via Optical-Flow SupervisionZile Zhong, Yuxin Du, Tao Lin, Haoxiao Wang +3
Vision-language-action (VLA) models provide a unified framework for visual understanding, language grounding, and robot control, yet anticipating how the scene will evolve beyond the current observation can provide additional information for control. Action supervision alone does not explicitly encourage such anticipation, while future-image prediction entangles task-relevant motion with largely static appearance. To address these limitations, we introduce Evo-World, a lightweight VLA model that augments policy learning with future motion prediction through optical-flow supervision, thereby providing a task-relevant predictive signal focused on motion rather than appearance. We further design the training procedure to preserve these predictive representations during policy learning, regulating representation diversity while decoupling representation learning from action optimization. Across simulation benchmarks, Evo-World demonstrates strong performance, achieving a tier-averaged success rate of 91.1% on Meta-World MT50 , with a 13.0% relative improvement over the non-predictive baseline. On real-world AgileX robots, Evo-World outperforms the evaluated baselines across single-arm and bimanual manipulation tasks while using only 0.87B parameters and delivering lower GPU memory usage and higher inference efficiency. These results demonstrate that future motion prediction through optical-flow supervision provides an effective and lightweight approach to enhancing the predictive capabilities of VLA models.
vision-language-actionvlavla modelmanipulationmemorybenchmark - arxiv:2610.12933 · cs.AILearning More by Training Less: Uncertainty-Guided Progressive Contraction for Efficient Reasoning Post-TrainingSuorong Yang, Jiaxin Wang, Jiaming Su, Chentao Yue +3
Large language models have achieved remarkable advances in complex reasoning. However, scaling reasoning post-training with ever-larger corpora can substantially increase training cost without proportional performance gains. In this study, we therefore ask: how far can reasoning supervision be compressed without sacrificing capability? To this end, we propose an uncertainty-guided progressive contraction framework that concentrates supervision and optimization on the reasoning trajectories most valuable for learning. Specifically, rather than treating a teacher-generated chain-of-thought (CoT) as a single realized path, we construct uncertainty-profiled reasoning supervision by building Monte Carlo reasoning trees around intermediate reasoning states to expose process-level uncertainty. This uncertainty first contracts the original corpus into a compact teacher-informed pool. A second, learner-aware contraction then performs online routing during SFT, concentrating optimization according to the student's evolving learning state. Together, the two stages progressively contract both supervision and optimization, substantially reducing the student training budget. Experiments across diverse reasoning benchmarks and LLM families show that our method uses as little as 0.22% of the optimization budget of full-data SFT, over 450x less training exposure, while maintaining or improving reasoning performance. Notably, our framework generalizes well across heterogeneous student families, black-box teachers, and weak-to-strong transfer. This indicates that it is not only a way to accelerate training but can also enhance reasoning capability.
post-trainingbenchmark - arxiv:2610.12932 · cs.CLSEEDS: Preview-Guided Evidence Admission for Search AgentsJiajin Liu, Chenxi Xu, Dongzhe Fan, Yuanfu Sun +1
Search agents extend large reasoning models with multi-round access to external knowledge, yet most existing systems largely conflate retrieving evidence with consuming it. Retrieved documents are commonly incorporated according to fixed or rank-based policies, despite the fact that evidence utility is conditioned on the agent's current reasoning state. Consequently, a lower-ranked candidate may be critical for the current step, while a higher-ranked candidate may provide redundant, irrelevant, or misleading information. We formulate this overlooked problem as evidence admission, which asks, at each search step, which retrieved candidates should be allowed to enter the agent's evolving reasoning context. To enable such selective control, we introduce SEEDS (Selective Evidence Entry During Search), a preview-guided evidence admission framework for search agents. SEEDS first exposes lightweight previews of retrieved candidates and then lets the agent jointly determine which candidates and how many should be fully inspected, conditioned on its current reasoning state. Unlike fixed or adaptive prefix policies, SEEDS can select arbitrary subsets with flexible cardinality, and it can be instantiated directly with an existing reasoning agent or further optimized through learning. Across nine knowledge-intensive QA benchmarks under both local corpus and live web search, SEEDS consistently improves search effectiveness while substantially reducing full-evidence consumption. Experimental analyses show that SEEDS more effectively selects useful candidates beyond the corresponding retrieval prefix. These results establish evidence admission as a complementary dimension of agentic search, separating what information is retrieved from what information is ultimately allowed to shape reasoning.
agentagenticbenchmark - arxiv:2610.12927 · cs.AICollaborative Learning and Reasoning over Model SlicesYuheng Wang, Runde Yang, Zhuohan Bao, Qiran Zhang +8
Large language models (LLMs) excel across diverse tasks, benefiting from knowledge priors, in-context reasoning, and test-time computation. Despite these strengths, single-model reasoning remains vulnerable to error propagation, as later steps depend on the model's earlier outputs, leaving reasoning blind spots difficult to independently reassess. To address this limitation, we develop \textit{collaborative learning}, encompassing the construction of heterogeneous collaborators and the learning of effective cross-model collaboration. Specifically, \textit{model slicing} replaces a large model with smaller, heterogeneous models under a comparable parameter budget, enabling prior reasoning to be reassessed across distinct model parameterizations. \textit{Pyramid supervision} combines protocol distillation with step-level supervision to refine reasoning and interaction decisions throughout collaboration. We evaluate our approach across four task categories: multi-hop question answering, mathematical reasoning, code generation, and open-ended constrained generation. The trained heterogeneous models achieve comparable or better task performance than the original large model and established multi-agent baselines, including reinforcement-learning-based methods, while also achieving higher inference efficiency than the multi-agent baselines and exhibiting differentiated collaboration patterns across tasks. These findings show that learned collaboration turns model heterogeneity into complementary reasoning capabilities.
multi-agent - arxiv:2610.12915 · cs.LGControlled-Minimax: Stabilizing Adversarial Optimization via Control TheoryTianjiao Luo, Jianfei Chen, Jun Zhu
Minimax optimization is fundamental to adversarial learning yet suffers from severe stability challenges, often manifesting as persistent limit cycles or divergence. This paper investigates these instabilities through the lens of continuous-time dynamical systems. By modeling training dynamics as a second-order Ordinary Differential Equation (ODE), we rigorously identify the root cause of non-convergence: the problematic eigenstructure of the loss function's Hessian near equilibrium points. To address this, we introduce Controlled-Minimax, a novel stabilization framework that reformulates the optimization trajectory as a controllable physical system. Unlike heuristic regularization techniques, our approach derives a specific feedback controller that provides theoretical guarantees of local exponential stability, regardless of the underlying Hessian spectrum. Consequently, our method stabilizes general minimax problems where traditional gradient descent-ascent methods fail. Extensive experiments on pathological benchmarks including the Dirac-GAN, 2D Gaussian mixtures, and Swiss Roll datasets, as well as high-resolution image synthesis with StyleGAN2-ada, demonstrate that Controlled-Minimax effectively suppresses oscillatory behavior while ensuring fast and robust convergence.
benchmark - arxiv:2610.12914 · cs.AIOGPO: Offline Goal-conditioned Policy Optimization for Recoverable Vision-Language-Action ModelsXule Gao, Xi Wang, Zehua Zang, Rui Wang +2
Vision-language-action (VLA) models have shown strong promise in robotic manipulation, yet their post-training still predominantly relies on trajectory-level supervised imitation over robot demonstrations. While effective for learning feasible actions, this paradigm supervises policies to reproduce expert actions at each step, biasing them toward demonstration-specific action paths and providing limited guidance for recovering toward task-progress states once execution deviates from demonstrated trajectories. To address this limitation, we propose OGPO, an Offline Goal-conditioned Policy Optimization framework for recoverable VLA post-training. Instead of treating offline demonstrations merely as step-wise action labels, OGPO adaptively relabels trajectories with semantic key states and constructs goal-conditioned process rewards to optimize the policy for reaching these task-progress states. In this way, OGPO shifts VLA post-training from trajectory-level action imitation to key-state reachability learning, enabling policies to acquire a more robust ability to complete goal states from feasible off-demonstration states without requiring additional online interaction. Experiments on LIBERO and MetaWorld show that OGPO consistently improves VLA policy performance over standard supervised fine-tuning. Moreover, evaluations on LIBERO-Plus and our proposed LIBERO-ReAct, a mid-execution perturbation benchmark, further demonstrate that OGPO achieves stronger robustness and goal-directed recoverability under distribution shifts and recoverable off-demonstration states.
vision-language-actionvlavla policymanipulationliberopost-training - arxiv:2610.12910 · cs.ROSampling-based Kinodynamic Planning with World ModelsYitian Gao, Hanlan Yang, Zachary Kingston
Visual world models predict the consequences of actions from images, but planning with them is typically done by optimizers such as CEM and MPPI. However, these optimizers stall on long-horizon tasks where progress requires motion the objective does not reward, such as moving around a block before pushing it. This paper revisits kinodynamic sampling-based motion planning for world models, using the learned model as the propagator of a tree search in latent space. Our key insight is that the sampling strategies devised for high-dimensional search in configuration space apply directly to the latent space of a world model, where they rapidly expand through intermediate states that myopic optimizers never sample. We present two exploration strategies for the high-dimensional latent space, nearest-neighbor-guided RRT and projection-based KPIECE, with GPU-native batched expansion for efficient device utilization. We evaluate with an off-the-shelf DINO-WM on four simulated domains and a real-world block-pushing task. Our approaches match or exceed the success rate of CEM and MPPI at up to 13.8x lower planning time in simulation, and improve the success rate by 20% on the real robot.
world model - arxiv:2610.12904 · cs.LGGIST: Generator-state-Informed Supervision for Tabular Foundation ModelsZhangyang Peng, Jingze Shi, Tongyi Zhang, Yuyu Luo
Tabular foundation models (TFMs) based on prior-data fitted networks typically use sampled hard query labels, leaving avoidable sampling variability in pretraining. A key observation is that intermediate generator states can reveal label uncertainty beyond a sampled outcome. We propose Generator-state-Informed Supervision for TFMs (GIST), which uses these states to average query losses over conditional label distributions. GIST jointly designs task generation and query supervision, using entropy-calibrated encodings to obtain tractable, input-consistent targets on supported label-dependent branches. We show that this averaging preserves the population objective and yields no larger gradient covariance at fixed parameters within each generating distribution. Under matched pretraining schedules, GIST improves mean rank across three architectures on both TabArena and TALENT without changing architecture or inference. Across these benchmarks and architectures, GIST wins 62.1% of paired dataset-level comparisons against the corresponding hard-label controls.
benchmark - arxiv:2610.12901 · cs.CVJMT-YOLO: Multi-task Domain Adaptation via Segmentation-Guided Consistency LearningZhenhua Yu, Jiahao Zhang, Wenchao Zhang, Ou Ye +1
Domain adaptive object detection (DAOD) aims to reduce performance degradation due to distribution shifts between training (source) and testing (target) datasets. However, owing to insufficient modeling of fine-grained features and limited instance-level alignment, existing approaches become less effective under complex environmental conditions, such as extreme weather conditions and object occlusion. We overcome these challenges by proposing JMT-YOLO, a novel joint multi-task learning framework for DAOD. JMT-YOLO is based on the Mean Teacher architecture. It introduces an auxiliary semantic segmentation task and a masking mechanism to enhance the modeling of foreground-background semantic boundaries in the target domain. Specifically, fine-grained feature degradation is reduced by introducing a multiscale context-aware segmentation head equipped with a dense connection structure to effectively capture local and global contextual features. A mask-consistency loss is formulated by applying random masking operations to target images, thereby guiding the network to learn structural context and improving instance-level feature alignment. Extensive experiments on three benchmark domain adaptation tasks (Pascal VOC to Clipart1k, Cityscapes to Foggy Cityscapes, and KITTI to Cityscapes) demonstrate that JMT-YOLO achieves detection performances of 46.9%, 57.3%, and 61.0%, respectively. These results demonstrate superior performance over existing state-of-the-art and baseline methods, thereby validating the effectiveness and generalization of JMT-YOLO.
benchmark - arxiv:2610.12895 · cs.CVMeshBind: Point-to-Mesh Binding for Non-Rigid Scene Flow Automatic AnnotationYinqi Chen, E Li, Shuaijun Wang, Weiyuan Peng +2
Scene flow estimation is essential for many autonomous driving (AD) and robotic applications, but obtaining ground-truth scene flow for non-rigid objects such as pedestrians is highly difficult. We present MeshBind, an automatic annotation method that uses mesh models to generate per-point scene flow for non-rigid objects. The novelty of this work is threefold: 1) developing a multi-view module that reconstructs an articulated mesh model from six surround cameras and registers it to the LiDAR frame; 2) developing a local-frame binding technique that attaches each point to the mesh via a per-triangle tangent-normal frame, invariant under rigid motion yet adaptive to articulated deformation; 3) developing a three-layer flow registration pipeline that combines ego-vehicle motion compensation, box binding, and mesh binding to produce full-scene per-point flow. We implement MeshBind in SF-Studio, an interactive annotation tool that visualises flow and allows human mesh corrections with automatic recomputation. We also release SFB (SUScape-Flow Benchmark), a large-scale benchmark built on the public SUScape dataset, covering 41k frames with per-point non-rigid pedestrian annotations and a Rigid/Semi-Rigid/Non-Rigid evaluation protocol. Experiments show that fine-tuning on SFB reduces three-way endpoint error (EPE) by 2-3x, and brings non-rigid EPE to the same level as rigid EPE.
benchmarkevaluation protocol - arxiv:2610.12886 · cs.ROLeapBot-JAC: Joint Action Chains for World Action ModelsChenhao Zhu, Baibing Liu, Pei Liu, Rui Yang +4
Action-chunking policies predict future controls but execute only a prefix before replanning. How should a fixed action-token budget be organized to support execution? We propose LeapBot-JAC, which allocates sparse future-control references and dense execution targets within one shared action expert. Both chains are supervised by demonstrated controls and jointly denoised at aligned physical-time positions. Directed attention allows execution tokens to read reference tokens subject to the host's visibility constraints. JAC adds neither action tokens nor parameters and retains the host's world-modeling process; both chains participate in inference, while only the execution chain drives the robot. On LIBERO, JAC reaches 98.3% success with FastWAM and LeapBot-WA, up from 97.0% and 97.3%. On zero-shot LIBERO-Plus, their success rates improve from 53.5% to 70.4% and from 73.1% to 77.3%, respectively. RoboTwin and two real-world tasks provide additional deployment evaluations. Single-training-seed comparisons and FastWAM ablations support action-role organization as a practical design choice under a fixed action-token budget.
liberorobotwin - arxiv:2610.12884 · cs.LGCoGameReg: Cooperative-Game-Based Collaborative Semi-Supervised Regression for Seismic Reservoir Property PredictionZhiyu Guo, Jiwei Jia, Lei Li
Accurate estimation of reservoir properties from seismic data remains challenging when well-log labels are sparse but three-dimensional seismic observations are abundant. We present CoGameReg, a cooperative-game-based semi-supervised regression framework that uses contribution-weighted predictions of heterogeneous regressors to construct shared pseudo-labels. This design makes each regressor's influence explicit in the learning targets generated for unlabeled seismic samples under sparse well control. The Tri-Game Shapley mechanism combines a rank-MSE performance game with a pairwise consistency game to estimate nonnegative regressor weights from labeled training data. These weights remain fixed during collaborative training and are reused for final prediction fusion. Candidate pseudo-labels are screened using a common local k-nearest-neighbor error-reduction criterion before retraining. We evaluate CoGameReg on 10 public regression datasets, a synthetic three-dimensional P-wave velocity prediction task, and a field water-saturation application. The benchmark advantage is most pronounced at the 2.5% labeled-data ratio and decreases as supervision increases. CoGameReg obtains the best blind-well metrics in the synthetic experiment. In the field application, predictions clipped to 0-100% yield a pooled coefficient of determination of 0.5942, a root mean square error of 5.7441 percentage points, and a Pearson correlation of 0.8265 across three blind wells. CoGameReg has the highest Pearson correlation among the four field methods. The results support the use of CoGameReg to integrate sparse well labels with dense seismic attributes, with performance varying across metrics and well locations.
benchmark - arxiv:2610.12883 · cs.LGHART: Hybrid Attention-RWKV Time series Foundation ModelQingwen Lin, Boyan Xu, Shifeng Xie, Zhifeng Hao +2
Non-autoregressive multi-step forecasting (NAF) enables time series foundation models to predict an entire future horizon in a single forward pass. Despite its strong sequence modeling capabilities, RWKV-7 exhibits long-horizon degradation in our NAF experiments. In this setup, future patches are represented as missing inputs, requiring the recurrent state to evolve across the prediction horizon without new observations. Our analysis of RWKV-7's generalized delta rule suggests a mechanism we term Placeholder Idling Decay (PID): repeated state transitions can attenuate historical information when placeholder-driven writes provide insufficient compensation. Layer-wise analysis reveals reduced state-injection norms in most layers, while transition-matrix norms remain similar between historical and prediction regions, consistent with PID. Motivated by this analysis, we propose HART, a Hybrid Attention-RWKV Time-series Foundation Model that alternates attention and RWKV blocks, combining direct access to historical tokens with recurrent temporal modeling. Controlled experiments on GIFT-Eval and TIME-Benchmark show that HART improves over pure RWKV at medium and long horizons while maintaining comparable short-horizon performance, and achieves better aggregate performance than a comparably sized pure Transformer. With 36M parameters, HART achieves long-horizon MASE comparable to Toto-2.0-1B on GIFT-Eval (0.752 vs. 0.754), using approximately 1/28 of its parameters.
benchmark - arxiv:2610.12881 · cs.AIMind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial EditingZheng Ren, Yanning Wang, Ziheng Huang, Fei Huang +3
Understanding and manipulating spatial relations is fundamental to AI systems that reason about physical environments and construct grounded world models. However, existing evaluations of multimodal large language models (MLLMs) for spatial reasoning rely predominantly on static question-answering (QA) over small-scale or synthetic scenes, rarely probing whether models can modify spatial configurations while satisfying explicit geometric constraints. We introduce GeoSpatialBench, a benchmark designed to evaluate an escalating progression of spatial cognition, ranging from spatial relation understanding and geometric reasoning to constrained spatial editing. Grounded in real-world urban data across six geographically diverse cities, GeoSpatialBench evaluates a comprehensive taxonomy of 28 topological, directional, metric, and ordering relations across structured GeoJSON and map image modalities, with ground-truth references and constraints verified via GIS operations. Our empirical evaluation across frontier MLLMs uncovers a stark spatial gap: structured GeoJSON consistently outperforms map images, with multimodal combinations offering no reliable gain over GeoJSON alone, and while models show reasonable competence on qualitative topological and ordering, performance drops on quantitative metric relations. Crucially, editing performance on ordering relations declines relative to QA, and most failed edits violate at least one specified spatial constraint. These results highlight a gap between passively recognizing spatial relations and actively manipulating geometric configurations. GeoSpatialBench provides an open, rigorous diagnostic testbed to benchmark these spatial limitations, laying essential empirical groundwork for physically grounded world models and embodied spatial AI.
embodiedworld modelbenchmark - arxiv:2610.12877 · cs.ROTAME-Nav: Temporal Asymmetric Mixture-of-Experts Distillation for Agile and Versatile Robot NavigationLingjie Zhang, Jun Xue, Shanze Wang, Haoyu Xi +3
Agile and reliable navigation is a core capability for embodied robots navigating complex spatial constraints and dynamic interactions. However, a single policy often struggles to accommodate the distinct decision-making demands of diverse scenarios. We present TAME-Nav, an asymmetric Teacher-Student navigation framework built around a temporal soft mixture of experts (Soft-MoE). The Teacher combines clean observations with causally maintained dynamic-obstacle tracks to construct privileged representations, while the Student learns complementary navigation features from corrupted observation histories through temporal encoding, soft expert routing, and latent distillation. Procedural scenario generation and parallel task-level simulation broaden training coverage, while deployment-informed asymmetric domain randomization supports sim-to-real transfer. Across in-distribution and unseen compositional scenarios, TAME-Nav achieves higher success rates, lower collision rates, and higher navigation scores than representative baselines. On a real quadruped robot, it completes all twenty trials across local-trap escape and narrow-passage navigation with sudden dynamic obstacles, with only one minor contact.
embodiedquadrupedsim-to-real - arxiv:2610.12876 · cs.LGWhen Solvers Get Moody: Quantifying and Predicting Performance Variability in Mixed Integer ProgrammingMourchid Adegbindin, Brenda Dietrich, Jamol Pender, Andrea Lodi
Mixed-integer programming (MIP) solvers are widely used, yet their performance can vary substantially even under seemingly neutral perturbations. Such variability complicates benchmarking, and the interpretation of computational studies. We introduce the Weighted Variability Score (WVS), a robust multi-component metric that aggregates dispersion in normalized runtime, final optimality gap, LP iterations, and branch-and-bound nodes across repeated runs. On a large subset of MIPLIB 2017 instances, each solved in 100 randomized runs under a four-hour limit, WVS reveals a right-skewed distribution with a substantial upper tail: many instances are essentially stable, but some exhibit large variability that is not explained by basic properties alone. Notably, this experiment proved optimality for the open instance 'neos-5045105-creuse' in two SCIP runs. Using static descriptors and root-level features, a tree-based predictor with a gated tail uplift achieves a mean absolute error of 0.058 and Spearman rank correlation of 0.65 on a sealed test split. Feature-importance analysis highlights root degeneracy, matrix structure, coefficient ranges, and presolve reductions as the main drivers of high WVS. Because variability is systematic and partially predictable from inexpensive early-run features, our findings offer a practical tool for preemptive tuning and lay a foundation for fairer evaluation of new algorithms.
benchmark - arxiv:2610.12874 · cs.CLTemporal Evidence Forests for Long-Horizon Multi-Party Conversational MemoryJunyou Guo, Chongyang Tao, Yan He, Yong Wang +1
Long-term memory has been widely adopted in LLM-based agents to support persistent interaction and personalized assistance. Long-term multi-party interactions, however, accumulate substantially more detailed information, with decisions repeatedly updated and states evolving across participants and interaction stages. Temporal structure is therefore crucial for tracing such memories: relevant information often appears densely within short intervals, while transitions among different states are anchored by a strict temporal order. Existing temporally aware memory frameworks primarily store time as metadata or use temporal signals to guide retrieval over preconstructed memory structures, without using temporal structure to both recover locally concentrated evidence and reconstruct its complete event progression. To address these limitations, we propose T-Mem, a temporal-structure-based memory framework that preserves interactions and organizes query-relevant evidence through two temporal mechanisms. Temporal Evidence Discovery exploits the local concentration of related messages to recover overlooked evidence, while Temporal Memory Structuring models state transitions and supporting relations over time and compresses low-information spans within the resulting forest. Evidence Forest Linearization then serializes the structured evidence for answer generation. Experiments on two long-term multi-party memory benchmarks demonstrate that T-Mem consistently outperforms competitive memory frameworks across LLMs, parameter settings, domains, and query types.
memorybenchmark - arxiv:2610.12870 · cs.AILocalized Generative Design of Ship Hulls with Diffusion Models and High-Fidelity AssessmentHadi Keramati, Mohammed A. Hannan, Patrick Kirchen, Sina Tousi +3
Practical ship design requires localized refinement and performance evaluation. This paper presents a reward-directed diffusion framework for localized hull optimization. Parametric masking during dataset generation restricts geometric changes to selected variables, including the bulbous bow and forebody, while preserving full-hull continuity. Surrogate-assisted sequential Monte Carlo sampling targets reduced predicted calm-water resistance, with stability retained through training data and displacement matched during screening. An automated viscous free-surface CFD pipeline, validated against measurements for two benchmark container ships, evaluates a generated variant and GenHull E, a hull refined by a naval architect within the same representation. At matched KRISO Container Ship (KCS) displacement, the generated variant has comparable total resistance at $F_n=0.195$ but 45-50% higher resistance at $F_n=0.250$ and $0.260$, missed by empirical screening. GenHull E achieves 6-8% lower total resistance up to $F_n=0.240$ but higher resistance above $F_n=0.250$ as opposing friction and pressure trends reverse the gains. Aggregating resistance across this crossover can conceal tradeoffs that emerge when friction and pressure components are evaluated separately. The assessment reveals an inability to represent a faired bulbous bow and a reward lacking viscous pressure and stability terms. These findings show how high-fidelity assessment informs improved representations and objectives for physically realizable generative designs.
benchmark - arxiv:2610.12866 · cs.CVCaptchaAgent: Verifiable Visual Reasoning for CAPTCHA SolvingShangquan Sun, Ruoyu Chen, Zhirui Liu, Xiang Liu +3
Modern reasoning CAPTCHAs require fine-grained perception, compositional relation reasoning, and grounded browser interaction. End-to-end vision-language model agents remain brittle in this setting because a missed object, incorrect count, or confused relation can propagate directly to the final action. To address this problem, we present CaptchaAgent, a structured visual reasoning framework for interactive CAPTCHA solving. Instead of predicting an action directly from a screenshot, CaptchaAgent first constructs a visual intermediate representation (V-IR) that explicitly records entities, attributes, and spatial or topological relations. A symbol-only ASCII protocol further requires the parser to commit to a concrete object set and count. Building on this global representation, localized evidence refinement revisits ambiguous regions at higher effective resolution, while counterfactual consistency verification tests whether the resulting action remains stable under task-preserving transformations. Across three proprietary backbones on Open CaptchaWorld, CaptchaAgent improves Pass@1 by 21.3-25.8 percentage points over a commercially available browser agent baseline evaluated with the same backbones. On the separate offline Oedipus-data benchmark, it further improves average Pass@1 by 9.2-12.3 percentage points over the Oedipus solver across three matched backbones. The intermediate traces show that exact counting, continuous geometry, and ordered execution remain major sources of automation difficulty for the evaluated agents, providing practical guidance for designing more resilient compositional CAPTCHAs.
agentbenchmark - arxiv:2610.12863 · cs.CLUnreliable Narrator Framing as a Cost-effective Mechanism for Satire Explanation of Australian and American Satirical NewsKanay Gupta, David Y. Liu, Aditya Joshi
Satirical news is a unique form of misinformation: it is intended to be humorous by the original publication source but can be misinterpreted. Explanation of satirical news articles is challenging because recent and local context needs to be incorporated. This is a pilot study that explores explanation generation for satirical news articles from Australia and compares them alongside those from USA. The paper demonstrates that framing explanations on unreliable narrator theory on open-weights models can be a feasible, cost-effective alternative to frontier models. We find that models identify the satirical tropes more accurately on the American source than the Australian one. This work results in a novel dataset and an evaluation benchmark for satirical explanation.
benchmark - arxiv:2610.12861 · cs.ROEvidence-Guided Counterfactual Learning for Long-Tailed Robotic PoliciesWeiwei Chen, Chenghao Xu, Meiling Yu, Xu Yang +1
In the practical deployment of vision--language--action policies, handling long-tailed task distributions is a common challenge due to the highly imbalanced composition of robot demonstration datasets. To investigate this issue, we study the head-task action bias in shared robot policies, particularly focusing on its relationship with task-specific visual evidence. Our experimental analysis shows that, when the visual evidence required by a tail task is insufficient, the policy increasingly falls back on action patterns reinforced by data-rich head tasks, resulting in degraded performance on under-represented tasks. Motivated by this observation, we propose Evidence-Guided Counterfactual Learning, a training framework for long-tailed robot policies. Our method identifies decision-relevant visual evidence using instruction-related and action-related signals, and constructs counterfactual observations by removing the selected evidence. The resulting counterfactual predictions are used to strengthen the association among task instructions, visual evidence, and actions, with the supervision adaptively adjusted according to the number of demonstrations available for each task. The proposed framework requires neither additional training data nor region-level annotations and incurs no additional computation during deployment. Extensive experiments across simulated benchmarks, different VLA architectures, and real-world robot platforms demonstrate that our method robustly and consistently improves long-tailed robot policy learning, particularly for tail tasks, while maintaining reliable performance on head tasks.
vlarobot policybenchmark - arxiv:2610.12855 · cs.AIMitigating Capability Degradation in LLM Self-Improvement via Representation Geometry RegularizationJiaqi Tian, Ting Long
On-Policy Self-distillation is a self-improvement paradigm that enables large language models (LLMs) to improve their capabilities by leveraging the same model as both teacher and student under different conditioning contexts. However, we find that OPSD methods can progressively degrade previously acquired capabilities: queries that are correctly responded at earlier training stages may become incorrectly responded as optimization proceeds, even the overall performance continues to improve. Further analysis reveals that this degradation coincides with a deterioration of the geometry of hidden representations, characterized by reduced intra-cluster compactness and diminished inter-cluster separation. Motivated by this observation, we propose Representation Geometry Regularization (RGR), which preserves representation geometry during post-training by encouraging compactness within cluster and separation across cluster. RGR can be seamlessly integrated into existing OPSD methods without altering their core optimization procedures. Extensive experiments on multiple OPSD methods and benchmarks show that RGR generally alleviates capability degradation while retaining capability improvements. Our code is available in https://github.com/supermachinelearner/RGR.
self-improvementpost-trainingbenchmark - arxiv:2610.12849 · cs.AICo-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull RequestsMohammad Wathiq Soualhi, Basem Suleiman
Current software engineering agents are evaluated predominantly inside isolated sandboxes against synchronous local tests. However, deploying features in collaborative repositories requires modifying continuous integration (CI/CD) pipelines, containers, and provisioning manifests alongside application logic. Because agents lack deployment awareness, attempting cross-domain modifications introduces unverified dependencies into asynchronous integration pipelines. To isolate the causal integration overhead of dual-scope pull requests (PRs)-modifying both application code and deployment infrastructure-we evaluated 26,999 PRs across two large datasets (AIDev v5 and MOSAIC-3M) encompassing six agent architectures and an aligned human baseline. Using a deterministic four-tier file taxonomy and an exact 4D strata-matching framework, we isolated integration metrics under conditional exchangeability while controlling for application volume. We find agents operate primarily as application coders or chore workers, with maintenance tasks capturing 17.70% to 25.41% of agent PRs. Dual-scope modifications represent only 4.48% to 4.55% of agentic PRs, yet trigger bimodal integration outcomes. In the first mode, explicitly reviewed contributions experience protracted delays, adding a median penalty of +13.13 hours and multiplying time-to-merge by 3.24x, driven mechanically by CI/CD and provisioning manifests. In the second mode, maintainer gatekeeping exhibits a structural bypass: even for external contributors lacking repository write access, agent identity reduces the odds of human review by 63.7% compared to human peers. Consequently, 43.1% to 56.2% of dual-scope PRs bypass inspection to merge silently in a median of under 31 minutes. These uninspected modifications compromise build verification, demonstrating the need for deployment-aware benchmarks and strict path-based access controls.
agentai agentagenticbenchmark - arxiv:2610.12837 · cs.LGCOFFEQA: Counterfactual-Guided Few-Shot Distillation for LLM Question AnsweringKavinda Kehelella, Sanghamitra Dutta
Knowledge distillation aims to train a smaller student model to mimic a larger teacher model for resource-constrained environments. However, the process of distillation is typically data-intensive and computationally expensive, particularly for generative tasks. Few-shot distillation offers an alternative by transferring teacher knowledge using limited training samples. However, we observe that few-shot distillation performance is heavily dependent on the choice of these training samples. In fact, we demonstrate that using more uncertain samples near the teacher's decision boundary can significantly deteriorate distillation performance. Motivated by this observation, we propose Counterfactual-guided Few-shot Distillation in Open-book Question Answering (COFFEQA), a novel strategy that aptly uses counterfactuals to provide additional supervision around challenging factual samples. In the generative QA setting, we define a counterfactual as a minimally modified context that induces the teacher to change its response to an alternative answer. We provide geometric insights on how factual-counterfactual pairs can constrain the deviation between the teacher's and student's decision boundaries. We further introduce a new metric, Context Following Difficulty (CFD) that further validates counterfactuals prior to distillation based on agreement with the intended alternative answer and dependence on the modified context. COFFEQA uses CFD-validated factual-counterfactual pairs for few-shot distillation. Experiments across five in-domain and three out-of-domain QA benchmarks using T5 and Qwen2.5 families show that COFFEQA outperforms factual-only distillation baselines under the same few-shot budget. For instance, on TriviaQA, COFFEQA improves over the factual-only baseline by 8.77 average EM points and 9.98 average F1 points under the T5 setting with 32 few-shot pairs.
benchmark - arxiv:2610.12835 · cs.CVStructure-Aware Matching for Robust UAV Thermal-to-Satellite Geo-LocalizationChun Liu, Yuxin Wang, Zhenxiang Huo, Linlin Zhu +2
UAV thermal-to-satellite geo-localization localizes UAVs by matching real-time thermal images against georeferenced satellite images, enabling autonomous navigation in GNSS-denied and low-visibility conditions. However, substantial cross-modal disparities in color, brightness and viewpoint hinder conventional appearance-based methods from establishing reliable correspondences. While existing approaches predominantly address global modality shifts, they overlook the invariant scene structures inherently shared between thermal and satellite views. To bridge this gap, we propose SAMF, a Structure-Aware Matching Framework that explicitly exploits stable cross-modal structural cues to improve UAV thermal geolocalization. Specifically, the Directional Structure Enhancement Module (DSEM) strengthens robust structural representations by capturing directional and low-frequency spatial patterns, and the Modality-Aware Affine Remapping Module (MARM) subsequently applies affine correction to these enhanced features, further promoting cross-modal alignment. Additionally, we introduce the Thermal-UAV-Paired benchmark derived from the Thermal-UAV dataset. Extensive experiments on both the Boson-nighttime and Thermal-UAV-Paired datasets show that SAMF achieves state-of-the-art performance. Ablation studies further validate the effectiveness and synergistic complementarity of DSEM and MARM. The code and dataset are released at: https://github.com/YuxinWang879/SAMF.git.
benchmark - arxiv:2610.12832 · cs.ROVLMs are Native Action Models: Unleashing the Manipulation Capabilities of VLMs with Explicit Action-Space GroundingJingkun Yi, Shujie Zhang, Zirui Zhou, Haoxiao Wang +7
Pretrained vision-language models (VLMs) already exhibit strong visual, spatial and reasoning capabilities relevant to robotic manipulation. The key challenge in turning pretrained VLMs into generalist manipulation policies is to expose these capabilities through an appropriate action interface. Vision-language-action (VLA) models provide a unified trainable policy, but typically introduce learned action tokens, action heads, or action experts whose semantics must be learned from robot data pretraining. In contrast, modular foundation-model-based manipulation methods can exploit pretrained VLM capabilities for zero-shot manipulation, but rely on external planning and control scaffolds that are not end-to-end trainable as a unified continuous-action policy. In this work, we introduce EASG, an Explicit Action-Space Grounding framework that bridges these two paradigms. By projecting a tool center point (TCP)-centered action frame into the wrist camera observation and expressing actions in the form of VLM's native textual generation interface, EASG makes the semantics of a continuous robot action space directly observable in the VLM's perceptual context. This allows pretrained VLMs to directly generate executable robot actions using their existing visual-spatial reasoning capabilities, without robot-action pretraining or additional action modules. Besides, the same action interface supports direct fine-tuning with robot trajectories, allowing the models to continuously improve beyond their manipulation capabilities unleashed by EASG. Overall, EASG enables zero-shot manipulation and generalization across object positions, categories, and robot embodiments, while supporting effective fine-tuning in the same continuous action space. These results demonstrate that, given an appropriate action interface, pretrained VLMs can themselves serve as native action models for robotic manipulation.
vision-language-actionmanipulationaction head - arxiv:2610.12830 · cs.LGCross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression TargetDu Cheng, Junyu Lu, Jingfan Zhang, Yuzhuo Zhang +2
Reasoning post-training draws on offline demonstrations and policy-generated rollouts, yet conventional supervised fine-tuning (SFT) followed by reinforcement learning (RL) separates their objectives and limits continued reuse of collected responses. We propose \textbf{Cross-Behavior Policy Optimization} (CBPO), which makes these sources compatible with one regression loss through a fixed-reference target. Because the generating policy does not enter this target, positive and negative offline completions, reference responses, and current and historical rollouts can share a common reward-labeled record format and replay buffer. As new responses enter the buffer, optimization retains the same regression objective without coordinating separate SFT and RL objectives or requiring stored behavior-policy probabilities, importance weighting, or a learned critic. Restricting the available sources gives offline, on-policy, and off-policy variants, while CBPO-Unified combines them. Across two model scales and four mathematical reasoning benchmarks, CBPO delivers leading \texttt{avg@32} and \texttt{pass@32} performance across benchmarks and data regimes. On Qwen3-1.7B, CBPO-Unified improves benchmark-averaged \texttt{avg@32} and \texttt{pass@32} over SFT DAPO by 2.33 and 4.44 percentage points, respectively. In the replay ablation, retaining historical rollouts improves these metrics by 1.87 and 3.72 percentage points over the no-history configuration.
post-trainingbenchmark - arxiv:2610.12828 · cs.LGTreeHCA: Hindsight-Guided Exploration and Credit Assignment for Multi-Turn LLM AgentsDebajoy Mukherjee, Jeremy Carleton, Sushil Vemuri, Srinivas Shakkottai +1
Outcome-supervised group-relative policy optimization (GRPO) assigns the same advantage to every token in an LLM agent trajectory, leaving useful and unhelpful decisions undifferentiated. Hindsight credit assignment (HCA) can refine this feedback, but its estimates rely on trajectories containing informative alternatives at consequential histories. We introduce TreeHCA, which couples hindsight-guided exploration with hindsight credit assignment. TreeHCA uses changes in reference-answer likelihood to revisit intermediate histories and sample alternative continuations, forming a tree of reasoning and tool interactions. Because this exploration changes the distribution of sampled continuations, we derive the corresponding inverse-hindsight importance correction, including an exact finite-pool identity. We use this structure in a normalized tree backup that propagates terminal outcomes into turn-level advantages. This shared hindsight structure is TreeHCA's central design principle, linking informative exploration with hindsight-guided credit assignment. Across seven question-answering benchmarks and three Qwen backbones, TreeHCA outperforms all baselines in aggregate exact match, validating the effectiveness of paired exploration and credit assignment for multi-turn LLM agent training. Our code is available at github.com/TheBlackCat22/TreeHCA.
agentllm agentbenchmark - arxiv:2610.12823 · cs.CLWhen Charts Deceive Web Agents: A Paired Benchmark for Misleading Visualization-Grounded TasksYisheng Li, Dongming Han, Hongkun Pan, Bingcheng Mao +4
Web agents increasingly browse, interpret, and act on web content on behalf of users. In many realistic workflows, however, the visual evidence they consume is not neutral: charts and dashboards can be misleading, shaping judgments without issuing any explicit malicious instruction. Unlike chart question answering, Web Agents treat charts as intermediate evidence whose misinterpretation can propagate into concrete downstream actions --- a reliability risk that remains underexplored. We introduce MisVisAgentBench, the first paired executable benchmark for evaluating how misleading visualizations affect Web Agent execution. It comprises 280 task instances in matched clean--misleading pairs that differ only in chart evidence. We further provide a diagnostic framework that isolates misleading-induced failures from baseline task difficulty (Zhu et al., 2025) and captures execution-level effects such as extra browsing steps and decision hesitation. Across thirteen vision-language Web Agents, replacing clean charts with misleading counterparts reduces the average task success rate by more than 34 percentage points. Moreover, these failures predominantly follow the targeted misleading action branch, suggesting that deceptive charts systematically redirect rather than randomly disrupt agent decisions. These results reveal that visualization robustness is a critical yet understudied dimension of Web Agent safety and reliability.
agentbenchmark - arxiv:2610.12822 · cs.AIReward Hacking as a Transmissible Strategy in Multi-Agent Coding SystemsYuepeng Hu, Pegah Ghahremani, Reza Aghajani, Mahesh Pasupuleti +1
Multi-agent systems are increasingly used to solve coding tasks by coordinating agents that share code and plans. These agents are often optimized with reinforcement learning (RL) using automated evaluators, but bypassing evaluation can earn reward without producing a genuine solution. Prior work has largely treated reward hacking as a single-agent failure. In this work, we show that a reward-hacking strategy elicited in one agent can propagate to others and affect system coordination. Across four open-weight backbones, coding RL elicits and amplifies reward hacking in two settings: explicit mechanism descriptions in the system prompt and mid-training that models upstream exposure to facts about the coding environment. Using post-RL agents from the mid-training setting as sources, we observe propagation through code and shared memory, and across roles through natural-language plans. Even agents based on small open-weight models induce reward hacking in stronger closed-weight targets. On hard tasks, propagation can intensify along a transmission chain after the original source leaves as the code acquires more persuasive justifications. We also theoretically analyze conditions under which reward hacking amplifies, persists, or decays across agent interactions. Beyond propagation, reward hacking can bias task routing toward reward-hacking agents and survive candidate aggregation. As potential mitigations, we evaluate code review by the coder or a separate verifier, both of which reduce delivered hacks. Together, these results establish reward hacking as a transmissible strategy whose effects extend beyond the agent in which it first emerges.
agentmulti-agentagent systemevaluator - arxiv:2610.12820 · cs.LGInverse Synthesis of Shock Time Series from Shock Response Spectra Using Ensembles of Conditional Variational AutoencodersAdam Watts, Charles Young, Ryan Bowering, Andrew Jeon +1
The shock response spectrum (SRS) characterizes the peak responses of single-degree-of-freedom systems to transient acceleration. Because the mapping from an acceleration time series (waveform) to its SRS is many-to-one, inverse synthesis seeks candidate waveforms consistent with a prescribed spectrum. We extend an earlier conditional variational autoencoder (CVAE) framework with a recurrent decoder that predicts multiscale wavelet coefficients and reconstructs waveforms through an inverse discrete wavelet transform. Individual models exhibit limited variability under latent sampling, motivating an ensemble of independently trained models spanning different mother wavelets and decomposition levels. Each member produces a separate candidate waveform for the same target SRS. Evaluation on four held-out benchmark datasets shows lower mean and median spectral errors for the illustrated wavelet model than for the earlier direct time-domain CVAE and a sum-of-decayed-sinusoids (SDS) baseline. A conditioning study examines frequency-grid and encoding choices. Comparisons with published inverse-SRS methods demonstrate superior performance across four holdout benchmark datasets (two operational shock datasets, one earthquake dataset, and one synthetic shock dataset) and competitive performance on synthetic targets reported by Brake. Single-model inference requires approximately 0.1-0.6 ms per waveform during batched inference compared with 5-8 s for SDS, excluding offline training. This low inference cost enables rapid generation of distinct SRS-compatible candidate waveforms across the ensemble, although their physical suitability requires assessment beyond spectral agreement.
benchmark - arxiv:2610.12818 · cs.ROLeWAM: End-to-End World and Action Modeling with JEPAsMinghao Fu, Tavis Siebert, Eryk Halicki, Randall Balestriero
Joint-embedding predictive architectures (JEPAs) learn compact latent world models without pixel reconstruction. Existing JEPA pipelines typically train visual representations and action-conditioned dynamics before adding a control policy or solver. We introduce LeWAM, an end-to-end JEPA for control with: (1) a joint training objective over next latent state prediction and action flow matching, and (2) an isotropic Gaussian constraint on the latent state, enabling a single model to support direct policy execution and efficient planning by evaluating sampled actions with its learned latent dynamics. Compared with prior JEPAs in visual planning, LeWAM improves success rate from 28.6% to 89.7% on contact-rich tasks and from 10.9% to 46.2% on long-horizon tasks, and plans 32.3 times faster. On behavior cloning tasks in simulation and physical robots, LeWAM is also competitive with established methods. Interpretability analyses show that LeWAM learns control-relevant representations and action distributions effectively guiding test-time planning and control.
world modelaction-conditionedlatent dynamics - arxiv:2610.12813 · cs.LGVEPA: Verified Evolving Formal Policy for Lifelong LLM Agent GuardrailsDuy Nguyen, Lesly Miculicich, Bhavana Dalvi Mishra, Shuo Li +4
LLM agents increasingly operate over sensitive resources, such as private documents and mutable system states, which can create serious safety and security risks. Runtime guardrails should therefore make inspectable, reproducible, and deterministic allow or refuse decisions before potentially irreversible agent actions are executed. However, safety and security requirements are rarely complete before deployment, so guardrails need to keep adapting as new risks emerge. Existing adaptive guardrails learn from deployment experience, but they usually apply safety policies through LLM inference, which can lead to inconsistent decisions and ambiguous policy interpretations. Formal guardrails, on the other hand, enforce policies deterministically, but they usually rely on pre-deployment or task-specific policies and have no mechanism to adapt to newly observed risks. We introduce VEPA, a framework for the verified evolution of formal agent guardrails. VEPA represents the guardrail as a formal policy of executable symbolic rules over typed agent events. During deployment, we use an LLM guided by deployment feedback to propose policy patches that fix newly observed failures while preserving previously correct behavior. Then, a deterministic verifier only accepts policies that are structurally valid and conflict-free. Finally, an evidence-aware authority layer activates a verified rule only when it has enough supporting evidence, so uncertain updates cannot directly affect guardrail decisions. Across ASSEBench-Safety, ASSEBench-Security, and ATBench, VEPA consistently outperforms baselines while expanding the scope of deterministic formal-policy enforcement. These gains also hold under more challenging deployment conditions, including mixed streams, corrupted feedback, and longer horizons.
agentllm agent - arxiv:2610.12807 · physics.opticsPhantom Zernike Wavefront Sensor: Phase Contrast with Engineered Focal Plane Reference SpecklesBenjamin Courtney-Barrer
We introduce the Phantom Zernike Wavefront Sensor (phantom ZWFS), an engineered reference extension of phase-contrast wavefront sensing in which controlled pupil plane modulation generates off-axis coherent speckle structures that undergo localized focal plane phase shifts. These references may replace the central ZWFS reference when the on-axis PSF core is required for another optical function, such as photonic science coupling, or may augment a conventional central ZWFS response to provide additional wavefront information. Using a monochromatic scalar model, we derive the resulting carrier structure and show how the engineered references can be recovered through spatial demodulation and incorporated into calibrated reconstruction. A simple four-reference realization demonstrates that the reference geometry redistributes photon sensitivity across spatial frequency magnitude and orientation, producing mode dependent changes in linearity and cross-talk rather than a uniform improvement over a classical ZWFS. We then consider differential piston on a seven segment aperture as an application specific example. A hybrid sensor retaining the central ZWFS phase region and adding six engineered references that match the segment geometry gives similar precision near the phased state but substantially improved performance at larger piston excursions. Under the adopted photon-noise-limited benchmark, the hybrid reduces the nonlinear reconstruction error and provides better conditioned optical encoding of the piston state than an idealized vector ZWFS, allowing more precise piston estimation from the same detected photon flux at larger piston excursions.
benchmark - arxiv:2610.12806 · cs.LGTrainable Quantum-Native Language Models: Dissipative Memory, Capacity Limits, and Hardware ValidationDeniz Yunus Göğüş
We study byte-level autoregressive language models whose hidden state is a small quantum register, whose transitions are learned token-conditioned quantum channels, and whose next-byte probabilities come directly from Born-rule measurements without a learned classical vocabulary projection or softmax. In the fixed-width recurrent setting, unitary dynamics cannot contract or reset stored distinctions; experimentally, unitary recurrence loses to its retrained one-token control in every tested variant. Introducing learned dissipation, then token-conditioned dissipative gating, yields useful memory beyond one token. The gated model improves test negative log-likelihood by 0.20 +/- 0.03 nats/byte over retrained parameter-matched one-token controls at context length 12, and by 0.29-0.33 at longer contexts, but never beats retrained two-token controls. A key-value recall benchmark shows a width-dependent threshold: one stored pair meets the pre-registered accuracy bar at 4-5 memory qubits, two pairs at 6-7, and three pairs remain unsolved. This is consistent with, but does not establish, a capacity explanation for the short effective memory horizon. As a secondary result, one-qubit models reach lower stationary memory entropy than a heuristically optimized classical predictive frontier at matched error in 9/9 seeds. On IBM Heron hardware, computational-basis memory-register distributions show signal against a uniform null in 12/12 circuits across prefixes of up to 12 tokens, next-bit probabilities pass pre-registered accuracy bars at four-token prefixes, and bytes are generated autoregressively by sampling physically measured bit probabilities. The tested models are classically simulable and substantially worse than classical n-gram baselines. We claim no computational quantum advantage.
memorybenchmark - arxiv:2610.12794 · cs.LGMeta-Reflective Evolution Effectively Improves Production AI SystemsSeung Won Wilson Yoo, Chang Zeng, Aditi Somayajula, Sahithi Ankireddy +6
Large Language Model (LLM)-guided evolutionary optimization has successfully improved prompts, programs, and even entire AI systems. Most optimization methods select a candidate from the search frontier, then mutate it in one LLM pass based only on its failures. This focus on the frontier can stall on production AI systems, where isolated failures reveal little about complex, hidden interactions. We introduce CoCoEvolve (Cortex Code Evolve), an evolutionary optimizer built around what we call meta-reflection, wherein an agentic mutator (Cortex Code) selectively retrieves evidence from the entire evolutionary history and probes the live system before verifying and proposing mutations. We apply CoCoEvolve to optimize three classes of production AI systems: data agents, LLM-powered data pipelines, and data engineering workflows. On DABStep, CoCoEvolve tops the public leaderboard, reaching 92.8% held-out hard accuracy compared to 78.4% for Meta-Harness and 30.4% for GEPA under matched conditions. Across six LLM data pipeline workloads, it outperforms every evaluated baseline. On data-eng-bench, CoCoEvolve lifts test-set solve rate from 59.1% to 77.4%, past the best baseline of 73.6%. It also has 11 percentage points higher accuracy than GEPA on HotpotQA while remaining competitive with specialized optimizers on established mathematical and systems benchmarks. Matched ablations confirm that each component of CoCoEvolve contributes to these gains, demonstrating the value of meta-reflection for optimizing production AI systems.
agenticbenchmarkleaderboard - arxiv:2610.12793 · cs.ROGamma: Grounded Multi-Agent Memory with Mechanical Audit for Memory-Intensive ManipulationYudong Liu, Yueqian Lin, Zijia Tang, Yuxi Zheng +10
Pretrained vision-language-action (VLA) policies fail on memory tasks, behaviour that depends on events observed long before the current frame, because their training data is overwhelmingly Markov and mapping episodic memory directly to action chunks is hard. Yet the same policy, finetuned once to follow a privileged oracle's grounded-subgoal text, nearly solves these tasks: the difficulty lies entirely in mapping memory to a grounded symbolic subgoal. Existing work entrusts this stage to a single VLM that selects keyframes and reasons over raw frames, and falls far short of the oracle: key identities and dynamics are buried in noisy pixels, the reasoning spans hundreds of frames in an unbounded context, and hallucination corrupts the memory itself. We instead present GAMMA (Grounded multi-Agent Memory with Mechanical Audit), which builds the stage as a collaborating two-agent memory system: a detector tool (SAM-3) for spatial grounding, a VLM writer that distils each replan window into one grounded text line, an append-only text memory bank, and a VLM reasoner that reads the bank and emits the next grounded subgoal at the oracle's cadence, wrapped in a propose-verify harness that admits, defers, corrects, or rejects every agent claim against mechanical visual evidence, at training-corpus construction and at deployment alike. On a sixteen-task memory-manipulation suite GAMMA recovers a large fraction of the oracle ceiling with the policy held fixed, reaching the ceiling on several tasks, and transfers with unchanged contracts to a second benchmark.
vision-language-actionmanipulationmemoryepisodic memoryagent memoryagent - arxiv:2610.12792 · cs.CLLarge Language Models, Machine-Assisted Cultural Analytics, and the Agentic TurnAndres Karjus
Technologies like large language models make it easier to convert cultural material into analyzable variables, while LLM-driven agentic systems extend machine assistance to other parts of the research workflow. Rather than a full how-to guide or an exhaustive review of recent LLM use cases, this chapter looks at some crucial aspects of this new paradigm as well as the bigger picture. I argue that these technologies expand the scale, methodological range, and scope for delegation, while the basic logic by which those measurements support cultural claims remains mostly unchanged.
agentic - arxiv:2610.12790 · cs.ROTactile Sensing-based Secure and Gentle Grasping of Unknown ObjectsFeng Han
Reliable robotic manipulation requires maintaining a firm grasp while strictly avoiding both contact slip and structural damage to the object. Satisfying these inherent \textit{secure-and-gentle} grasping constraints is challenging for unknown objects. We present a novel online data-driven predictive control framework for safe dynamic robotic grasping of unknown objects. The proposed system features a pair of compact, single-channel tactile-sensing modules that characterize the gripper-object dynamic interaction in real time, entirely bypassing the need for prior knowledge or offline training. A finite-state-machine-based grasping force probing mechanism is developed to establish the initial grasping force and explicitly identify grasping force constraints. Through online dynamics learning, a Gaussian Process (GP) model captures gripper-object interaction dynamics. The model uncertainties are further used to form robust grasping constraints, which are embedded into a model predictive control scheme. We demonstrate error convergence in a probabilistic sense. The proposed control framework runs at 100~Hz in real time to dynamically manipulate and handle objects rather than static holding. Extensive experimental evaluations across diverse contact surface topologies and various types of objects validate superior performance and efficiency compared to baseline strategies. The proposed method is able to manipulate objects ranging from delicate items, such as raw tofu and marshmallows, to rough objects, such as rocks.
manipulationtactilegrippergrasp - arxiv:2610.12789 · cs.AIEvoBelief: Falsifiable World Models for Self-Improving LLM AgentsJanet Wang, Jiang Guo, Yi Xiang, Jiaqing Yuan +5
Self-evolving LLM agents typically improve how they act through accumulated experience, reflection, or skills. Yet even procedurally capable agents can fail when their beliefs about environment dynamics are incomplete, incorrect, or outdated. We study a complementary axis of self-evolution: evolving those beliefs during deployment. Such beliefs can support multiple tasks, but incorrect ones can also propagate across them. We introduce EvoBelief, a self-evolving world model that represents environment knowledge as falsifiable hypotheses. Unexpected outcomes and decision-relevant unknowns trigger hypothesis formation. Later observations and controlled experiments provide independent validation before a rule can guide predictions or plans within its supported scope. Counterexamples narrow or retire rules as the environment changes. The language model remains frozen, and each rule remains linked to its evidence and the decisions it changes. Across four benchmarks spanning static dynamics, hidden drift, and scientific discovery, EvoBelief improves task performance and reuses learned rules across tasks. On ALFWorld without actor-side transition memory, it improves success over the matched Frozen World Model by 23.9% and 31.3% with Claude Haiku 4.5 and GPT-5.4, respectively. On MiniGrid, it revises stale rules and recovers after unannounced dynamics changes. In DiscoveryWorld's Reactor Lab, it discovers and validates quantitative laws, completing 83.3% of Normal-tier and 58.3% of Challenge-tier instances, versus 0% for each evaluated baseline. These results demonstrate self-improvement through testable, revisable environment knowledge rather than model-parameter updates.
world modelllm agentself-improvingself-improvementself-evolvingbenchmark - arxiv:2610.12783 · cs.CVShift-Aware Identity-Guided Latent Refinement for Referring Audio--Visual SegmentationKun Li, Sami Sebastian Brandt, Michael Ying Yang
Referring Audio--Visual Segmentation (Ref-AVS) is an emergent multimodal task requiring the precise identification and segmentation of a specific object based on a natural language expression grounded in both visual and auditory cues. Unlike traditional AVS, which segments generic sound sources, or referring video object segmentation (Ref-VOS), which relies solely on visual--textual grounding, Ref-AVS necessitates fine-grained tri-modal interaction across vision, audio, and language. However, existing methods often fail to maintain consistency when subjected to target shift, a phenomenon where the model erroneously transfers its focus between objects due to transient occlusions, acoustic fading, or identity ambiguities. To address this, we propose a novel Shift-Aware Identity-guided Latent (SAIL) refinement framework. It introduces a dual-token strategy that decouples frame-level dynamics from a global semantic anchor to explicitly model target-shift cues. We design a shift-aware refinement module that rectifies drift by aligning tokens with domain-specific evidence. Finally, we leverage a decoder that integrates the refined embeddings with a continuous memory update to maintain spatio-temporal coherence and identity consistency throughout the video sequence. Extensive experiments conducted on two Ref-AVS benchmarks demonstrate the effectiveness of our proposed method, significantly outperforming existing AVS, Ref-VOS, and Ref-AVS approaches. The code will be released after publication.
memorybenchmark - arxiv:2610.12779 · eess.SYGame Petri Nets: Compositional Modeling and Analysis of Large-Scale Strategic SystemsQuanyan Zhu
Large-scale strategic systems, such as maintenance workflows, cyber campaigns, and multi-agent AI pipelines, consist of many interactions whose outcomes determine which later interactions become possible, who takes part, and with what resources. We introduce game Petri nets, formalized as outcome-driven compositional game Petri nets (OCGPNs), to model and analyze such systems. Local games are attached to places of a colored Petri net, and a game-to-token interface converts each resolved game into typed tokens that enable, synchronize, or block subsequent games. For general, concurrent nets, we give an operational semantics and a structural theory based on invariants and Farkas certificates, which shows that guards can certify unreachability whereas incentive instruments can only change values. For sequential nets, the net induces a stochastic game on its game places. We prove that global equilibria are exactly collections of equilibria of local games augmented by continuation values, characterize through successor-level pivotality when downstream games change upstream behavior, and compute values place by place via a decomposition into strongly connected components, at a cost additive in local game sizes. A composition calculus based on place fusion glues certificates across subnets and summarizes downstream subnets by their entry values. Two running examples, a maintenance workflow and an intrusion campaign derived from multi-resolution cyber-defense games, illustrate the theory, including the composition of a newly discovered attack scenario with an existing campaign.
multi-agent - arxiv:2610.12772 · cs.ROReflex: Visually Grounded Reactive Humanoid ControlTaoyang Jia, Weikai Huang, Linxin Song, Jared Darlington +5
Humans effortlessly react to the world; they adeptly return a tennis shot, catch a falling cup, step aside from a passing cart, or pass a box tossed during truck unloading. These everyday actions require anticipating a moving target and reflexively responding with the whole body within about a second. Such visual reactive whole-body control remains challenging for humanoids, which must (1) coordinate whole-body control, (2) react to object dynamics in real time, and (3) ground perception in egocentric vision. We study catching thrown boxes as a representative task that demands all three capabilities; existing systems cover only part of it, relying on end-effectors, motion capture, or marked objects. We present Reflex, a three-stage framework that learns these capabilities stage by stage while connecting them through a compact representation of object dynamics. First, a state-based policy learns whole-body catching with reinforcement learning. Second, the policy learns to infer the dynamics of a moving box from delayed and incomplete observations. Third, an egocentric RGB-D encoder learns to recover this dynamics representation directly from visual observations while keeping the whole-body controller fixed. This decomposition provides each capability with a direct training signal and makes visual learning substantially more scalable. In simulation, Reflex achieves 85.7% catch success from egocentric RGB-D, compared with 87.9% when given privileged box observations. Temporal visual history is critical: removing it reduces success by 35.6 and 39.8 points on centered and laterally offset throws. On a real Unitree G1, Reflex catches human-thrown boxes with 65% and 40% success at 2.5 and 5 m, reaching 76% and 59% of human catchers' success at the same distances.
humanoidwhole-body control - arxiv:2610.12766 · cs.LGProvenance-grouped protocol for evaluating machine learning in perovskite photovoltaicsQiwei Han, Chi Zhou
Machine-learning models for perovskite solar cells are typically evaluated using random data splits, which we show systematically leak information through massive internal duplication. Because nearly two-thirds of curated devices share their exact recipe with another, random splits primarily reward the mere recall of historical data rather than testing true physical generalisation. To solve this, we mapped the institutional provenance of the Perovskite Database and established a rigorous hierarchy of grouped splits that progressively isolate duplicate devices, publications, and institutions. Benchmarking thirteen models establishes new state-of-the-art performance across all splits and reveals a critical regime shift: while tree ensembles dominate random splits by recognising familiar recipes, their ranking collapses on genuinely unseen institutions and future discoveries, where composition-aware neural architectures excel. Furthermore, feature importance demonstrates that the device architecture and fabrication methodology dictate final efficiency just as strongly as the absorber chemistry. This standardised protocol empowers the community to separate memorisation from true physical discovery.
benchmark - arxiv:2610.12762 · cs.AIFaithful and Complete LLM-Assisted Automated Construction of Hierarchical Hardware Knowledge GraphsHaotian Qiao, Robert P. Dick
Hardware datasheets contain engineering specifications essential for component selection, system integration, and hardware compatibility verification. However, manual inspection is tedious and error-prone because datasheets are lengthy and heterogeneous, with dense information fragmented across tables, figures, and text. Although large language models (LLMs) can automate this process, naïve one-shot processing omits relevant specifications even when the document fits within the model's context window. We present an automated LLM-driven pipeline that transforms hardware datasheets into general-purpose hierarchical hardware knowledge graphs through chunk-based property extraction, hierarchical routing, and iterative refinement. The framework uses LLMs for information extraction and semantic reasoning while preserving source provenance and applying graph updates through validated instructions and deterministic local execution. This staged design reduces per-query context and maintains traceable intermediate representations. The resulting knowledge graphs provide semantically organized, source-grounded hardware properties for downstream retrieval and reasoning. We evaluate the framework on 20 hardware datasheets spanning diverse component types and document lengths. We assess property faithfulness and introduce inter-graph completeness to measure relative semantic coverage without exhaustive ground truth. Our framework achieves 98.8% property faithfulness compared with 76.1% for the one-shot baseline, while fully covering 83.6% of faithful baseline properties; in the reverse direction, the baseline fully covers only 10.5% of ours. These improvements provide more reliable and comprehensive engineering information for downstream hardware design and verification, reducing the risk of overlooked constraints and incorrect decisions.
knowledge graphiterative refinement - arxiv:2610.12758 · cs.CLDistressBench: Evaluating Multi-Dimensional Crisis Support in Large Language ModelsDrew Rein, Patrick Oathout, Vishal Kumar, Udari Madhushani Sehwag
Language models have been adopted faster than evaluation practices that reliably assess their risks, and a growing share of use is affective rather than informational. Within that traffic users disclose suicide and self-harm (SSH) crises. Existing safety benchmarks score models primarily on refusal, but refusal is not the desired behavior here; the conversation requires a substantive supportive response. We introduce DistressBench, 718 English conversations with clinician-authored user turns spanning 23 SSH subcategories, each paired with a task-specific rubric of weighted atomic criteria across seven dimensions of crisis support and a clinician reference response. A model's score is the weighted average over the criteria its reply satisfies, reading directly as the fraction of required care delivered. The best of 25 frontier models satisfies 88.4% of weighted criteria and the median model 71.4%, against 98.7% for clinician references scored on the same criteria. Pooled across all 25 models, in 35.3% of conversations where a model satisfied every criterion for recognizing the crisis, it failed to route the user toward human help. The shortfall concentrates in the dimensions requiring the model to act rather than withhold. Contrasting each dimension's median model against its best separates capability limits from choices: de-escalation reaches 74.6% in the strongest model against a median of 46.0%, and safety disclaimers 84.6% against 8.3%. Multi-turn conversations score below single-turn ones (68.5% against 74.2%). We release the corpus, rubrics, judge calibration labels, and a companion annex of 20 long-horizon red-team transcripts. These results argue for evaluating crisis safety on the care a model delivers rather than on what it declines to say, and for treating de-escalation and resource routing as deployment requirements.
benchmark - arxiv:2610.12757 · cs.CLMADS: Multi-Agent Dialog Simulation for Robust Conversational AgentsArkajyoti Chakraborty, Adam Zernik, Ishika Kulkarni, Mudit Arora +5
Task-oriented conversational agents remain fragile under realistic conditions, especially when users exhibit non-cooperative behavior. Existing function-calling benchmarks underrepresent adversarial conversation trajectories, thereby limiting the training resources available for developing robust agents. We present MADS (Multi-Agent Dialog Simulation), a synthetic data generation pipeline that produces structured, diverse dialogue trajectories. We inject adversarial conversation, producing validated conversation trajectories that capture realistic, unhappy paths. Using MADS, we construct MADS-Bench: a benchmark spanning six domains, 55 personas, and 1095 conversations, with approximately 66% of conversations containing failure-prone conversation scenarios. We evaluate the robustness of the trained models using a two-stage training approach that combines supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR).
multi-agentbenchmark - arxiv:2610.12756 · cs.MAHow Do Hardware Faults Manifest Differently in LLM Agents?Aiden Rubey, Zachary Coalson, Cong Chen, Jean-Philippe Monteuuis +2
We present the first systematic study of the resilience of large language model (LLM) agents to random hardware-induced faults. Prior work on hardware fault resilience in LLMs focuses on model-level outcomes, such as incorrect outputs or generation failures. Yet LLM agents repeatedly interact with tools and environments, creating loops that can change how hardware faults manifest. We conduct an extensive evaluation across three agent benchmarks, comprising 6,814 agent executions: 2,400+ clean runs and 4,300+ fault-injected runs with independently sampled random two-bit weight faults. We trace how these faults propagate through agent execution. Unlike prior studies, we find that agentic execution transforms model-level corruption into distinct system-level outcomes: (1) agents can recover from faulty model outputs and still complete tasks correctly; (2) this recovery increases computational and execution costs; (3) a few faults cause subtle but semantically meaningful errors while the agent otherwise behaves normally; and (4) for some models and scenarios, faults can alter security and alignment behavior.
agentllm agentagenticagent benchmarkbenchmark - arxiv:2610.12754 · cs.LGNV-Tesseract-AD: Curriculum-Enhanced Conditional Diffusion for Multivariate Time-Series Anomaly DetectionAditi Gautam, Manikandan Ravikiran, Saira Qureshi, Sena Fatma Ekiz +3
We propose NV-Tesseract-AD, a curriculum learning-enhanced conditional diffusion framework for multivariate time-series anomaly detection. Our central hypothesis is that reconstruction difficulty can be explicitly structured along two complementary axes, masking severity and diffusion noise level, and that training from easier to harder tasks along both axes simultaneously stabilizes optimization and improves residual discriminability. We integrate a Transformer-based diffusion backbone with a three-stage dual curriculum over masking ratios and diffusion timesteps, retaining anomalous samples throughout training and relying on structured corruption to drive self-supervised representation learning. We evaluate NV-Tesseract-AD under two regimes: in-distribution training on the TSB-UAD-M corpus and strict zero-shot transfer to ten EasyTSAD benchmark families without per-dataset tuning. The dual-axis curriculum produces masking-invariant reconstruction, confirmed by a near-zero loss gap between complementary masking strategies within the first training stage, and yields an approximately 3.7-fold improvement in F1 and a 56 percent reduction in MSE relative to a non-curriculum baseline. Zero-shot performance reaches F1 = 0.984 on NAB and F1 = 0.948 on NormA. Weaker results on heterogeneous families are traced to unsupervised threshold calibration rather than reconstruction quality, identifying calibration as the dominant remaining detection bottleneck. Accelerated inference via DPM-Solver++ reduces sampling cost by a factor of 3.5 to 5.7 at the dataset level but couples to thresholding behavior, establishing that the sampler and threshold must be validated jointly. Together, these findings demonstrate that aligning diffusion denoising difficulty with curriculum learning principles provides a principled and practical approach for robust anomaly detection in complex multivariate time series.
curriculum learningbenchmark - arxiv:2610.12747 · cs.ROTrajectory Prediction for Autonomous Driving in Road Construction Zones Using Human-in-the-Loop Driving DataShuo Zhang, Aman Sunesh, Semiha Ergan, Kaan Ozbay
Ego-trajectory prediction in urban roadway work zones remains an underexplored topic in autonomous-driving research, with limited dedicated data and systematic evaluation. Roadway work zones involve temporary changes in the lane layouts and connectivity of the roads, complicating interactions with surrounding vehicles and workers. These changes make future vehicle trajectories difficult to predict. To address these challenges, we collect WZDrive-Data, a multimodal dataset comprising 1,183 work-zone driving segments from 33 drivers, using a human-in-the-loop driving simulator with prerecorded worker animations and VR-controlled workers. Driver control and gaze signals are recorded from human participants, while vehicle trajectories and scene information are obtained from the simulator. Our proposed multimodal ego-trajectory predictor, WZDrive, achieves a mean minADE (K=6) of 1.09 m and minFDE (K=6) of 2.12 m. Compared with the best-performing state-of-the-art baseline for each metric in our benchmark, WZDrive reduces minADE (K=6) by 7.18% and minFDE (K=6) by 13.18%. This research addresses a gap in autonomous-driving research on urban work zones by combining human-in-the-loop data collection with multimodal learning from human driving signals and in the context of work zones.
human-in-the-loopbenchmark - arxiv:2610.12738 · cs.LGKITE: A Knowledge-Injected Temporal Encoder for Time-Series Event ForecastingJonas Petersen, Pratik Jawahar, Riccardo Maggioni, Gian-Alessandro Lombardi +5
Forecasting rare, high-cost events in multivariate time-series systems is hard because their precursors are seldom observed, so a purely data-driven model has little to learn from. The engineers who run these systems, however, hold knowledge that precedes such events, information absent from the scarce labels. We call this a semantic prior and inject it into a self-supervised event forecaster through two switchable mechanisms, a covariate mechanism and an attention-bias mechanism, each the identity at its null, so one architecture serves every prior type with no per-dataset architecture search. A prior helps when it supplies information the observed window does not already contain: in a short context an informative prior beats no prior in-domain (pooled h-AUROC over the no-prior baseline: a periodicity clock +14%, p<0.001; a conservation residual +47% at a 0.25 label fraction), and a working prior transfers out-of-domain (+53%), substituting for feature transfer, while priors the window already recovers stay inert and the attention-bias mechanism shows no measurable gain. KITE is a switchable, attributable route to contextual conditioning, and a substrate for scaling toward cross-domain, pretrained time-series foundation world models that carry their governing structure explicitly.
world model - arxiv:2610.12737 · cs.LGKernelized Parameter Sensitivity Atlases for Amortized Conditional InterpretabilityDavide Wiest, Ahanaf Hasan Ariq, Abdul Monaf Chowdhury
Gradient-based attribution provides input-specific information about model parameters, but computing it via backpropagation for many samples is expensive, while static importance scores discard input dependence. We derive KPSA (Kernelized Parameter Sensitivity Atlas) from a block decomposition of the empirical neural tangent kernel. It measures normalized parameter-group sensitivity, embeds those sources in an explicit query space, and uses a lightweight kernel to estimate sensitivities for unseen inputs. We derive bounds that separate finite-source from irreducible representation error and give margin-based top-$k$ recovery. This paper studies two interpretability applications. Firstly, KPSA identifies parameter groups with high susceptibility to perturbations across vision, forecasting, and protein-modeling setups. Across a fivefold range of parameter budgets ($0.02$-$0.1\%$), its selected groups attain $39$-$85\%$ of the perturbation susceptibility of a first-order backpropagation oracle. In vision and forecasting, these parameter groups form sparse sensitivity circuits that extend across depth and vary systematically with the input. Secondly, we use KPSA on an activation-attribution problem for MLP features in transformers. It retains $81\%$ of the gap between a backpropagation oracle and a constant-sensitivity baseline on vision while increasing batched query-time throughput from 551 to 2,041 images/s and reducing peak GPU memory from 4.55 to 0.44GB. On the protein-modeling task, it recovers $68\%$ of this gap. An ablation of KPSA's kernel aggregation shows that nearest-neighbor retrieval in KPSA space can remain competitive. The empirics show that compact kernel atlases can store useful input-dependent parameter sensitivity while amortizing repeated gradient attribution, a step toward scalable conditional interpretability. Code can be found at https://github.com/Axym-Labs/kpsa .
memory - arxiv:2610.12734 · cs.ROStereoEngine: Scaling Stereo Bimanual Robot Data without Stereo CamerasJason Chen, I-Chun Arthur Liu, Gaurav Sukhatme, Daniel Seita
Stereo vision is increasingly used for robotic manipulation, with a growing body of work incorporating it into Vision-Language-Action (VLA) models. However, the scarcity of large-scale, real-world stereo datasets remains a fundamental bottleneck for scaling such policies. Recent generative monocular-to-stereo methods target settings such as VR content and autonomous driving. No prior work produces realistic synthetic stereo data for robotic manipulation, where stereo supervision has come predominantly from simulation. We propose StereoEngine, which introduces two complementary methods to synthesize stereo data for robotic manipulation. In the first, we warp a monocular (left) video into the right view using estimated depth and inpaint the disoccluded regions with a video diffusion model, lifting monocular demonstrations into stereo pairs without training on real stereo. In the second, we render a stereo pair in simulation and jointly generate both photorealistic views, producing consistent left-right data without any real video as input. StereoEngine outperforms existing baselines in generated stereo quality, and using its synthetic data for policy mid-training or task-specific fine-tuning substantially improves downstream bimanual manipulation. Project website: https://stereoengine.github.io
vision-language-actionmanipulation - arxiv:2610.12733 · cs.ROVisual-Wi-Fi Navigation to Signal-Emitting DevicesLihao Wang, Tianjian Xu, Tianmin Shu, Renjie Zhao
Indoor navigation to task-relevant targets remains difficult when the target is small, occluded, or visually indistinct. Meanwhile, smart appliances, mobile devices, and IoT tags emit Wi-Fi signals during everyday communication, providing a pervasive but underused spatial cue. We study visual-Wi-Fi navigation, where a robot reaches a signal-emitting device in an unmapped environment using onboard visual observations and Wi-Fi packets overheard from the device, without connecting to the device or modifying infrastructure. Realizing this requires pose-dependent Wi-Fi observations during closed-loop policy learning and reliable spatial cues from bearing measurements corrupted by indoor multipath propagation on a moving robot. We present WiFiSpaces, which extends the Habitat embodied simulator with online ray-traced Wi-Fi sensing, rendering Wi-Fi observations for a robot-mounted antenna array at continuous poses during policy rollouts. On top of it, we build ViFiNav, a localization-aware navigation framework: an online source-localization algorithm exploits robot motion to disambiguate and robustly aggregate bearings from multiple viewpoints into a confidence-aware source estimate, and a learned policy fuses this evolving estimate with depth observations and learns to act on it as it is refined. Experiments show that exploiting robot motion is key to accurate source estimates, and that fine-tuning on ray-traced Wi-Fi observations in WiFiSpaces improves the success rate of ViFiNav. The policy transfers zero-shot to unseen scene datasets, and we deploy it on a real robot with a Wi-Fi sensor built from a commodity router, without any real-world training.
embodied - arxiv:2610.12730 · eess.SYROAM: Reinforcement Learning Optimized Adaptive Moving Target Defense for Smart GridMohammad Zakaria Haider, Prabin Mali, Muhammad Nadeem, Sumit Paudyal +2
Smart grids rely on distributed phasor measurement units (PMUs) and wide-area communication networks whose data-acquisition pipelines are vulnerable to stealthy false data injection (FDI) attacks that evade conventional bad-data detection (BDD). Moving target defense (MTD) counters this exposure by continuously remapping sensor identities, but existing schemes apply static or pre-scheduled randomization and are each constrained by a single failure mode: seed-based methods are fast yet fragile to key compromise, while machine learning (ML) based prediction methods are resilient yet incur prohibitive latency. Neither adapts its randomization to live threat evidence. This paper presents ROAM, a deep reinforcement learning (DRL) driven MTD framework in which a deep Q-network (DQN) agent continuously re-optimizes the sensor-to-ID mapping at the aggregation layer. At each decision step, the agent selects the deception coverage, flags the specific sensors to remap, and sets the split of the remapped sensors between seed-based and ML-prediction-based recovery, without modifying PMU hardware and while preserving IEEE C37.118 compatibility. On held-out BDD-compliant FDI scenarios across the IEEE 14-, 57-, and 118- bus systems, ROAM keeps the percentage of stealthy attacks below 3% while sustaining detection rates above 93%. Against an adaptive soft actor-critic (SAC) attacker that observes the defender's configuration, ROAM keeps stealthy attacks below 2.6% with detection above 92%. Hardware-in-the-loop testing on an OPAL-RT platform confirms real-time feasibility, with sub-18ms average shuffle execution and an average reshuffle blind window of 2.6% of the 3-s decision cycle.
agent - arxiv:2610.12728 · cs.LGA Categorical Atlas of Parameter-Efficient Fine-Tuning: Cones, Orbits, and GaugesXiaoyu Li, Zhizhou Sha, Chiwun Yang, Dai Shi
Parameter-efficient fine-tuning has hundreds of methods, usually compared by parameter count and benchmark score. We compare them as maps. A pretrained checkpoint is a base point in weight space, and a weight-space method is a smooth map from a small parameter space that starts at that point. These maps form a slice category in which the frozen model is initial and full fine-tuning terminal. Three invariants of the map do most of the work. Its image near the base point governs expressivity, through the first-order image, the dimension, a min-cut bound on rank and whether that point is smooth or an apex. Its fibres, with the optimizer's metric, govern training dynamics. Base change moves the base point and covers splitting initialisations, quantisation, restarts and merging. We prove, for example, that zero-initialised LoRA, and Householder reflection adaptation at its default start under stated rank and parity conditions, begin at the apex of a cone; that no exact initialisation lets LoRA reach an update of rank above twice its own; that exactly orthogonal methods never change a weight's singular values in exact arithmetic, however often they are merged; that under Adam with no epsilon, weight decay or clipping and one shared schedule, LoRA+ from the standard zero initialisation follows exactly the trajectory of plain LoRA with its scale multiplied by the learning-rate ratio; that Adam with shared hyperparameters respects only the signed permutations inside LoRA's continuous symmetry group of full-rank factors; and that the activation function decides when a scaling adapter folds into preceding weights. We classify 382 methods from 138 papers by seven coordinates read off their formulas, with 403 simulation arrows and 485 obstructions. Every numbered result is proved in full, and results due to others are credited where we re-derive them.
benchmark - arxiv:2610.12710 · cs.ROREMM: Revisable Embodied Memory for ManipulationRevanth Krishna Senthilkumaran, Ruwan Wickramarachchi, Alessandro Oltramari, Jonathan Francis
Long-horizon manipulation requires robots to retain task-relevant history while revising conclusions no longer supported by physical evidence. Retaining observations alone does not specify which completed conditions should be withdrawn after a disturbance or which obligations require repair. We introduce REMM, Revisable Embodied Memory for Manipulation, a supervisory memory layer for a frozen G0.5 vision-language-action executor. REMM separates an append-only evidence history from revisable task state and explicitly links derived relations and completed conditions to their supporting facts. When accepted evidence changes a supporting fact, it withdraws dependent conclusions and schedules targeted recovery at verified skill boundaries without updating the executor. Across 51 physical trials, including operator-assisted runs, REMM improves mean recorded task progress over the strongest baseline from 57% to 91% in intervention recovery and from 43% to 70% in sequence recall. Complementary video diagnostics show improved grounding of retained history into the next instruction, including comparisons with $π_{0.5}$-compatible high-level planner adaptations. These results support revisable memory as a practical interface for continued manipulation without policy retraining. Project: https://revanthsenthil.github.io/remm/.
vision-language-actionembodiedmanipulationmemory - arxiv:2610.12707 · cs.CVUnsupervised Multimodal Reward ModelingYueying Li, Jingxuan Fan, Kianté Brantley, Sham M. Kakade +1
Vision-language reward models are trained on annotated preference pairs, which are expensive to collect, can disagree, and are ranked by benchmark accuracy. We build one with no human preference label: a linear head on an intermediate layer of a frozen Qwen3-VL backbone, trained to score a web caption above a perturbed version of the same caption; labeled data enters only to select the layer. The layer is the decisive choice, worth 5.8 points over the last layer, and one recipe transferred without re-tuning beats or at least matches GPT-4o on three benchmarks at 32B, 6.6 points ahead on VL-RewardBench, from a few thousand parameters at about a thousandth of fine-tuning compute. At an equal pair budget, perturbations teach a frozen head 3 to 5 points more than curated RLAIF-V pairs. Because the backbone is frozen, the objective is convex, and the perturbation sampler specifies the reward, which the benchmark does not identify: two heads trained on disjoint halves of the same perturbations tie on the benchmark and differ by 6.4 points in hallucination judging. Retraining the head on the policy's own verifier-labeled candidates cuts caption hallucination by 5.1 CHAIR points and lifts image-generation pass rate by 5.4, while scoring lower on every reward benchmark. Together, an intermediate-layer probe, free same-image perturbations, and a verifier-driven bootstrap turn give a recipe for multimodal reward modeling that needs no annotator, costs a fraction of fine-tuning, and is specified by the comparisons it is trained on rather than by a benchmark rank.
benchmark - arxiv:2610.12696 · cs.ROSpa-Bench: A Real-Robot Benchmark for Spatial Grounding in Vision-Language-Action ModelsJustin Tien-Smith, Matthew Pidden, Rolandos Alexandros Potamias
Vision-language-action models (VLAs) offer a promising route toward general-purpose robotics by transferring semantic knowledge from large-scale vision-language pretraining into language-conditioned control. However, most VLA evaluations emphasize aggregate manipulation success under changes in objects, instructions, or environments, leaving unclear how reliably these policies ground spatial descriptions in the physical scenes where they act. We therefore ask a sharper question: how reliably can current VLAs translate spatial descriptions into appropriate real-robot behavior? To investigate this, we introduce Spa-Bench, a real-robot benchmark that evaluates spatial grounding across six tabletop tasks covering Object State, Relative Size, Referential Description, Relational Placement, Ordinal Position, and Counting. Our primary evaluation compares in-distribution (ID) and out-of-distribution (OOD) spatial configurations while retaining training support for the relevant objects, concepts, and actions, reducing object and motor unfamiliarity as alternative explanations for failure. Four diagnostic conditions further probe physical execution, sensitivity to wording, object-task associations, and recognition that no action is required. We release 4,092 episodes collected on the SO-101 robot arm: 1,200 human-teleoperated demonstrations and 2,892 real-robot evaluation rollouts from five state-of-the-art VLA policies. Across the three fully evaluated policies, success falls from 67.5-73.3% on ID spatial configurations to 40.7-52.0% on OOD spatial configurations, while matched direct instructions improve success by 28.3-40.0 percentage points. These results show that the evaluated VLAs can often execute the required manipulations but lack robust spatial grounding. Project materials, including videos, code, and benchmark data, are available at https://justintiensmith.github.io/Spa-Bench/.
vision-language-actionvlamanipulationbenchmark - arxiv:2610.12694 · cs.LGCritical Mass: Structure-Disjoint Splits Drift With the Libraries They Are Built OnTomo Oga, Devesh Shah, Cailum M. K. Stienstra, Gabriel Asher +3
Molecular machine learning evaluates out-of-distribution performance with structure disjoint splits, a construction rule fixed once at the scale its library happened to have: threshold a pairwise distance, then assign whole connected components to folds. For predicting structures from mass spectra, the field has converged on single-linkage clustering under the myopic Maximum Common Edge Subgraph (MCES) distance at a threshold of 10. This convention was set on 29,000 molecules but public libraries now hold 227,690 molecules. MCES is NP-hard per pair over a quadratically growing set, and so the criterion has never been evaluated at that scale. We propose an optimized version of this criterion, allowing for computationally feasible application on the public libraries: Admissible bounds and a union-find skip reduce $2.6 \times 10^{10}$ molecular pairs to only $1.15 \times 10^{7}$ integer programs, a $2{,}259\times$ saving, while provably producing the lossless partition. We find that at this scale the graph percolates. A single component holds $95.5\%$ of the library, capping any test set at $4.5\%$. What remains is not merely smaller, but systematically different: a held-out compound outweighs a training compound 88.1\% of the time, because a fixed absolute budget is a tighter relative tolerance on a larger molecule. Large library benchmarks using this splitting rule naively therefore conflate structural novelty with extrapolation to larger, more complex chemistry.
benchmark - arxiv:2610.12684 · cs.RONon-Prehensile Multi-Object Placement with Mobile Robots via Diffusion-Based Trajectory PlanningLance Pharand, Megnath Ramesh, Mark Chiu, Yash Vardhan Pant +1
Non-prehensile manipulation with mobile robots has primarily targeted placement in coarse goal regions. Precision placement has been studied with manipulators on benchmarks such as Push-T, where an omnidirectional end effector can readily re-approach an object from any side. For a mobile robot, correcting the same placement errors may require wide repositioning maneuvers around the object. We formalize multi-object pushing with a mobile robot as a multi-target assignment problem at tight tolerances. We propose a diffusion planner with a causal factorization: each robot denoising step is followed by an object step conditioned on the current clean robot estimate. This factorization allows us to sample multiple object outcomes for a single robot plan, capturing the multi-modality of pushing. We also design a set of pushing-specific costs for mobile robots, used for both guidance and best-of-$N$ sampling at inference. On Push-T, our planner attains the highest success rate of the methods we compare, while having the lowest rate of implausible object motion. Across three multi-box pushing environments resembling warehouse scenarios, it raises the fraction of boxes placed by $21.5$ percentage points over an unguided baseline, and replans $1.8\times$ faster than a planner that denoises the two trajectories together. Lastly, we deploy the guided planner on a TurtleBot 3 Burger with object shapes absent from the training data, where it places $85.0\%$ of objects within tolerance against Diffusion Policy's $37.5\%$.
manipulationdiffusion policymanipulatorbenchmark - arxiv:2610.12680 · cs.LGExpert-level detection of low-voltage intervals in EEG as a robust biomarker of neonatal encephalopathyJohn M. O'Toole, Sean R. Mathieson, Aurel Luca, Soraia Ventura +3
Background: Discontinuity in neonatal EEG is a critical marker of brain dysfunction but can be difficult to quantify visually. Inter-burst intervals (IBIs) are a key characteristic of discontinuity, yet their definition does not easily translate to AI detection. Objectives: To introduce low-voltage intervals (LVIs), defined exclusively by amplitude and duration, as a context-independent alternative to IBIs, develop an AI detection method for LVIs, and assess their clinical utility as a marker of brain injury. Methods: We developed a ConvNeXt model to detect LVIs and compared its performance with existing methods. We then tested the clinical relevance of detected LVIs across four applications: 1) grading background EEG abnormalities on an open benchmark dataset, 2) classifying clinical hypoxic-ischaemic encephalopathy (HIE) grades and comparing with a normal EEG dataset, 3) seizure prediction, and 4) association with seizure burden. Results: For training and validation, 654 hours of per-channel EEG from 123 neonates were reviewed and 51,162 LVIs were annotated. On held-out validation, ConvNeXt had an AUC of 0.996 and a Matthews correlation coefficient of 0.926. Model-reader agreement exceeded inter-reader agreement ($Δκ= 0.025$, 95% CI: 0.007 to 0.045, $p<0.001$), attaining expert-level equivalence. On a combined dataset of 444 neonates, percentage LVI showed a strong association with EEG grades (Spearman's $ρ=0.801$), a moderate association with HIE grades ($ρ=0.384$), a weaker association with seizure burden ($ρ=0.244$), and a strong seizure prediction capacity (AUC $=0.872$). Conclusion: AI detection of LVIs achieves expert-level equivalence, whereas quantitative features do not. Automated LVI quantification provides a robust clinical biomarker of neonatal encephalopathy associated with background EEG activity, HIE severity, and seizure risk.
benchmark - arxiv:2610.12676 · cs.CVWoodBR-Cross: A public wood-image dataset and individual-tree-disjoint benchmark for species identificationDaniel Casanova, Alexandre Bahia Gontijo, Arnaldo Candido Junior, Silvana Nisgoski +1
Wood-image benchmarks can yield optimistic estimates when images from the same tree occur in both training and test sets. WoodBR-Cross contains 4,875 transverse-surface images in 38 operational taxonomic classes, linked to 303 distinct trees identified by numeric catalogue witness codes (codigos-testemunho) in the Brazilian Forest Service collection. A species-level subset comprises 3,406 images, 20 classes and 214 trees. Three tasks compare duplicate-aware image partitions for all classes (A), image partitions for the species subset (B1), and individual-tree-disjoint partitions for that subset (B2). In B2, all images from each tree are kept together, so no tree is shared across training, validation or test within a fold. ResNet-50, ConvNeXt-Tiny and ViT-B/16 were evaluated with three outer folds, internal validation and five training seeds. Handcrafted and frozen-feature baselines complement border-only and randomized-label controls. Validation-selected ConvNeXt-Tiny achieved B2 tree-level macro-F1 of 0.8621 +/- 0.0317; frozen DINOv2 features yielded 0.9000 +/- 0.0722. Values are means and standard deviations across three seed-averaged fold means. Results estimate performance on previously unseen trees from this collection.
benchmark - arxiv:2610.12669 · cs.AIGeoFitBench-LLM: A Benchmark for Assessing Large Language Models' Capabilities in Geospatial Data Requirements Elicitation for Geo-Analytic TasksAmirhossein Vahdat, Thierry Badard, Luc Lamontagne
Large language models are becoming central to GeoAI systems, yet their evaluation rarely considers the elicitation of geospatial data requirements. This omission is critical as retrieval oriented geo-analytic tasks cannot be supported reliably without first identifying the necessary datasets and constraints. GeoFitBench-LLM is introduced as a benchmark for assessing whether LLMs can infer the datasets, the supporting resources and the constraints required by geo-analytic requests in natural language. The benchmark is structured around two reasoning dimensions, Spatio-Temporal Relational and Semantic Grounding, reflecting long-standing challenges in geospatial information retrieval and related natural language tasks. Ground truth requirements are encoded in a fixed, provider-independent schema for reproducible evaluation of resource identification and attribute-level specification. Experiments on seven models under minimal prompting indicate that identifying the necessary resources is often achievable, with GPT-5.4 Thinking achieving the best result by recovering the complete set of resources in 66.67% of benchmark requests. Results further indicate that accurate fitness-for-use specification remains more difficult as inferential demands increase.
benchmark - arxiv:2610.12668 · cs.LGRecurrent Harness for Agentic Continual LearningYuxin Xiao, Zhiyun Lu, Jianyu Wang, Yangtian Zhang +3
Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution shifts through continual learning. However, existing agent harnesses typically either evolve their states only through forward information flow or rely on additional replay or validation data for harness optimization. To address this, we propose ReHarness, a recurrent harness framework for agentic continual learning that complements forward read and write with backward revision under a strictly online streaming protocol. We ask what information could have been captured differently in the harness state to better inform the current instance in the stream. Specifically, after each instance, we leverage the resulting trajectory as feedback to revise the reflections retrieved for that instance, thereby propagating feedback backward through the textual harness state. Across three continual learning benchmarks and three language model backbones, ReHarness consistently outperforms strong raw-context baselines, memory- and reflection-based methods, and prompt optimization approaches. Further analysis shows that ReHarness produces source-grounded and meaningful revisions, corrects overgeneralized or outdated experience under distribution shifts, and improves both stability and plasticity during continual learning.
agentagenticbenchmark - arxiv:2610.12667 · cs.CLperturber: A Stateless Service for Semantics-Preserving Text PerturbationsKhoi-Nguyen Tran
Large language model (LLM) evaluations on clean benchmarks overstate model robustness: real inputs arrive perturbed, and these meaning-preserving variants routinely move model answers. Studying this systematically requires applying perturbations one at a time, reproducibly, and identically wherever they run, yet existing tools couple them to a benchmarking stack rather than packaging them as a reusable transform layer. We present perturber, a stateless service and Python library that applies exactly one semantics-preserving perturbation per call, drawn from a first-party catalog of 68 perturbations across 11 families. It turns on a single primitive, with composition left to the caller chaining calls, so the service and the library produce identical output by construction. We evaluate the tool itself, its correctness, reproducibility, and cost, rather than any model's robustness, measuring meaning-preservation per perturbation rather than assuming it. The demonstration adds a live playground, an introspectable catalog for benchmark selection, and a one-command reproducible evaluation.
benchmark - arxiv:2610.12666 · cs.AIIncremental Retrieval-Augmented Generation for Human-in-the-Loop Decision SupportFederico Mazzoni, Andrea Failla
We introduce iRAG, a human-in-the-loop decision-support system combining Retrieval-Augmented Generation (RAG) with Hybrid Decision-Making. Unlike conventional RAG systems, relying on static Knowledge Bases (KBs), our proposal addresses settings where the KB is initially empty and is progressively populated through human decisions. The system stores previous decisions as retrievable precedents and moves from silent observation to evidence-grounded contestation and, finally, to autonomous handling with abstention. Against an independent baseline, iRAG matches final-decision error under 10% drift without retrieval decay and reduces it under 40% drift across all configurations. Retrieval decay improves performance on changed knowledge while increasing error on stable knowledge, evidencing a stability--plasticity trade-off rather than a general advantage. Human oversight is an architectural provision of the workflow; its usability with real human users remains to be evaluated.
retrieval-augmentedraghuman-in-the-loop - arxiv:2610.12659 · cs.LGMagicBeanStalk: Escaping the RLVR Zero Advantage Trap with Recursive Data SynthesisXiming Lu, Aviral Kumar, Jan Kautz, Yejin Choi +1
Data-centric scaling of RLVR has focused on collecting or generating verifiable training problems. However, corpus size alone does not determine whether the dataset provides a useful learning signal for a target policy. To guide the synthesis of effective RLVR data, we experimentally characterize dataset effectiveness as a function of its problems, the target policy, and the training rollout budget. Under this characterization, we show that a large open-source math corpus pooled from widely used RLVR datasets falls almost entirely into a zero-advantage trap: for a fixed target policy and rollout budget, roughly 88% of its problems are solved in every rollout or failed in every rollout. Filtering concentrates what remains, but it can only select, discarding the hard problems. Effective synthetic problems should therefore require the reasoning operations and compositions required to solve those hard problems. Yet their difficulty must be calibrated, so that some rollouts succeed, some fail, and at least one correct solution fits within the training budget. Prompting a teacher to vary hard problems directly does not achieve this. Guided by these empirical principles, we introduce MagicBeanStalk, a top-down decomposition and bottom-up recursive data-synthesis algorithm that grows seed problems into families of substantively new, policy- and budget-calibrated training problems while preserving the seeds' reasoning blueprints. Across 8 math benchmarks, continual RLVR on MagicBeanStalk problems improves gpt-oss-120b from 61.2 to 69.8 (+8.6) and DeepSeek v4Flash from 72.4 to 77.9 (+5.4) on a 16K-token budget. Training on the full 78K source corpus improves by only +1.1 and its best filtered real data subset by +5.8. In finance, we synthesize over 14K verifiable problems from only 340 solutions and improve over base by 6.9 and 2.4 points on SecQue and FinanceBench, respectively.
benchmark - arxiv:2610.12658 · cs.LGData-driven Optimal Sensor Placement for Aerosol Monitoring in the UKTalha Ansar, Waqar Muhammad Ashraf, Alejandro Coca-Castro, Manvendra Janmaijaya +2
We develop a data-driven sensor-placement framework and apply it to aerosol monitoring in the United Kingdom (UK). A trained convolutional Gaussian neural process is embedded within the DeepSensor optimisation framework. Genetic optimisation with lazy evaluation and caching reduces mean computational time by 60\% (10$\pm$3 versus 25$\pm$7 minutes) while producing sequential placement performance comparable to the greedy solver. Using the CAMS reference field to construct a retrospective oracle benchmark, Joint NLL improves by about 22\% for Joint-MI-driven genetic placement after five locations for aerosol stations are identified. Seasonal and wind-regime analyses show that agreement between model-based criteria and oracle benchmarks varies with meteorological transport conditions. These results show a computationally efficient approach for data-informed expansion of environmental observing systems.
benchmark - arxiv:2610.12657 · cs.LGKronecker Product Attention: Memory-Efficient KV Compression via Structured FactorizationBahareh Nikpour, Hossein Rajabzadeh, Maryam Dialameh, Vahid Partovi Nia +1
Efficient autoregressive generation is increasingly limited by the memory footprint of the key-value (KV) cache, which grows linearly with sequence length, batch size, and model depth. Existing approaches such as Multi-Query Attention (MQA), Grouped-Query Attention (GQA), Multi-Head Latent Attention (MLA), and Tensor Product Attention (TPA) reduce this cost through different trade-offs, but often sacrifice expressivity, require additional positional-encoding machinery, or impose restrictive low-rank structure. We propose Kronecker Product Attention (KPA), which represents key and value activations as sums of Kronecker products of compact, token-dependent matrix factors. KPA strictly generalizes TPA: rank-one vector-outer-product factorization arises as a degenerate Kronecker split, while non-degenerate matrix factors can represent richer block-structured patterns. We further show that a structured rotary embedding operator matched to the Kronecker representation preserves the relative-position property of RoPE while rotating only the compact factors, removing the need for a decoupled RoPE branch as in MLA. Empirically, KPA matches or exceeds TPA, MHA, MQA, GQA, and MLA across four model scales and nine downstream benchmarks under identical training conditions, while achieving up to 10x KV cache compression. The Kronecker head split is a tuneable hyperparameter that allows practitioners to navigate the compression-accuracy trade-off at design time without architectural changes.
memorybenchmark - arxiv:2610.12655 · cs.AICLEAT: Learning Value-Guided Clarification for Interactive AgentsJiatan Huang, Zheyuan Zhang, Ziming Li, Tianyi Ma +3
LLM agents can execute increasingly complex tasks, but effective assistance also requires aligning their actions with goals and constraints that users may leave unstated. We study this problem as interactive intent alignment through clarification. Yet clarification is useful only when the agent can turn the answer into better decisions. As training changes how the agent handles incomplete information and uses additional answers, the same clarification can become more or less useful. We introduce CLEAT (CLarification through valuE-guided Agent co-Training), a framework that co-trains a clarification-value controller and the task policy from shared interaction outcomes. We formulate residual query value to measure the task utility gained by asking rather than proceeding under the current policy, and estimate it through paired rollouts from the same interaction history. These paired returns train the controller to predict clarification value and the task policy to select useful questions and act on the answers. The controller guides subsequent rollout collection, while outcomes from the updated agent provide new value labels that allow clarification guidance to adapt as the agent learns. With Qwen3-4B, CLEAT achieves the highest mean score in all ten evaluation settings across four benchmarks. Gains over the strongest baseline reach 13.2 and 6.5 percentage points on UserGym Travel and IN3 underspecification judgment accuracy, respectively. Ablations show that co-training improves the task policy even when the controller is removed at inference, while adapting clarification guidance to the evolving policy yields further gains.
agentllm agentbenchmark - arxiv:2610.12654 · eess.SYSymbolic-Permutation-Based Direct Sparse Jacobian Assembly for Accelerated Power-Flow AnalysisTianshi Cheng, Venkata Dinavahi
The repeated assembly of the sparse Jacobian matrix constitutes a primary computational bottleneck in the Newton-Raphson power-flow analysis. Through an algebraic equivariance analysis of the Jacobian matrix, this paper proposes a direct sparse Jacobian assembly method based on symbolic permutation. By pre-applying the permutation to the admittance matrix during a one-time symbolic phase, the runtime bus-type projection overhead is entirely eliminated. Consequently, complex Jacobian differentiation and global matrix assembly fuse into a single operation, yielding a single-pass, branchless algorithm that streams values directly into contiguous memory. The framework is realized in the open-source RustPower solver. Benchmarks on IEEE test systems and PEGASE 9241 demonstrate that the proposed assembly is 24.4-30.1x faster than the MATPOWER- style baseline and 6.0-7.8x faster than the Schafer-Braun optimized assembly. End-to-end, the grid-level solve time is 11.7x-154.3x faster than pandapower 3.5.4 with Numba, while leaving numerical results and convergence behavior unchanged. Compared with the native C++ LightSim2Grid 1.0.0, grid-level performance is comparable on IEEE 39 and 1.3x-1.8x faster on IEEE 118 and the PEGASE systems. The method extends directly to general problems where a sparse Jacobian inherits its structure from a static network operator, including transient stability analysis, EMT simulation, and OPF Hessian assembly.
benchmark - arxiv:2610.12651 · cs.LGSynAct: Synergistic Active Feedback Learning for LLM AgentsNing Liu, Ian Li, Kristina Klinkner
LLM agents executing multi-step workflows fail in two fundamentally different ways: recoverable slips, which further attempts can repair, and knowledge gaps, which retrying cannot resolve. Expert feedback can address the latter, but expert attention is scarce. The key challenge is therefore not whether to ask for feedback, but where feedback can change the outcome. Existing approaches either avoid expert feedback, allowing agents to reinforce their own errors, or allocate feedback at the task level without identifying consequential decisions. We present SynAct, an active learning framework that treats expert attention as the binding constraint and allocates feedback at the level of individual decisions. SynAct ranks decisions by the mutual information between the selected action and the terminal outcome across repeated rollouts, queries an expert at the highest-value decisions, and distills the resulting corrections into transferable rules that the agent can reuse without expert access at deployment. We theoretically characterize what this signal identifies under finite repeated sampling: with k rollouts and at least m observations per action, outcome-constant decisions have zero mutual information, while outcome-separating decisions have mutual information at least H2(m/k) bits, yielding exact separation for any threshold t in (0,H2(m/k)). This also explains why success-based acquisition can be blind when all rollouts fail: success is constant even when failed runs reach different outcomes. Across four agent benchmarks and four models spanning three families, SynAct improves held-out accuracy in all 16 evaluated settings, by +11.7pp on average. The same signal transfers to inference-time routing, where SynAct outperforms budget-matched cascade, uncertainty, and expert-judge routers in 15 of 16 settings, while a single targeted correction outperforms seven additional unaimed retries.
agentllm agentagent benchmarkbenchmark - arxiv:2610.12650 · cs.CVFeature Competition and Its Representational Origins in Vision Language Models: Evidence from the Stroop ParadigmNurbüke Teker, Rui Xiao, Zeynep Akata, Shuchen Wu
When you ask a vision-language model (VLM) a question with an image, it answers your question based on the image. But to act means to choose: saying one thing means choosing to respond not say another. This becomes an issue when the image contains multiple features that equally relate to the question at hand: how would VLMs choose to respond? This problem is precisely studied by the classical Stroop task in psychology: among a set of deliberately designed images whose text and color conflicts (e.g., \textcolor{blue}{RED}), participants are instructed to report the color. We adapt this psychological paradigm to a benchmark and prompted a range of contrastive and generative VLMs on their behavior. Across models, we observe a persistent bias toward the feature of text in Stroop images: when text and color disagree, models preferentially generate responses centered to the text rather than color. We then opened the black box and examined the source of this bias and why certain features influences the model's behavior more than others. In the embedding space, we found that textual cues are represented more strongly and separably than color cues. This representational asymmetry predicts intervention success: steering models toward text-related directions is substantially easier than steering them toward color-related directions. Using a classical psychological paradigm, we demonstrate, at both behavioral and representational levels, that distinct features within the same image can exert unequal influence on VLM behavior. Our findings suggest that VLMs assign different degrees of saliency to different features within the same image, highlighting the need to understand how cue-specific saliency shapes their performance in widely used downstream applications.
benchmark - arxiv:2610.12646 · physics.opticsOptimal linear-optical interferometers for unitary t-designs in a multi-photon Fock spaceRobert A. Grinshtein, Ivan V. Dyakonov, Stanislav S. Straupe
We investigate the construction of unitary $t$-designs in a multi-photon Fock space on programmable linear-optical interferometers. Using the frame potential as the optimization objective, we identify architectures that realize approximate unitary 1- and 2-designs with considerably fewer controllable parameters than required for universal linear optics. For example, we find numerical evidence suggesting that for unitary 1-designs, the required number of programmable parameters scales empirically as $2d$ with the number of modes $d$, instead of $O(d^2)$. We benchmark the resulting ensembles using single-photon transition probabilities and average channel fidelities. Furthermore, as a practical result, we develop a photon-number estimation protocol for multi-photon Fock states that leverages these optimized 1- and 2-designs. Our findings demonstrate that shallow interferometers can accurately reproduce Haar-averaged first moments, while second-moment-sensitive observables provide a considerably stricter test for approximate unitary 2-designs.
benchmark - arxiv:2610.12642 · cs.ROPriMoRetarget: Humanoid Motion Transfer Through Prioritized Motion RetargetingNicholas Ioannidis, Dun Yang, Max Smith, Tue Vu +3
Motion retargeting is a critical preprocessing step for transferring human motion data to humanoid robots. While existing methods are effective for single-character motions, interactions involving multiple characters and objects introduce additional contacts and spatial relationships that must be preserved. Retargeting is commonly formulated as a weighted multi-objective optimization problem, where conflicting objectives can require careful tuning of relative weights and can still compromise important motion characteristics. We introduce PriMoRetarget, a prioritized motion-retargeting framework that replaces relative objective weighting with an explicit priority hierarchy. Lower-priority updates are constrained to preserve higher-priority objectives, allowing critical characteristics such as foot placement and interaction contacts to take precedence over lower-priority pose objectives. The method is evaluated on four datasets spanning single-character motion, character-object manipulation, and character-character interactions. The resulting motions better preserve task-relevant interactions and provide reference trajectories that can be tracked more reliably than those produced by widely used retargeting methods.
manipulationhumanoid - arxiv:2610.12638 · cs.LGMachine Learning and Time-Series Foundation Models for Day-Ahead Electricity Forecasting in a University BuildingAmey Vasulkar, Samuel Kernan Freire, Arie-Willem de Leeuw, Tadeo-Baldiri Salcedo-Rahola
Day-ahead electricity forecasts can help building operators schedule heating, ventilation, and other services around anticipated demand. Choosing a forecasting model also requires balancing accuracy with its forecast-time inputs, local training, and computational requirements. We benchmark statistical, machine-learning, recurrent neural-network, and pretrained TimesFM models for a university building. We use chronological validation and evaluate all configurations on the same 57 test days, comparing accuracy across workdays, weekends, and holidays alongside local fitting and forecasting time. Weather covariates use retrospective observations. TimesFM 3.0 with covariates achieves the lowest overall errors, reducing mean absolute error by approximately 43\% relative to weekly seasonal-naive forecasting. XGBoost remains competitive, although paired daily comparisons do not establish a clear mean-absolute-error advantage for TimesFM. TimesFM also performs strongly using only past electricity consumption. Adding covariates improves its holiday forecasts but slightly worsens workday and weekend forecasts, leaving overall mean absolute error almost unchanged. TimesFM requires no building-specific weight training, while XGBoost offers rapid local fitting and inference. The evaluated LSTM takes longer to fit without outperforming either approach. An exploratory historical evaluation reveals seasonal variation, while a separate weather-source comparison produces only small changes in the selected TimesFM configuration's accuracy. These results support pretrained TimesFM as a strong initial forecasting baseline for this building, with XGBoost as a competitive locally fitted alternative. Covariates are particularly useful when improved holiday forecasts justify the additional input preparation.
benchmark - arxiv:2610.12637 · cs.RODistributed Harmonic-Covariance Feedback for Hole Closure in Planar Robot SwarmsJitian Liu, Subhrajit Bhattacharya
We consider hole closure in a planar multi-agent system whose sensing disks form a time-varying Čech complex. We propose a harmonic-covariance feedback that uses harmonic edge signals to locate holes and converts those signals into agent forces. For distributed evaluation, we use a fixed-degree polynomial of the regularized Hodge Laplacian. This polynomial is evaluated through local operator applications. The closed loop has a unique global trajectory from every safe initial state. The model data and initial state are supplied with procedures for approximation to any requested accuracy with explicit error bounds. We assume that hole area is measurable and bounded, holes evolve continuously without splitting or merging, and only finitely many temporary new holes appear. Under these conditions, offline finite calculations produce rational lower bounds for the cumulative hole area on the time horizon without querying trajectory data. These bounds converge to that cumulative area, whether finite or infinite. If it is finite, holes close in the time-averaged sense: the average normalized hole area over every fixed-length time window tends to zero as time tends to infinity. In a 15-second numerical demo, all holes close by 9.9s and remain closed through the end.
agentmulti-agentagent system - arxiv:2610.12636 · cs.ROSelectively Actuated Fiberbots for High-precision Minimally Invasive SurgeryJinshi Zhao, Libaihe Tian, Alex Ranne, Qindong Zheng +8
Long, slender instruments are essential for minimally invasive surgery (MIS), but achieving precise distal manipulation becomes increasingly difficult when actuation extends along the entire instrument. Here, we present an electrothermally actuated fiber-based robot designed for MIS procedures, in which Joule heating is concentrated in the distal active segment. The fiber is fabricated using a thermal drawing process and uses embedded metallic wires for thermal actuation. This robotic fiber, 1.9 mm in diameter and 1.2 m in length, can precisely manipulate surgical laser fibers with positional precision below 100 $μ$m. The compact size of the fiber robot allows it to pass through the working channel of a flexible endoscope, while keeping both devices mechanically uncoupled to allow independent motion. A phantom demonstration combining the robotic fiber with a da Vinci instrument conceptually demonstrated its compatibility with existing endoscopic systems for clinical applications. Our robotic fiber enables precise distal motion and holds the potential to improve clinical outcomes by enhancing precision in MIS procedures.
manipulation - arxiv:2610.12625 · cs.CVForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video DiffusionZekai Gu, Peng Wang, Jiahao Lu, Yongsen Mao +2
Autoregressive video diffusion models have become a leading approach to real-time interactive video generation and video world modeling. However, existing methods typically allocate computation uniformly across space when generating the next video chunk, updating all patches with the same denoising schedule and number of function evaluations. This ignores the spatial heterogeneity of video content: static, simple, or recurring regions are often easier to denoise, while other regions require further refinement or additional context. A uniform budget thus leads to redundant computation on easy patches, whereas reducing the fixed step count can leave difficult patches insufficiently refined. We introduce \methodname{}, a general framework that dynamically allocates denoising steps to individual patches: easy patches stop early to improve efficiency, while difficult patches receive more refinement steps. This design accelerates generation with negligible quality degradation. Our method is compatible with most existing few-step autoregressive diffusion models, requiring only a lightweight routing module with modest training. Experiments demonstrate that \methodname{} reduces the total number of denoising steps applied across video patches by about 50\% while maintaining visual quality comparable to the four-step baseline.
world model - arxiv:2610.12624 · cs.CVMemReg: Streaming Outdoor LiDAR Point Cloud Registration with Hybrid Memory BuffersJiuming Liu, Mengmeng Liu, Guangming Wang, Lihao Liu +5
Prior outdoor LiDAR registration works are commonly limited by the pair-wise input paradigm, which neglects temporal correlations inherent within streaming sequences. In this paper, we propose a novel multi-frame outdoor point cloud registration network for streaming LiDAR scans enhanced with pose-related memory buffers. The key observation is that long-term temporal LiDAR sequences can provide rich global contextual information to complete sparse measurements, filter outliers, and address low-overlap problems, thereby boosting registration performance. Specifically, two hybrid memory buffers are designed, including an implicit memory feature buffer and an explicit memory pose buffer, to store and dynamically update pose-related temporal features. Moreover, a novel dynamic history weighting module is developed to adaptively fuse current and history pose-related features. Extensive experiments on three outdoor datasets, including KITTI, nuScenes, and Apollo-Southbay, demonstrate state-of-the-art performance of MemReg, surpassing all previous pair-wise methods and also multi-frame SLAM systems. Our method also generalizes surprisingly well to multiview indoor registration scenarios with rather competitive performance on 3DMatch, 3DLoMatch, and ScanNet. Code will be released at https://github.com/IRMVLab/MemReg.
memory - arxiv:2610.12617 · cs.CLGeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence ReportsVeronika Solopova, Ivan Havlytskyi, Viktoria Skorik, Ostap Vykhopen
Geopolitical and strategic intelligence reports constitute a rich source of expert knowledge and have increasing value in the current political climate, but their heterogeneity and analytical complexity pose challenges for retrieval-augmented question answering. We introduce a benchmark for grounded question answering over 415 open-source geopolitical and strategic intelligence reports, comprising 5,525 document-grounded question-answer pairs spanning factual, inferential, comparative, and risk-oriented questions. We propose a document-aware generation pipeline that profiles reports before generating questions and validate dataset quality through expert annotation and an LLM-as-judge protocol. Using the benchmark, we evaluate 15 retrieval systems and six open-weight LLMs for RAG. We find that models perform similarly on document-level retrieval, while at the harder chunk level retrieval quality is not driven by embedding-model scale: bge-m3, a mid-size open encoder matches an order of magnitude larger ones and outperforms commercial embedding APIs. In contrast, answer generation remains challenging even given the gold evidence, particularly for inferential and risk-oriented questions.
retrieval-augmentedbenchmarkllm-as-judge - arxiv:2610.12611 · cs.MASoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software EnvironmentsTian Jin, Wenhao Wang, Jing Kang, Haoting Shi +3
Computer-use agents (CUAs) are rapidly improving, yet synthesizing diverse and reliable software environments at scale remains challenging. Native application environments require substantial construction and integration effort, which limits application coverage and increases the risk of application-specific overfitting. Browser-hosted environments provide limited interaction depth and workflow complexity. These limitations motivate SoftwareGym, an automated pipeline for synthesizing GUI software environments with diverse interfaces, executable functionality, and runtime-verified behavior. It generates structurally diverse designs, realizes them as runnable applications, and uses GUI evaluation with iterative repair to ensure functional reliability. Using SoftwareGym, we synthesize 182 applications across twelve categories and achieve a mean GUI task pass rate of 91.5%. We construct SoftwareGym-Bench, a 120-task evaluation suite spanning the same twelve categories, and use trajectories collected from these environments for CUA training. The resulting model improves Pass@3 from 41.39% to 56.97% on the strictly out-of-domain OSWorld benchmark and achieves 40.0% on SoftwareGym-Bench. These results demonstrate the potential of synthesized software environments as scalable and transferable supervision for CUA training.
agentbenchmark - arxiv:2610.12609 · cs.ROGraph-Based Heuristics for Minimum Constraint Removal in Cluttered Robot Motion PlanningAntony Thomas, Fulvio Mastrogiovanni, Marco Baglietto
Humanoid and service robots operating in clut- tered human environments may encounter motion planning problems that are infeasible when all surrounding objects are treated as fixed obstacles. The Minimum Constraint Removal problem, which we refer to as MCR, addresses this situation by identifying the minimum number of constraints, such as movable objects, whose removal enables a collision-free path. However, computing an optimal MCR solution is NP-hard. In this work, we propose a graph-based heuristic pipeline that combines bidirectional feasible-set generation with fixed- length searches over reduced MCR graphs. We further derive an extended feasible-set generator for instances in which the candidates produced by the first generator do not contain a complete optimal removal set. Across six benchmarks, the evaluated pipeline matches the exact solution in three cases and, in the remaining cases, selects at most 31.25% more obstacles than the optimum, while being between 3.4 and 33.7 times faster than exact search. In one of the benchmarks, involving a manipulation task amidst clutter, selecting two rather than seven obstructing objects reduces the combined MCR, inverse- kinematics, and motion planning time from 84.72 s to 30.59 s. These results indicate that the proposed approach provides a practical compromise between computational efficiency and solution quality for motion planning among movable obstacles.
manipulationhumanoidbenchmark - arxiv:2610.12601 · cs.CLReflective Prompt Optimization of a Deep-Research Agent: A Topic-Disjoint, Multi-Seed Protocol for Measuring Transferable Gains and Prompt-Level OverfittingElias Lumer, Sahil Sen, Vamse Kumar Subbiah, Kevin Paul
Prompt optimization is an attractive alternative to reinforcement learning for adapting language-model agents, since it is cheap and produces human-readable artifacts. On factual tasks, however, it carries a failure mode that scalar-reward reinforcement learning does not. An optimizer that reads the training examples can write their answers into the prompt, so an in-distribution gain may be memorization rather than transferable behaviour. We apply reflective prompt evolution (GEPA) to the two system prompts of a multi-agent deep-research agent and evaluate it under a topic-disjoint split in which no topic is shared across train, validation, and test. Held-out citation reward rises by 0.079, from 0.702 to 0.781, with a bootstrap 95\% confidence interval of [0.051, 0.107], and the gain replicates across three seeds (mean 0.107). Nearly half of the winning prompt is a memorized answer key, yet a controlled ablation shows this content earns no reward even on the exact training questions it encodes. The large validation-minus-held-out gap is therefore small-sample selection under a noisy judge, not memorization. Varying the verifier isolates what makes the gain transfer. Decomposed per-dimension feedback is the causal ingredient, and collapsing it to a single scalar reward makes held-out transfer negative. The gain persists under an out-of-family judge and is largely reproduced by a hand-written version of the discovered recipe. Credible evaluation of prompt optimizers therefore requires held-out topics, multiple seeds, and verifier ablations. We release the candidate prompts, lineage diffs, figures, tables, and analysis.
agentmulti-agent - arxiv:2610.12599 · cs.LGSTAPLE: Static Sparse Upcycling of Pretrained Checkpoints via Embedding ModulesRanajoy Sadhukhan, Euijin Hong, Sheng Cao, Zechun Liu +8
Sparse computation can scale the parametric capacity of LLMs without proportionally increasing active computation, but pretraining sparse architectures remains expensive and data-hungry. Existing sparse upcycling methods mainly target Mixture-of-Experts models, where expert homogeneity, sample inefficiency, and system overheads can limit practical scalability. Static sparse memory offers predictable access and token-specific updates that can help address these challenges, but naively integrating it into pretrained computation yields poor returns. In this work, we introduce STAPLE, a recipe built upon STEM for integrating static sparse memory into pretrained models. Whereas STEM replaces FFN up-projections with token-indexed embeddings, STAPLE retains them and adds the embeddings as a residual pathway, preserving pretrained computation while learning complementary token-specific information in a scalable manner. On OLMo-2 1B, STAPLE improves over continued dense training by 4.27 points on HumanEval, 2.80 on MBPP, 2.27 on GSM8K, and 1.65 on DROP. Average performance increases with static capacity, and improvements persist on the larger OLMo-2 7B backbone. STAPLE also outperforms static sparse baselines such as STEM and an Engram-style model, and achieves a higher average score than an MoE upcycling baseline while decoding 2x faster with less than half its GPU model memory and measured GPU energy per token in our throughput-oriented decoding evaluation. Importantly, despite introducing billions of parameters late in training, our host-offloaded implementation keeps generation throughput within 1.5% and training throughput within 3% of the dense baseline, while caching only the ~5% most frequent embeddings on GPU. These results show that static sparse memory can provide a sample-efficient, scalable, and sustainable path for expanding pretrained models without sparse pretraining from scratch.
memory - arxiv:2610.12596 · cs.LGSpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the SpireScott C. Lowe, Sander W. Keemink
Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short and episodic, and performance on long tasks is hard to dissect into stored knowledge, reasoning and luck. We introduce SpireBench, in which models play the complete commercial deck-builder Slay the Spire (StS), where early decisions decide long-term success. Across 20 large language models (LLMs) at the game's highest difficulty, frontier models beat heuristic baselines and match the average human player but remain far behind experts. This gap widens as the run lengthens: the strongest models win the first act as often as experts, then fall behind. What separates strong models from weak is how well they play each fight; all of them misjudge risk over a run, preserving health rather than spending it to grow stronger. A comprehensive, self-consistent renaming of every game term shows that part of their performance rests on prior knowledge of the game, and models do not improve from the memories they write across runs, which are often wrong and overly cautious. Our harness is the first to give a model the complete original game, and we compare it with existing harnesses. Overall, SpireBench offers an unsaturated long-horizon benchmark with tools to locate where and why agents fail.
agenticbenchmark - arxiv:2610.12593 · cs.AIKnow What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop LearningWei Yang, Qing Ping, Youzhi Luo, Yawei Wang +3
The continued improvement of large language models increasingly depends on synthetic experience, yet effective data synthesis for interactive agents requires not only executable and verifiable trajectories, but also interactions that provide learning value for the current task agent. Existing methods increasingly incorporate environment feedback, data validation, or learner failures, but still face a feedback-to-decision gap: observed weaknesses do not directly specify how future synthesis should change, or whether they can be represented by the current synthesis space. To address this gap, we propose EvoSyn, a learning-feedback-driven multi-agent framework that organizes synthesis around a revisable state specifying what interaction factors can be deliberately generated and where synthesis effort should be allocated. A role-specialized multi-agent system translates learner feedback into synthesis revisions, while a Designer allocates synthesis directions and a Planner grounds them into executable experience. This process enables within-space adaptation toward weak or under-covered regions and synthesis-space expansion that promotes newly discovered factors into explicit generation controls. Experiments on $τ^2$-Bench and CAR-Bench show that EvoSyn improves average task success by 13.3 points over the strongest synthesis baseline, while producing higher-quality and structurally broader synthetic experience and discovering controllable factors missed without learner feedback.
multi-agentagenticagent frameworkagent system - arxiv:2610.12586 · cs.LGRealism VS Accuracy: Event Sequence Forecasting from a Generative Modeling PerspectiveDmitry Osin, Egor Surkov, Petr Mokrov, Igor Udovichenko +4
Event sequences are chains of random events, each described by heterogeneous (numerical and categorical) features. The problem of event sequence forecasting occurs in finance, healthcare, business process intelligence, and other fields. In this work, we study multi-horizon forecasting of event sequences as a conditional generative modeling problem. We evaluate forecasts not only for prediction accuracy, but also for distributional realism. To this end, we present a benchmark comprising metrics for both quality aspects, strong statistical baselines, recent models adapted from adjacent fields, and curated real-world datasets. Careful evaluation reveals that no method excels at both accuracy and realism, highlighting a fundamental trade-off between the two. Finally, we introduce Wasserstein BaryBooster, an algorithm that aggregates samples from a realism-strong diffusion model into a state-of-the-art predictor, demonstrating that distributional realism can be converted into prediction accuracy. Code is available at https://github.com/xaosina/event-sequence-forecasting.
benchmark - arxiv:2610.12582 · cs.CLOne Model to Loop Them All: Elastic Latent Recurrence for Language ModelsFaisal Ladhak, Shantanu Acharya, Santiago Akle Serano, Simeng Sun +2
A latent recurrent language model applies a shared block of layers repeatedly, so one checkpoint can trade inference compute for accuracy by changing the loop count. At one loop, however, such models typically fall well short of a non-recurrent model of the same size, a one-loop tax that makes a separate non-recurrent model the better choice whenever latency matters. We present Elastic Latent Recurrence (ELR), a recipe for training looped language models without this tax. At one loop, an ELR model costs the same to serve as a non-recurrent model of the same size and, trained on the same data, reaches similar accuracy. Each additional loop then buys more accuracy for more inference compute. Three choices make this work: a gated state update with a learned step size, loop counts mixed within each optimizer update, and conditioning each pass on its loop index and budget. The first two preserve one-loop accuracy, and the third lowers loss at every additional loop. Mixed depths can be introduced late in pretraining to limit the added training cost, and with zero-initialized conditioning added at the switch, this late schedule reaches lower loss than mixed-depth training from scratch. In MoE models, reusing first-loop expert routes on later loops cuts mixed-depth update time by 11.7% with no measurable change in accuracy. At inference, keeping only the last loop's attention KV cache holds attention KV memory at its one-loop level while retaining most of the gain from additional loops. On 4B dense and 30B-A3B MoE hybrid models, ELR at one loop is 0.52 points below and 1.04 points above its matched baseline on a ten-task average, and four loops add 7.25 and 4.75 points. Carried through post-training, the recipe yields Koi-4B, a single checkpoint that scores an estimated 18 on the Artificial Analysis Intelligence Index at one loop, matching Qwen3.5-4B, and 29 at four loops.
memorypost-training - arxiv:2610.12575 · cs.ROMind the Temporal Gap: Evaluating Video Models for Temporal Understanding in DrivingShiva Sreeram, Erfan Aasi, Tsun-Hsuan Wang, Alaa Maalouf +1
Modern video-language models are increasingly treated as general-purpose video reasoners, yet it remains unclear whether they robustly capture temporal dynamics in safety-critical settings such as driving. We study this question through controlled ego-motion tasks that require identifying actions from driving videos. Across video-language models, we find that standard prompting, visual prompting, few-shot prompting, and chain-of-thought prompting remain unreliable and highly task- and model-dependent, with persistent class biases, although newer models show substantial task-specific few-shot gains. In contrast, lightweight LoRA finetuning and simple probes trained on intermediate visual features recover strong motion-discriminative performance, indicating that motion-relevant cues are often present inside the models but are not reliably used by the final video-to-language pathway. These results suggest that, in driving, current video-language models remain unreliable temporal reasoners and often behave more like frame-level, bias-driven recognizers than dependable temporal world models.
world model - arxiv:2610.12571 · cs.LGAn all-transistor physical-learning transformer can be trained to perform in-context learningMichael C. Abbott, Benjamin B. Machta
Most systems trained by equilibrium propagation or coupled learning are in the same class as multi-layer perceptrons: while they may be universal function approximators, they struggle to learn associative tasks which are easy for transformers. Equilibrium propagation relies on a bidirectional flow of information through the physical system between input and output. The reverse flow is broken by more complex nonlinear systems, such as those performing multiplication which is needed to express dot-product attention. Here we explicitly restore this bidirectional flow by introducing extra circuit elements for this purpose into a double or dyadic circuit. We then use these ideas to construct an attention mechanism exploiting the exponential current law of sub-threshold MOSFET devices. We show that in simulations this circuit can be trained to perform a simple in-context learning task, despite using realistic reverse components which transmit only an approximate gradient. For this training to succeed we need cross-entropy loss (not mean squared error). We generate nudges appropriate for this loss using a novel floating circuit element, based on the same MOSFET sub-circuit used for softmax. We train the resistors in this circuit using the Lion optimiser, which can be implemented using one capacitor per parameter to store local memory of past gradient estimates.
memory - arxiv:2610.12570 · cs.CLContextual Correction of Parallel Draftsfor Speculative DecodingRoy Eisenstadt, Harel Lidar, Tal Gonen, Omer Luxembourg +4
Speculative decoding accelerates large language model inference by using a lightweight drafter to propose multiple tokens that are subsequently verified in parallel by the target model. Recent diffusion-based drafters make this paradigm particularly attractive: deep attention-based neural backbones provide strong predictions, while drafting multiple future positions in parallel avoids the sequential cost of autoregressive generation. This parallelism, however, comes at a cost. Tokens within a draft block are predicted without access to the realized identities of preceding draft tokens, removing intra-block dependencies that would naturally be available under autoregressive generation. We introduce DCOCO (DFlash Contextual Corrector), a lightweight mechanism that restores these dependencies while preserving parallel drafting. Rather than committing to each position's top prediction, DCOCO retains multiple candidate tokens and evaluates their contextual compatibility across adjacent draft positions in parallel, enabling contextually informed token selection at low additional cost. Across four verifier backbones and ten benchmarks, DCOCO achieves the highest average throughput in every evaluated configuration, spanning greedy and stochastic decoding with and without extended reasoning, with speedups of up to 6.6x over vanilla decoding. Its advantage persists under concurrent serving: DCOCO outperforms the strongest competing method by 6-23% across 4-32 concurrent requests, while other sequential correctors fall below uncorrected DFlash at these loads. These results demonstrate that recovering intra-block dependencies through parallel contextual scoring delivers consistent acceleration across decoding regimes and serving loads.
benchmark - arxiv:2610.12569 · cs.CLSWE-Duel: Towards a Self-Scaling Arena for Coding AgentsWei Minn, Zhensu Sun, Lwin Khin Shar, David Lo
Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue that a benchmark should instead aim to be self-scaling: its tasks and oracles are created at evaluation time, so no content exists in advance to leak, and its difficulty is set by the participating agents rather than fixed at release. We introduce SWE-Duel, an arena in which two coding agents evaluate each other over mirrored Red-Blue turns. In each turn, the Red agent works on a real repository across three context-isolated sessions. It proposes and implements a new feature with feature tests, then embeds a subtle bug in that feature along with sealed bug-triggering tests. The resulting pull request is admitted only if (1) it passes the feature tests and the repository's existing tests while failing exactly the bug tests, and (2) a fresh session of the same agent can repair the bug blind, which rules out unsolvable tasks. The Blue agent then reviews the pull request without being told a bug exists. It wins only if its revision passes all three test suites, and then the two agents swap roles. We run a tournament among 11 model-harness participants on 15 repositories in five languages for 1,500 turns. The leaders win in different ways. GPT-5.5 with Codex CLI ranks first as the strongest solver, repairing 98.3% of the defects it reviews. Claude Opus 4.8 with mini-swe-agent ranks second as the strongest task author, with a 27.3% Red win rate. Finally, within one model family, tasks written by the newest version defeat a fixed-reference solver far more often than those of older versions (42.9% vs. 4.0%), giving preliminary evidence that task difficulty scales with task authoring capability.
agentbenchmarkarena - arxiv:2610.12568 · cs.CVMIRAGE: Metric Inference and Reliability-Aware Gaussian Estimation from Feed-Forward VisionXinzhe Wang, Changjian Jiang, Kaiwen Song, Xudong Li +7
Feed-forward 3D priors enable high-quality reconstruction from image streams but often lack reliable metric scale and suffer from long-term trajectory drift. In contrast, LiDAR--inertial estimation provides metrically accurate motion but lacks the image-space consistency needed for high-fidelity reconstruction. We propose $MIRAGE$, which anchors feed-forward visual geometry to LiDAR--IMU metric motion and regulates online pose corrections according to correspondence support and cross-modal agreement, jointly enabling accurate metric pose estimation and high-fidelity Gaussian reconstruction. Experiments on Oxford Spires, M2DGR and INS show that MIRAGE achieves accurate metric trajectory estimation, outperforming COLMAP, a widely used but computationally expensive reference for vision-only benchmarks. Motivated by the scarcity of long-horizon monocular benchmarks for large-scale indoor reconstruction, we further build a multimodal data-collection platform and use MIRAGE to establish accurate 6-DoF reference trajectories for a new vision-only benchmark. We benchmark recent monocular large-scale reconstruction methods on this dataset, providing a systematic evaluation of their performance in long-horizon indoor scenes.
benchmark - arxiv:2610.12567 · cs.ROCASTER: Formalizing Zero-Shot Manipulation from Synthetic Videos as Constrained OptimizationYinlong Dai, Homanga Bharadhwaj, Dylan P. Losey
Prior research on learning from humans often requires real human demonstrations. But advances in video generation models offer a new paradigm: we can now prompt these generators to make synthetic videos of the task. On the plus side, these synthetic videos take place in the robot's current environment, and do not require actual human teaching. However, while the generated videos appear to show plausible motions, they lack both physical consistency and robot grounding, and thus the robot cannot directly roll out the trajectory shown by the video. In this paper we seek to formalize the process of going from synthetic video generation to real-world robot trajectories for zero-shot manipulation tasks. We recognize that this problem is an instance of constrained optimization. The object trajectories extracted from the synthetic video provide an initial guess at the correct motion, and the robot must refine these trajectories (for instance, within a digital twin) while enforcing physical feasibility and semantic consistency. Our optimization-based formalism provides insights into the video generation properties necessary for success. Specifically, we show that the video generation must probabilistically seed the search within a semantic basin of attraction where the trajectory can be locally modified without losing its task alignment. Our analysis further reveals that state-of-the-art approaches can be viewed as instances of our unified formalism with key simplifications. In our experiments we remove these simplifications to more closely match the underlying optimization, leading to more robust zero-shot trajectories from synthetic videos and improving average task success by 34.1% compared to the best-performing baseline. See videos at our project website: https://collab.me.vt.edu/CASTER
manipulation - arxiv:2610.12566 · cs.LGSample-Adaptive Zeroth-Order Post-TrainingHaiyuan Wan, Yanyi Li, Weicheng Lin, Cong Fang
Zeroth-order (ZO) optimization offers a memory-efficient alternative to backpropagation for fine-tuning large language models. However, existing ZO methods typically sample training examples uniformly, overlooking their evolving importance and leaving avoidable estimation variance. To address this limitation, we propose Sample-Adaptive Zeroth-Order Optimization (SAZO), which learns sample importance online and adaptively allocates queries to accelerate convergence. SAZO extracts gradient-norm information from existing directional differences to estimate sample importance without access to true gradients. Furthermore, to track evolving importance from sparse minibatch feedback, SAZO maintains per-example exponential moving averages that aggregate observations across updates. The method requires no additional model evaluations and only $O(N)$ additional scalar state compared with MeZO. We prove that SAZO asymptotically matches the leading convergence term of the minimum-variance sampling oracle, and achieves a strictly faster convergence rate than standard methods. Extensive experiments across four model families demonstrate improved average downstream performance and up to $6\times$ faster convergence to the same training loss in terms of query count.
post-training - arxiv:2610.12561 · cs.ROWhat Should Embodied Agents Remember? Benchmarking and Evaluating Memory Modality for Embodied AgentsJunxiang Wang, Yuchen Liu, Yi Wu, Guofei Chen +5
Memory allows large language model (LLM) agents to use past experience, often stored as textual records, when responding to requests. For embodied agents that control robots, visual and spatial observations introduce a broader choice of memory modalities, affecting both the information available for subsequent tasks and the model inference costs of constructing and using memory. We introduce MeMoREval, a benchmark for studying this problem through a controlled experience-request protocol. Agents first experience a sequence of events without knowing the subsequent tasks, and subsequently they use memory to respond to information and action requests without receiving new observations. The benchmark comprises 53 tasks across four simulated indoor environments and measures task success alongside the inference costs of memory construction and use. Our reference evaluations reveal that storing frames outperforms storing generated descriptions at lower write-time inference cost for the primary model, while storing frames with scene graphs achieves the highest aggregate task success for every tested model. Extensions to accumulated experience, selective frame retention, and visual input to memory writers demonstrate how the benchmark accommodates further memory-design investigations. Two physical-robot demonstrations establish the feasibility of applying its protocol beyond simulation.
embodiedmemoryscene graphembodied agentbenchmark - arxiv:2610.12558 · cs.ROPanTact: Teaching Whole-Body Dexterity with a Wearable Contact InterfaceXiaomeng Xu, Han Zhang, Zhian Ruan, Xiaofeng Guo +5
Humanoid robots have many degrees of freedom and contact surfaces, yet most loco-manipulation research restricts manipulation to the hands and avoids other body contacts with the environment. To extend manipulation beyond the hands, we present PanTact, a system that learns humanoid whole-body dexterity, the capability to manipulate with any suitable body surface, directly from robot-free human demonstrations. Our key idea is to use contact as manipulation-centric information that transfers across embodiments. Contact locations and timing specify the interactions needed to accomplish a task, while the robot chooses how to coordinate its body to realize them within its own physical constraints. Specifically, PanTact captures, learns, and executes whole-body contact via: 1) a wearable, robot-free data collection interface that augments egocentric vision and bimanual UMI grippers with whole-body modular contact patches to record body contact locations and states; 2) a visuomotor policy that mitigates the egocentric observation gap and predicts whole-body contact goals; and 3) contact-aware whole-body control formulations that realize active contact goals using suitable robot surfaces. We deploy PanTact on a Unitree G1 humanoid without additional body contact sensors, demonstrating whole-body dexterity involving body support, pushing, sweeping, and load-sharing. Website: https://pantact.github.io
manipulationhumanoidwhole-body controlgripper - arxiv:2610.12549 · cs.ROFly-by-Code: Embodied Coding Agents for Aerial Manipulation with Active Visual and Physical FeedbackJaewoo Lee, Jeongyeon Seo, Sihyun Cho, Gyeongrak Choe +9
Embodied coding agents construct robot policies from natural-language instructions by generating executable programs and refining them from execution feedback. This refinement assumes that execution feedback reveals whether the task succeeded and, after a failure, provides sufficient evidence to guide program revision. Aerial manipulation violates this assumption in two ways. Payload constraints restrict onboard camera coverage and leave task-critical outcomes outside the robot's view (partial observability), while strong dynamic coupling and limited control margins make physical interactions fragile (limited interaction robustness) and leave failure causes unresolved. Re-examining the same feedback cannot recover observations that were never collected or separate failure causes that the available evidence does not distinguish. To acquire this missing evidence, we introduce Active Feedback (AF), an active "View and Probe" framework. When execution feedback leaves unresolved questions, the agent synthesizes a separate diagnostic program that runs in simulation to inspect unseen outcomes from informative viewpoints (View) or test hypotheses about failure causes through targeted physical interactions (Probe). Across six simulated aerial manipulation tasks with 60 trials per condition, AF reduces false completion declarations from 25 to 5 and raises final task success from 31.7% to 75% compared with terminal feedback under the same coding-agent configuration and task-execution limit. Using shared robot APIs, task programs refined with AF in simulation run on a physical aerial manipulator without task-program source-code modification and complete multi-stage manipulation tasks in the real world. These results show that executable diagnosis fills gaps in execution feedback for embodied coding agents, improving both completion assessment and program refinement in aerial manipulation.
embodiedmanipulationmanipulatoragent - arxiv:2610.12545 · cs.LGAutoIndexer: Flexible-Order Decoding by Training Causal Models on Chains of EditsShu Ishida, Aliasghar Khani, Tianyu Zhang, The Cong Luong +2
Autoregressive decoding is less suited to non-causally ordered data, e.g., cross-references or future dependencies, since their outputs cannot be revised post hoc, unlike iterative human reasoning. Diffusion LLMs partially mitigate this limitation but still cannot flexibly insert or remove arbitrary numbers of tokens from a pre-generated context. We design AutoIndexer as a generative model with a novel training and decoding mechanism that simulates a Chain of Edits, allowing the model to flexibly modify its prior outputs in hindsight via token insertions, substitutions, and deletions. The model learns to predict marker tokens for opening and closing edits, simultaneously moving a cursor to positions in the existing token sequence, analogous to a text editor. Training sequences are obtained by perturbing ground-truth labels with inverse chained edit operations, and the model learns to edit by undoing those inverses. The perturbation training allows AutoIndexer to be robust to erroneous context and adaptable to editing tasks such as code correction. We demonstrate that our method exhibits post-generation context-editing capabilities that most autoregressive and diffusion models lack without compromising performance on standard LLM benchmarks. The code is available at https://github.com/AutodeskAILab/autoindexer.
benchmark - arxiv:2610.12536 · cs.AIEliteTable: Self-Improving Program Search for Executable Control PoliciesStuart Farmer
EliteTable is a self-improving program-search algorithm guided by large language models (LLMs) that uses a fixed-capacity table of high-scoring solutions to guide new proposals, edits of existing solutions, and remixes of several solutions. Performance was evaluated across six Gymnasium control tasks, each with ten generations and fifty candidate slots per generation. Each task was evaluated across ten independently initialized searches. Candidate-score medians rose between the first and final generations in all six tasks, and selected-winner search-score medians rose in five. In CartPole-v1, the selected winner reached the search-score ceiling in the first generation of all ten searches. All ten paired held-out endpoints improved in four of the six tasks. BipedalWalker-v3 and CarRacing-v3 improved without reaching their reporting targets. Six of ten Acrobot-v1 searches declined on held-out episodes, and the median paired change was negative. The results document improvement during program search and the transfer of selected-winner gains to new episodes in some tasks. Comparisons and ablations are needed to establish EliteTable's relative performance and the contributions of its components.
self-improving - arxiv:2610.12527 · cs.LGBehind-the-Meter Photovoltaic Visibility from Net Smart Meters: Deployment Regimes and Operational InsightsJack Zheng, Hao Wang
Distribution operators need visibility of behind-the-meter photovoltaic (PV) generation, yet most residential customers are observed only through net smart meters. Deep-learning-based PV disaggregation can restore this visibility, but its operational value depends on whether the model serves known customers, new customers, future periods, or new regions. We quantify this dependence using four deployment regimes that separate household transfer from temporal extrapolation, applied to Ausgrid smart-meter data with cross-dataset adaptation to the Pecan Street data. Using a fixed training protocol, we benchmark representative deep sequence architectures for PV disaggregation under regime-matched evaluation. At a fixed 48-hour context length, daylight mean absolute error (MAE) of the best model rises from 0.104~kW on seen households in the future test period to 0.185~kW on unseen households over the same period, and under a fixed training contract the deployment regime explains far more of the error variation than model choice. Under target-domain normalization, fine-tuning on five target-region households reduces source-model transfer error by 28\%--36\%. Long input windows help known-customer extrapolation, while their new-customer benefits vary by model. These findings suggest regime-matched error budgets, limited target supervision for model adaptation in new regions, and use-case-dependent context selection for energy data analytics.
benchmark - arxiv:2610.12522 · cs.LGMolP2SBench: Do LLMs Really Reason from Molecular Properties to Structure?Yuhang Xie, Zhiyi Shi, Zeyi Zhang, Zhisheng Qi +3
Large language models (LLMs) are increasingly used in molecular discovery and structure elucidation, where decisions depend on physical observations. Existing evaluations primarily focus on end-to-end molecular reconstruction, where correct predictions do not necessarily indicate reliance on the supplied properties. We introduce MolP2SBench, a benchmark for molecular property-to-structure (P2S) reasoning in LLMs. Each task presents a masked molecular scaffold with given properties and asks the model to select the missing structure from plausible candidates. We shuffle or replace properties to test reliance on correct property-structure pairing and responsiveness to counterfactual property changes. A channel-wise leaderboard uses Property-Grounded Recovery (PGR), giving equal weight to source and counterfactual recovery. Evaluating seven models, we find that LLMs can use physical properties for structure prediction, but performance varies substantially across property types. Higher accuracy with a property does not necessarily imply greater responsiveness to it: a model may benefit more from $^1$H NMR than from $^{13}$C NMR, yet be less likely to change its prediction when the $^1$H data is replaced. LLM performance also need not reflect the relative difficulty of these properties for human chemists. Although UV-Vis spectra provide less direct structural information than NMR spectra, Astra achieves higher accuracy with UV-Vis data than with NMR peaks. MolP2SBench supports studying how LLMs extract and use physical-property information, revealing patterns that may differ from conventional chemical intuition and providing a foundation for more reliably property-grounded models for molecular and quantum-chemical inference. Code and dataset: https://github.com/DUAL-Xiao/MolP2SBench.
benchmarkleaderboard
02 US SEMI · SEC 8-K FILINGS
1 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 Opens Hong Kong Office in Causeway Bay2026-10-09
- 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