PHYSICAL AI · 2026-10-08

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.

344 items today · 289 arxiv · 1 SEC 8-K · 54 humanoid · 0 CN photonics

01 ARXIV · PHYSICAL AI PAPERS

289 items
  1. arxiv:2610.10538 · cs.RO
    Never Look Back: Understanding Persistence in 3D Object Memory from Egocentric Videos
    Shravan Chaudhari, William Paul, Suchi Saria, Rama Chellappa +1

    As we move through the world and carry out everyday tasks, we encounter objects that may become relevant only later. We are capable of recalling where we left something or what was inside a container, even without knowing we would need it later. Here, we study how an embodied assistant can build a similar memory from egocentric videos, by observing a person's day-to-day activities. We present Ledger, a persistent 3D object memory that combines object locations, their histories, and contextual descriptions. It associates observations across the recording and retains objects after they leave the view, including those the person never touches. It clusters each object's observations by resting locations and records a move only after repeated evidence, reducing the effect of localization noise. Short descriptions preserve details such as an object's contents or supporting surface. It saves these records to later answer spatial questions without having to access the original images or video. Our memory raises HD-EPIC accuracy from 29.7% to 42.6%, UCS-Bench accuracy from 33.8% to 38.5% and localizes Ego4D objects with a 0.99 m median error on returned predictions. Our analyses identify complementary roles for temporal persistence, contextual descriptions, and retrieval. Our study on 100 stitched streams of multiple scenes each further exposes failures in both retrieval and construction. Per-scene construction partially recovers the performance lost across scene changes compared to that of single scene streams.

    embodiedmemory
  2. arxiv:2610.10536 · cs.AI
    Decoupling Exploration from Optimization in RLVR
    Saif Punjwani, Micah Goldblum

    Modern language models undergo reinforcement learning with verifiable rewards (RLVR) on top of already-trained checkpoints. A key promise of RLVR is the discovery of new reasoning strategies. In principle, a model can sample novel ideas absent from its prior training data. In practice, however, augmenting RLVR with strong novelty incentives has seen limited success and can degrade model quality. Because verifiable rewards supervise only a narrow slice of the model's knowledge and behavior, such degradations are difficult to recover from. Instead, we decouple exploration from optimization in a framework we call Exploration-Distillation (ExpDis). We train one or more explorer policies with a novelty bonus in the reward, filter their trajectories for correctness and quality, and distill them into a separate student policy. The student policy is then trained without a novelty bonus. We repeat the above procedure for several rounds, alternating between exploration and optimization. This decoupling allows us to aggressively scale exploration without degrading the student policy. Across seven mathematical reasoning benchmarks and two model families, ExpDis outperforms DAPO at the same wall-clock budget. Moreover, we observe improved pass@$k$ scaling, indicating that ExpDis produces models that generate more diverse correct solutions.

    benchmark
  3. arxiv:2610.10534 · cs.RO
    RoboPrompt: Intuitive Robot Policy Steering with Sparse Human Input
    Yanwen Zou, Chenyang Shi, Guoxuan Xu, Wenye Yu +4

    End-to-end robot policies trained through imitation learning remain constrained by limited data diversity, making reliable zero-shot deployment in real-world settings challenging. Shared-autonomy methods enable human correction through teleoperation, but specialized hardware and operator training hinder deployment at scale. Other approaches incorporate human guidance as additional policy inputs, often requiring architectural changes and dedicated training for steerability, which limits their applicability across policies. We present RoboPrompt, a general-purpose, lightweight robot policy steering system that enables users to guide policy behavior through intuitive, sparse inputs, including drawn traces, target points, and coarse directional instructions. RoboPrompt decouples human-intention translation from the underlying policy: a reusable module converts human guidance into action drafts, which are refined through the diffusion or flow-matching dynamics of the base policy. By controlling action generation in noise space, RoboPrompt balances human intent with the policy prior without modifying the base policy architecture or fine-tuning it for steerability. Experiments demonstrate effective steering across Diffusion Policy, $π_{0.5}$, and FastWAM. We further use steered rollouts for online policy improvement through DAgger. After 2-3 rounds of iteration, average success rates increase by 15.5\% for $π_{0.5}$ across three tasks and by 21.3\% across three policies(Diffusion Policy, $π_{0.5}$, FastWAM) on the Insert Bread task, while average human intervention counts decrease by 44.0\% (2.86 to 1.60) and 81.9\% (2.60 to 0.47), respectively.

    teleoperationdiffusion policyrobot policy
  4. arxiv:2610.10533 · cs.CL
    EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional Memory
    Hongru Cai, Ran Wei, Wenjie Wang, Chengfa Wu +3

    Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language models (LLMs) with limited additional computation. Beyond model scaling, this architecture has demonstrated the potential to decouple factual knowledge storage from general-purpose computation, offering a promising route to updating factual knowledge while keeping the Transformer backbone fixed. Realizing this potential is challenging because different expressions of a fact may activate different n-gram embeddings, while updating shared embeddings can unintentionally change the model's predictions about other facts. We propose EngramEdit for decoupled knowledge updates through conditional memory. EngramEdit first computes target memory representations that make the model predict the updated fact across multiple expressions. It then jointly updates the shared n-gram embeddings to match these targets across expressions and edits, penalizing updates to frequently reused embeddings more strongly to preserve unrelated knowledge. Experiments show that EngramEdit enables independent factual knowledge updates through conditional memory, achieving near-perfect editing success. Revised knowledge is usable across unseen expressions and in multi-hop reasoning, with nearly three times the strongest baseline's accuracy under chain-of-thought (CoT) prompting. Unrelated knowledge and general capabilities are largely preserved even as factual updates accumulate. These findings show that EngramEdit turns conditional memory into an editable knowledge interface, extending its role beyond model scaling to support decoupled knowledge updates.

    memorymemory architecture
  5. arxiv:2610.10528 · cs.RO
    Long-WAM: Scaling the Context of World-Action Models
    Wei Huang, Bohan Zhang, Chenzhi Liu, Isabella Liu +12

    Real-time robot control demands enough visual history to infer motion and task progress, but processing that history can delay action. We present Long-WAM, a model-system framework for scaling the context of causal world-action models under real-time control constraints. Our central finding is that access to history is not the same as using it: longer histories pay off far more when the video foundation is pretrained autoregressively (AR). We first learn causal prediction from robot and egocentric videos without action labels, then preserve this history-to-future structure during world-action adaptation. On RoboCasa GR-1, increasing context from 0.0 to 19.2 seconds raises success from 63.3% to 78.7%, whereas a bidirectionally pretrained initialization shows no net gain; robot-domain AR pretraining further raises peak success on GR-1 and LIBERO-Long. Long-WAM also achieves the best results among compared methods on LIBERO-Long, RoboTwin 2.0, and DOMINO. Streaming observation encoding, asynchronous execution, and hardware-specific acceleration enable deployment on RTX 5090, DGX Spark, and Jetson AGX Thor without dropping future prediction; on RTX 5090, each action chunk, including future-video latent prediction, takes 107.4 ms. Real-time deployment on Unitree G1 and YAM supports dynamic and long-horizon manipulation, including 95% success on dynamic cup stacking, where Pi0.5 and Fast-WAM succeed in none of 20 trials. As a memory-informed executor, Long-WAM also complements higher-level planning in composite tasks.

    manipulationpi0liberorobotwin
  6. arxiv:2610.10526 · cs.RO
    Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action Models
    Mikey Watts, Yuchen Cui

    Vision-language-action models (VLAs) are strikingly sensitive to instruction phrasing and do not inherit the language robustness of the vision-language models they are built on. A one-word edit can move success by tens of points: $π_{0.5}$ turns on a LIBERO stove 100% of the time for "switch on the stove" and 2% for "switch on the hot plate", and a $π_0$ checkpoint finetuned with rephrase augmentation still shows swings of up to 61 points. We characterize this sensitivity with statistically tested single-edit swings and an oracle phrase search, which shows that phrasing alone nearly closes the 21-point gap between in-distribution and out-of-distribution tasks. We then reduce it without modifying the policy. Because the sensitivity is systematic, it can be expressed as explicit rules: we score many phrasings of a few training tasks, have a large language model distill the evidence into ten to twenty rephrasing rules, and at deployment rewrite each incoming instruction once under these rules. The rules improve the frozen $π_0$ by 16 to 27% relative on twelve held-out tasks across adversarial, VLM-generated, and human-generated phrasings, with gains concentrated on out-of-distribution tasks. The pipeline replicates on $π_{0.5}$ and LIBERO, lifting in-finetune success from 93.6% to 97.8%. The method requires no retraining and no per-step verification, and applies zero-shot to unseen tasks and instructions. Project website: https://sttawm.github.io/rephrase-before-you-act

    vision-language-actionlibero
  7. arxiv:2610.10515 · cs.RO
    RoboJEPA: Scaling Robotic Latent World Models
    Artem Zholus, Nicolas Beltran-Velez, Jianhao Yuan, Sarath Chandar +8

    Latent world models have shown a remarkable ability to predict future states and to plan in the real world. In practice, however, we lack a principled way to estimate how their capabilities scale with model size, data, and compute, an open problem that slows progress in the field. In this work we present RoboJEPA, a world model based on the Joint Embedding Predictive Architecture (JEPA) and trained on a large-scale dataset spanning 12 robotic embodiments. We show that RoboJEPA's imagination error, the error of its latent rollouts, follows a second-order power law in compute, allowing us to predict model quality well beyond the scale at which the law is fit. We further show that downstream robotic planning performance improves predictably with compute, and that imagination error is strongly correlated with it, making it a reliable proxy for real-robot evaluation. Finally, we demonstrate that latent world models can be deployed zero-shot as robotic agents, planning toward a single goal image to solve tasks requiring long-horizon planning on real hardware. We release all model checkpoints together with our training and robot deployment code. To our knowledge, this is the first work to establish scaling laws for multi-embodiment robotic world models trained on real robot data, and RoboJEPA, at 8B parameters, is the largest JEPA predictor model trained to date.

    world model
  8. arxiv:2610.10513 · cs.AI
    SciExam for ENSO: Can AI Agents Build Climate Models?
    Yinling Zhang, Langchen Liu, Dongbin Xiu, Xueyan Zou +3

    Language-model agents are increasingly asked to carry out open-ended scientific research, yet their results are usually graded against a known answer, a rubric, or a language-model reviewer, none of which can tell whether a new scientific model is valid. The AI Science Exam for El Nino-Southern Oscillation (SciExam for ENSO) is a benchmark in which agents build low-order stochastic models of ENSO, the dominant mode of interannual climate variability, from real observations. Within a six-hour budget, agents process the observations, write their own diagnostics, which are then frozen, and develop a model using only these diagnostics as feedback. Hidden graders then test whether the model reproduces ENSO's statistics, recovers unobserved variables, and forecasts held-out years, and score a published model in the same way. Across twelve agent systems, six produce models that score higher than the published model, mainly through better reconstruction and forecasting. The simplified forms of the stronger models are each compatible with one of the two competing explanations of ENSO's warm-cold asymmetry, an open debate that the task never mentions. Controlled runs of the top system under varied information suggest that its scores do not come from recalling the dated observational record and that the information it receives shapes how it builds its model. SciExam for ENSO can thus evaluate agent research where no answer is known, and the results suggest that agents can already build competitive models whose structures bear on questions that scientists still debate.

    agentai agentagent systembenchmark
  9. arxiv:2610.10510 · cs.RO
    Factorized Tactile Representation and Control for Sim-to-Real Manipulation
    Siqi Shang, Bianca Aumann, Tye Brady, Joshua Migdal +1

    Tactile sim-to-real learning must bridge simulated contact and device-specific sensor responses while preserving information needed for control. We propose a factorized tactile representation and control framework that maps normal force and contact patch to an effective contact response recoverable from sensor readings. The response is separated into contact geometry, force distribution, and temporal contact change, with representation-specific encoding and randomization. A Tactile Gated Policy preserves these representations separately through control and operates over all mask configurations without retraining. We evaluate the approach through response reconstruction, spatial alignment, force regulation, and contact-rich adversarial peg insertion in simulation and the real world, enabling the utility and transfer reliability of different tactile representations to be assessed independently. The approach achieves <1 mm contact localization, 1.69 N force-tracking error on unseen geometries, and a 35% improvement in real-world adversarial peg insertion over the unfactorized response, with different tactile representations benefiting different interactions.

    manipulationtactilesim-to-real
  10. arxiv:2610.10507 · cs.AI
    RECAST: Learning to Compute the Right Context through Adaptive Evidence Routing
    Yilun Hao, Krishna Sayana, Isabella Ye, James S Ren +3

    Large language models are increasingly applied to tasks grounded in long, heterogeneous information sources. Conventional Retrieval-Augmented Generation (RAG) relies on fixed similarity-based retrieval, while agentic variants adapt queries and tool use but remain largely retrieval-centric. However, in many tasks, the evidence required for a solution is not explicitly present in any single source item. Instead, it must be derived through filtering, aggregation, or computation across multiple source items. In this work, we introduce RECAST (Routing Evidence through Computation, Access, and Synthesized Tools), a learned framework that formulates evidence construction as a sequential decision process over heterogeneous retrieval and computation operations, allowing evidence to be actively derived rather than merely retrieved. A lightweight RouterLM iteratively selects and formulates primitive operations or specifies customized operations for a frozen CompilerLM to translate into executable code. Once it judges the evidence sufficient, RouterLM passes the accepted evidence to a frozen AnswerLM to produce the final solution. We train RouterLM with supervised fine-tuning (SFT) followed by group relative policy optimization (GRPO). Across six heterogeneous benchmark families, RECAST achieves a mean success rate of 75.6%, outperforming the strongest large-model baseline by 15.9%. Moreover, training enables the Qwen3.5-9B RouterLM to outperform a training-free Gemini 3.5 Flash RouterLM by 5.0%. On three held-out benchmarks, RECAST improves over the strongest baseline by 15.0% on average, demonstrating strong zero-shot generalization across tasks and heterogeneous source representations.

    retrieval-augmentedagentictool usebenchmark
  11. arxiv:2610.10498 · cs.AI
    EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-Evolution
    Python Song, Zhixuan Liang, Kelsey Fu, Mengdi Wang +2

    Robot foundation models provide strong visuomotor control, yet their performance can degrade when object positions or task instructions change. Further improvements often require post-training on substantial robot data, which can be costly to collect through methods such as teleoperation. Agentic harnesses can adapt around the model, but current self-evolving harnesses use robot trials inefficiently when deciding which code and skill changes to pursue. We introduce EmbodiedRSI, a self-evolving agentic harness that autonomously decides where to explore next and turns the resulting physical interaction into improved code and skills. EmbodiedRSI realizes this through a Fast-Slow Dual-System Architecture, in which competing code and skill hypotheses are maintained in a Hypothesis Graph. Value-of-Information Experiment Selection chooses physical experiments that can distinguish these hypotheses. Their outcomes guide Code-Skill Co-Evolution. The Slow System builds Hierarchical Memory, and Reward-Grounded Memory Learning selects effective memory according to their value for later Fast-System improvement. On RoboCasa365, EmbodiedRSI reaches 77.0% overall success and 71.3% on Composite-Unseen, compared with 40.1% for the best baseline. EmbodiedRSI also reaches 86.8% overall success on LIBERO-Pro. Beyond benchmark performance, EmbodiedRSI transfers zero-shot to real-world robot, achieving 71.3% overall success across multiple challenging tasks.

    embodiedteleoperationrobot foundation modelliberomemoryagentic
  12. arxiv:2610.10489 · cs.RO
    HuMBLE: Human Motion-Driven Behavior Learning for Embodied Locomotion
    Mike Zhang, Dongho Kang, Kevin Bergamin, Nicola Burger +18

    Despite recent advances in humanoid locomotion, controllers optimized for command tracking and robustness tend to produce mechanical gaits, whereas controllers tied to human motion data often fail to generalize to commands outside the data distribution. This work introduces a learning framework that balances these competing objectives to synthesize real-time steerable, robust, and biomimetic locomotion policies from human data. Using an in-house curated locomotion dataset covering diverse speeds and directions, we first learn a natural locomotion prior policy through a teacher-student distillation process. Specifically, we train a full-body reference-conditioned policy with Reinforcement Learning (RL), then distill it into a lightweight prior policy conditioned solely on proprioception and a planar torso-velocity steering command. Next, we fine-tune the prior policy with multi-task RL to expand command coverage and robustness beyond the data distribution, pairing a goal-conditioned task that tracks arbitrary commands with a reference-guided task that tracks the human data as an explicit style regularizer. We validate our framework on three humanoid robots: the Boston Dynamics Atlas R1, Atlas D1, and Unitree G1. Experimental results demonstrate robust performance across real-world scenarios, including direct user-controlled locomotion in indoor and outdoor environments, and integration as the locomotion layer within hierarchical control stacks. Benchmarks against Tabula Rasa RL policies trained without human data and ablation studies confirm that our framework yields a lightweight, deployable policy that reconstructs coordinated whole-body behavior from a steering command, retaining the human gait characteristics while remaining robust and fully steerable.

    embodiedhumanoidbenchmark
  13. arxiv:2610.10479 · cs.RO
    Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot Policies
    Yihan Li, Yating Feng, Shengjiu Sun, Jianing Chen +6

    A simulation of a real robot workspace must preserve task-relevant interactions, while policies developed in it must operate on observations available to the real robot. Yet scene reconstruction and policy development are often treated separately. We present Agentic Real-to-Sim-to-Real (Agentic RSR), a framework that links scene reconstruction, policy development, and real-robot execution through the same manipulation task. Given a workspace video, a task description, and a known robot model, an agent recovers metric scale, iteratively refines the scene using visual feedback, and checks task-relevant interactions in MuJoCo. A coding agent then develops an executable policy, progressing from privileged object poses to visual observations and randomized simulation. The policy can interleave multiple observations and actions within one invocation, while the agent uses execution feedback to continue, retry, or revise its approach. A shared task-level interface carries the policy and accumulated experience to the real robot, where fresh observations and safety checks guide execution. Across 18 reconstructed scenes involving two robots, the mean four-view Depth MAE against reference depth estimates is 0.1057 m, the mean Lab $ΔE_{76}$ is 11.04, and the mean grayscale SSIM is 0.6990. In real-robot experiments, the aggregate task success rate reaches 80% of the simulation task success rate, indicating substantial retention of simulated performance on hardware. Code and reconstructed scene data will be made publicly available.

    manipulationsim-to-realagentagentic
  14. arxiv:2610.10478 · cs.AI
    Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base Models
    Tan Yu, Alexander Bukharin, Khushi Bhardwaj, Jennifer Williams +18

    How can we predict which base checkpoint is worth an expensive round of agentic post-training? End-to-end pass@$K$ tests whether successful behavior already appears in a base model's distribution, but it is a poor fit for agentic coding: many base checkpoints cannot reliably produce the well-formed tool invocation required to complete a task end-to-end. Single-shot or short-horizon tasks avoid these tool-calling failures by collapsing a multi-step interaction into a fixed prompt and a single patch, but they sidestep the core capability we care about: maintaining coherent state over many tool-using steps as the repository evolves. To bridge this gap, we treat successful post-trained agent trajectories as a lookahead signal of base-model potential. Replaying each trajectory and rerunning tests after every code-changing step identifies the decisive step: the first step whose cumulative patch flips the repository from failing to passing, certifying that the recorded action solves the task given the prior context. Motivated by a coverage principle for agentic traces, we build three screens at this step that do not require a base checkpoint to drive the harness from a cold start: (i) Decisive-Action BPB (bits per byte) measures the probability mass on the certified action, (ii) Patch MCQ tests the checkpoint's choice between that action and alternatives rejected by the same verifier, and (iii) prefix-conditioned pass@$K$ evaluates support for functionally-correct generations and credits any continuation that the tests accept. Across ten pairs of public base and post-trained models, all three screens rank the cohort in close agreement with post-trained SWE-bench Verified pass@$1$. As our methods need only a benchmark's successful trajectories and its verifier, they can be applied to turn future agentic coding benchmarks into base-model evaluations.

    agentagenticpost-trainingbenchmark
  15. arxiv:2610.10472 · cs.RO
    Robotic Boomerang Throwing via Model-Based Release Design
    Yang Liu, Colin Jones, Aude Billard

    Throwing objects that generate aerodynamic lift can greatly extend robot throwing beyond ballistic flight. A returning boomerang is a challenging example because its flight depends strongly on the release velocity, attitude, and spin, while robotic manipulators cannot readily reproduce the rapid motions used in human throwing. We present a model-based framework for robotic boomerang throwing centered on the release state. We identify the boomerang flight dynamics in stages to predict how flight changes across design variations. To systematically design the robot throwing motion, we screen candidate parameters according to how strongly and consistently they control release spin under uncertain contact conditions. These models are then used to design the throwing motion and boomerang for a 6-DoF manipulator with limited joint speeds. To our knowledge, this is the first robotic manipulator to generate a returning boomerang flight. In the demonstrated returning trial, the boomerang is released at 51 rad/s (8.1 rev/s), reaches 2.03 m from the robot base, and returns to touch down 0.31 m from the base. The successful release differs significantly from the measured human throws, showing that a robot need not imitate human throwing motion to achieve a returning flight. The project page is available at https://robot-boomerang.github.io

    manipulator
  16. arxiv:2610.10470 · cs.RO
    CMP-IRRT*: A Perception-Assisted Height-Adaptive Planner for Quadruped Robots
    Mingfan Zhao, Wendong Mao, Zhongfeng Wang

    Quadruped robots can traverse low obstacles, but many 2D planning pipelines still model obstacles as binary occupied regions and rely on sampling-based search that can be inefficient under a limited budget. We propose a perception-assisted height-adaptive planning framework based on CMP-IRRT*, a Channel Mamba PointNet-guided Informed RRT* planner. Given a calibrated top-view RGB observation, the perception module estimates obstacle regions and converts depth predictions into a ground-relative height map. The planner then performs height-conditioned collision checking, treating high obstacles as blocked while allowing low obstacles to be traversed, and uses the CMP guide to bias sampling toward promising regions while retaining standard free-space and informed sampling fallbacks. Experiments on 2D planning benchmarks show that CMP-IRRT* reduces explored nodes and iterations compared with classical and neural-guided baselines, and a controlled ablation supports the contribution of the Mamba-based guide. In constructed traversability-aware scenarios, the proposed planner reduces path length by up to 16.3% when low obstacles are traversable, and a Unitree Go2 demonstration further shows executable bypassing and traversal behaviors. Our code is publicly available at https://github.com/MingfanZhao/height-adaptive-planner.

    quadrupedbenchmark
  17. arxiv:2610.10468 · cs.AI
    A Society of Researchers: Designing Institutions for Populations of Autonomous Research Agents
    Ali Asaria, Deep Gandhi, Tony Salomone

    Deployments of research agents are moving to populations of thousands that share one pool of compute, while most current systems organize one project at a time or leave the population unorganized. We argue that such a population will acquire an organization whether or not its designers provide one, so designers should provide it explicitly, and that the multi-agent systems community holds the tools to do so. We propose a society of agents, a population of persistent agents under explicit institutions, and develop it for science as a society of researchers built on six principles. Principal investigators compete for compute through requests for proposals, independent review, and grants; a human governor, the mayor, allocates resources and assigns no tasks. In a running society of ten thousand researchers, asked only to improve the pretraining of language models, one lab reported a way to reach the same quality with about 30% less compute, a result the labs that tested it do not yet agree on. We close with six open problems for the agents community.

    multi-agentagent system
  18. arxiv:2610.10465 · cs.RO
    LLA-MPPI: Rapidly Adaptive Whole-body Control of Legged Robots with GPU-Accelerated Parallel Simulations
    Sebin Jung, Maitham F. AL-Sunni, Juan Alvarez-Padilla, Zachary Manchester +2

    Real-time whole-body controllers for legged robots typically plan through a fixed nominal model and degrade when the deployed dynamics change. Adaptive methods typically require a model structure that contact dynamics do not provide, or they need offline training for each anticipated condition. We present Look-back and Look-ahead Adaptive Model Predictive Path Integral control (LLA-MPPI). The method converts whole-body adaptation into selection over a bank of GPU-batched contact simulators with different physical or structural parameters. Windowed prediction errors select the simulator that best explains recent motion. A whole-body MPPI planner optimizes controls through the selected model. The framework requires no offline training, and its selected hypotheses are physically interpretable. Across four simulated tasks, it achieves 97.5% success while the strongest baseline reaches 74% and an oracle with the true model reaches 98.5%. Hardware validation on a Unitree Go2 shows the robot walking under a payload added mid-run, walking after one leg is disabled, and pushing a box to its goal while increasing its mass on the fly. Code, videos, and project details are available at: https://lla-control.github.io

    whole-body control
  19. arxiv:2610.10462 · cs.RO
    FoldBack: Self-Correcting Masked Generative Policy for Long-Horizon Garment Folding
    Lipeng Zhuang, Shiyu Fan, Yingdong Ru, Zhuo He +3

    We present FoldBack, a self-correcting masked generative policy for long-horizon garment folding. Existing long-trajectory policies may continue after a missed or slipped grasp even when the garment has not reached the intended configuration. We structure FoldBack's recovery mechanisms around three inference-time decisions: when to refine and verify, how to roll back, and where and how to retry. FoldBack aligns refinement and grasp verification with pick-and-place events, returns the robot to a retryable pre-grasp configuration while preserving successful grasps, and selectively regenerates the failed segment and selected future actions while avoiding previous failed grasp locations. To our knowledge, FoldBack is the first editable full-trajectory policy to unify these decisions, enabling failed interactions to be detected, undone, and repaired before execution continues, without recovery demonstrations or base-policy retraining. Across 33 real garments from six categories, FoldBack achieves 75.2% final folding success and 0.837 final-mask IoU, versus 45.7% and 0.689 for the strongest prior baseline.

    grasp
  20. arxiv:2610.10460 · cs.AI
    Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts
    Hejian Sang, Zhengze Zhou, Shayan Mohajer Hamidi, Xiaomin Li +2

    Multi-teacher on-policy distillation (MOPD) is used in two settings. In common-domain composition, several teachers score each student rollout from one prompt domain and their signals form a single target; in routed-domain distillation, prompts from different domains are assigned to the corresponding specialist. Both settings usually transfer each teacher's endpoint policy, which mixes what post-training changed with preferences inherited from the teacher's base. We introduce $Δ$-MOPD, which transfers each teacher's teacher-minus-base logit shift re-anchored at the student's frozen initialization, and compare it with endpoint supervision in both settings while holding teacher selection fixed. We first expose the mechanism that impedes endpoint transfer: inherited base pull can exceed the post-training shift. Removing it reduces the teacher-term norm ratio and target--student KL. Across our experiments, the results suggest that shift targets are particularly useful when teacher signals are combined at a state. With three composed teachers, $Δ$-MOPD exceeds endpoint composition by $4.11$ Math and $1.95$ five-benchmark points; with two, it matches endpoint accuracy. Under phased routing, it achieves higher mean performance in both phase orders and reduces the observed order gap from $10.50$ to $6.42$ points. Under interleaved routing, where each update involves one teacher, the two targets perform comparably. The phased results provide supporting evidence that the benefit may extend to signals accumulated across training phases. Target construction is thus an independent design axis in MOPD, complementary to teacher selection.

    post-trainingbenchmark
  21. arxiv:2610.10455 · cs.AI
    PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMs
    Linghao Meng, Feng He, Xuan Yang, Junyuan Mao +4

    Hallucinated information can propagate through multi-stage LLM systems and become part of the context for subsequent reasoning. Existing studies of post-hallucination reasoning (PHR) mainly characterize changes in final outcomes and aggregate reasoning dynamics, leaving how models resolve hallucinated premises at the response level insufficiently understood. In this work, we introduce PHRBench, a controlled benchmark for behaviorally structured PHR across four domains and 18 large language models. PHRBench characterizes each reasoning trajectory independently of final-answer correctness through Hallucination Compliance, Hallucination Avoidance, and Heuristic Correction, and defines an insightful trajectory as successful correction that ultimately reaches the correct answer. Across 4820 controlled instances, we find that successful recovery remains relatively rare and is associated with more frequent belief updates along the reasoning trajectory. We further find that properties of the hallucinated prompt contain substantial predictive signal for successful recovery, with a lightweight predictor achieving an AUROC of 0.847. These findings provide a behavioral view of post-hallucination reasoning, characterizing how LLMs resolve erroneous context and when successful recovery is likely to occur.

    benchmark
  22. arxiv:2610.10453 · cs.RO
    RFPO: Rectified Flow Policy Optimization for Embodied Control
    Ting Huang, Lisiyu Pan, Haoyu Wang, Zeyu Zhang +5

    Flow-based policies provide an expressive framework for continuous robot control, but their iterative ODE integration incurs substantial inference cost. Naively reducing the integration budget can severely degrade control, since policies optimized under full-step execution are not explicitly constrained to remain reliable under coarse numerical integration. We refer to this mismatch as the few-step discretization gap. To address this problem, we introduce RFPO, a flow-policy optimization framework for reliable few-step execution. Reward-aware online Reflow rectifies student-induced transport paths during on-policy learning, making the resulting policy more robust to coarse integration. A frozen Gaussian PPO controller supplies complementary action-space supervision at full and intermediate integration budgets, while the deployed policy remains a single flow student executed with one Euler step. Across Unitree Go2, Boston Dynamics Spot, Unitree H1, and Unitree G1, RFPO consistently preserves full-step control performance under one-step execution, with one-step returns remaining within 2.4% of their corresponding 64-step values across both zero and random initialization. On Unitree Go2, one-step execution retains 98.5% of the 64-step reward while reducing onboard mean inference latency from 4.39 ms to 0.08 ms, yielding a 54.9x speedup. Real-robot experiments further validate stable one-step locomotion. Code: https://github.com/AIGeeksGroup/RFPO. Website: https://aigeeksgroup.github.io/RFPO.

    embodied
  23. arxiv:2610.10447 · cs.AI
    A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching
    Randy Ardywibowo, Arnav Dalal, Jiantao Jiao

    Reinforcement Learning (RL) from outcome rewards suffers from sparse supervision, particularly on difficult, long-horizon tasks where successful trajectories are rare and costly to generate. On-Policy Distillation (OPD) offers an attractive alternative by providing dense token-level supervision from a stronger teacher along the student's own generations. Self-distillation methods further remove the need for a separate teacher model by conditioning the same policy on privileged information to serve as its own teacher. However, privileged conditioning alone does not guarantee that the resulting distillation update improves the student. Indeed, privileged information can lead the teacher to solve tasks through shortcuts unavailable to the student, producing supervision poorly matched to the student's current behavior. Consequently, even a higher-performing teacher can provide guidance that degrades student performance. To address this, we analyze how the choice of privileged teacher affects the student's update. We derive a necessary and sufficient condition for the teacher's local distillation update to be a positive multiple of the student's reward gradient. Our analysis suggests that the teacher should not only perform well on the task, but also provide guidance suited to the student's current capabilities. This characterization motivates a practical teacher-training surrogate that combines outcome rewards with token-level Kullback-Leibler (KL) regularization toward the student. Based on this result, we propose Joint On-Policy Learning and Teaching (JOLT), which jointly trains a single policy in two roles: a privileged teacher using a KL-regularized objective, and an unprivileged student using dense on-policy distillation. Across mathematical reasoning, coding, tool use, and terminal use, JOLT improves training efficiency and performance, with further gains from student rewards.

    tool use
  24. arxiv:2610.10444 · cs.AI
    RunningTab: Direct Workspace Interaction with Environment-Side Tabs
    Jinheon Baek, Soyeong Jeong, Yumin Choi, Dongsu Han +1

    Much knowledge work produces new deliverables from files a workspace already holds, and LLM agents are beginning to take such work over. Through direct corpus interaction, an agent can search and read any of those files from a terminal with no indexing, and producing a deliverable from many of them in this way is what we call direct workspace interaction (DWI). Reaching the files, however, is only half the task: nothing keeps track of what the task asks for, what has been read, and what was listed but never opened, all of which slip through the context window without leaving a trace, so an agent may extract a figure and still deliver a report without it. To address this, we present RunningTab, a framework that equips direct workspace interaction with an environment-side tab: a per-task record of what the task still owes, kept by the environment alongside the agent. Specifically, the agent adds its requirements, while the environment records every file read as an excerpt with its provenance and every listed but unopened file as a candidate; the agent can then see each requirement beside its best-matching excerpts and top unopened candidates, resolve it against matching content or set it aside with a reason, and, should it try to finish with requirements still open, receive them in a finish check. We validate RunningTab on three benchmarks with three LLMs, where it consistently outperforms plain DWI and baselines that keep the record in the model, while its tab usually holds the values a deliverable needs once seen.

    agentllm agentbenchmark
  25. arxiv:2610.10438 · cs.RO
    ECHO: Embodied Camera Observations of Human Object Carrying
    Xuefei Sun, Lorin Achey, Kali Hamilton, Alberto Speranzon +3

    Embodied and assistive agents must do more than recognize objects: they must reason about where an object belongs given the layout of an environment and the habits of the people who live in it. Progress on this problem has been limited, in part because no dedicated benchmark or dataset exists to define and evaluate it. Existing RGB-D scan datasets reconstruct static rooms without human activity, while human-object-interaction datasets capture motion without a navigable, fully reconstructed scene or a ground-truth notion of an object's natural destination. We introduce contextual object placement as a benchmark task: predicting an object's destination during an observed object-carrying episode. To support this task, we present Embodied Camera observations of Human Object carrying (ECHO), a large-scale synthetic dataset that pairs dense RGB-D scans of indoor scenes with recordings of an embodied human carrying everyday objects to context-appropriate destinations. ECHO is the first publicly available dataset to combine reconstructed scenes, human activity, natural language, and contextual-placement annotations. It comprises 3,805 human-annotated episodes across 159 floors of 115 HM3D scenes, involving 198 distinct objects. Each floor includes a complete RGB-D scan with human-annotated room labels and a surface list. Each episode provides synchronized RGB-D encounter clips; 6-DoF camera, human, and object trajectories; start and destination surfaces; an action caption; and a human-written context: a single sentence describing the inhabitant's routine that implies the destination without naming it. We evaluate contextual object placement using input-masked probes and an end-to-end baseline. Results show that no single input modality is sufficient, highlighting the need to jointly reason over scene structure, human activity, and contextual knowledge.

    embodiedbenchmark
  26. arxiv:2610.10437 · cs.RO
    Q-Learning with Scalar Adjoint Matching
    Yonghoon Dong, Minsung Yoon, Jaehyuk Kim, Jungwoo Park +2

    Flow policies capture rich and diverse action distributions, and fine-tuning them with off-policy RL to improve beyond the demonstrations has drawn growing interest. However, fine-tuning a flow policy against a learned value function is not trivial, because the policy generates its action over many flow steps. Adjoint matching offers a principled way to update the flow model itself by propagating value information from the final action back to each flow step, but it requires a vector--Jacobian product through the policy at every step, a cost that grows with the number of flow steps and the policy size. We observe that the batch-averaged velocity Jacobian of pretrained flow policies concentrates on its diagonal. Motivated by this finding, we derive a closed-form scalar adjoint that scales the value gradient at the final action by the flow time, eliminating the per-step vector--Jacobian products. We further find that controlling the critic's value at policy-generated actions is particularly important under the scalar adjoint. Based on these findings, we propose Q-learning with Scalar Adjoint Matching (SQAM), which combines the scalar adjoint with a value penalty at those actions. SQAM's gains concentrate on the four hardest OGBench domains, where its success rate exceeds that of the strongest baseline in each domain by 18 to 35 percentage points. To test whether SQAM extends to large pretrained policies, we also fine-tune a vision-language-action policy on a real bimanual robot. SQAM improves over supervised fine-tuning on all three tasks.

    vision-language-action
  27. arxiv:2610.10421 · cs.RO
    AirGroundVLN: A Large-Scale Benchmark for Goal-Oriented Air-Ground Collaborative Vision-and-Language Navigation
    Zhenxuan Zeng, Qingle Wu, Wei Suo, Maojia Wu +3

    Goal-oriented Vision-and-Language Navigation (VLN) requires agents to locate and reach targets described in natural language without prescribed routes. Air--ground collaboration is valuable for tasks requiring both wide-area search and fine-grained localization. However, systematic study of goal-oriented air--ground collaborative VLN remains limited by the lack of large-scale, diverse benchmarks and two core challenges: 1) substantial differences between aerial and ground views, together with useful observations becoming unavailable as navigation proceeds, make it difficult to maintain spatially consistent context across platforms and over time; and 2) asymmetric spatial observability makes ground perception locally detailed but spatially limited and aerial perception broad but locally coarse, limiting the reliability of single-platform planning. To address these limitations, we introduce AirGroundVLN, a benchmark containing 10,281 navigation episodes and 955 target instances across 19 Unreal Engine environments, with seen/unseen splits and an aerial-visibility protocol for systematic evaluation. Alongside the benchmark, we propose AG-CoNAV, a trainable reference framework comprising two key components: Spatiotemporally Anchored Collaborative Memory (SACM) and Aerial-Guided Regional-to-Local Planning (AGRLP). SACM maintains and retrieves spatially consistent historical context across aerial and ground observations. Meanwhile, AGRLP combines regional aerial guidance with fine-grained ground navigation. Extensive experiments demonstrate the effectiveness of AG-CoNAV and establish AirGroundVLN as a comprehensive benchmark for future exploration.

    memorybenchmark
  28. arxiv:2610.10411 · cs.AI
    Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding Rounds
    Yunxiao Zhao, Changxiao Cai

    Speculative decoding accelerates large language model inference by using a low-cost draft model to propose tokens that the full-size target model verifies in parallel. Parallel and semi-autoregressive (semi- AR) drafters improve drafting efficiency by proposing an entire block in a single forward pass, but training them raises a new difficulty: the draft distribution for a given position depends on where the decoding round starts, and where rounds start depends on how many tokens earlier rounds accepted. Existing training objectives typically rely on block-local surrogates that ignore this cross-round coupling, and therefore do not directly optimize the global decoding efficiency. In this work, we develop a theoretical framework for training and evaluating these drafters by representing speculative decoding as a Markov reward process. This formulation yields the Expected Decoding Rounds (EDR) objective, which weights local rejection costs by state occupancies and exactly equals the expected number of decoding rounds. Unlike prior surrogate objectives, EDR introduces no auxiliary hyperparameters. We then derive an exact temporal-difference gradient that supports unbiased stochastic optimization from target-model rollouts. The same framework also yields an exact offline evaluator for round counts, enabling paired drafter comparisons on shared target rollouts without running speculative decoding. Finetuning two state-of-the- art drafters, DSpark and DFly, with EDR consistently improves mean accepted length and outperforms existing training objectives across nine benchmarks spanning math reasoning, code generation, and chat.

    benchmarkevaluator
  29. arxiv:2610.10409 · cs.RO
    RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments
    Zhiqin Yang, Chenxin Li, Xiaomeng Hu, Yibin Liu +29

    General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities carry into the physical world. To investigate this, we introduce RobotWorld, a challenging simulation testbed for robot use: turning instructions and observations into physical task execution through robot interfaces. Its 84 tasks span manipulation, mobile manipulation, locomotion, driving, and aerial control, with explicit interaction budgets and executable success checks. By analysing task outcomes alongside execution traces, we identify both the capabilities that transfer and the gaps that prevent reliable completion. Furthermore, we find that current agents can construct sophisticated perception and control workflows, including image segmentation, camera calibration, spatial estimation, and dynamics-based computation. These capabilities, however, do not consistently compose into successful behaviour: agents lose task-relevant object states despite reaching commanded poses, fail to correct ineffective actions, recover too late, or mistake unfinished tasks for completion. This uneven transfer also differs across models: Astra succeeds more often on spatial and constrained-contact goals, whereas Opus 5.5 succeeds more often on continuous-balance and timed-interaction goals. By linking these outcomes to execution behaviour, RobotWorld provides both a rigorous proving ground and an empirical account of the remaining capability gaps, thereby establishing concrete targets for training and designing more reliable physical-world agents.

    manipulationbenchmark
  30. arxiv:2610.10407 · cs.AI
    SOTA: Stock Options Trading Agents Guided by Option-Implied Return Distributions
    Yizhen Xie, Mengyang Liu

    As option markets grow and AI advances, agentic systems for option trading are gaining increasing attention. Language-model-based agents can reason over contextual information such as news, but option trading presents a particularly challenging decision problem: a single stock can have thousands of contracts, and the agent must decide both which contracts to trade and how to combine them. Existing approaches often sidestep this complexity by restricting the policy to a fixed strategy structure, such as a straddle, limiting their ability to switch strategies as market conditions change. We present SOTA (Stock Options Trading Agents), an agentic trading framework for structured option-strategy selection. SOTA abstracts the large option universe into strategy-level decisions while deterministic resolvers handle portfolio implementation. We develop SOTA by post-training Qwen3.8-27B with supervised fine-tuning followed by reinforcement learning. SOTA is evaluated on options on nine large-cap U.S. equities and SPY against rule-based and machine-learning strategy selectors in the same trading environment. Over a six-month out-of-sample period, SOTA earns an 18.3% total return with a Sharpe ratio of 1.60 and a maximum drawdown of 8.96%. We also document an asymmetric role of news: news improves frontier-teacher trajectories, but retaining news during reinforcement learning reduces out-of-sample return from 18.3% to -2.7%.

    agentagenticpost-training
  31. arxiv:2610.10388 · cs.RO
    RoboQuest: Generalist Physical Agents that Search, Inspect and Test
    Liu Renhang, Navonil Majumder, Tej Deep Pala, Soujanya Poria

    Recent advances in multimodal foundation models have made them capable generalist physical agents for a range of manipulation tasks. However, successful operation in an unfamiliar environment may require an agent to seek task-relevant information through interaction when it is absent from the observations: it may need to determine where a relevant object is, inspect an unobserved property, or discover the effect of an unfamiliar tool. We thus introduce RoboQuest, a benchmark for goal-directed embodied exploration, where agents must actively acquire task-relevant information through physical interaction, use the resulting evidence to adapt subsequent actions, and autonomously decide when to commit to task completion. RoboQuest comprises ten mobile manipulation tasks centered on three forms of uncertainty: search, manipulation-based inspection, and interactive testing. We evaluate five frontier multimodal agents through a common visuomotor interface, as well as a $π_{0.5}$ policy fine-tuned on the full-episode demonstrations we release. The best agent succeeds in only 23\% of the episodes, and the fine-tuned policy almost never succeeds. Isolated tests of the execution skills the tasks are built from, with the hidden information supplied, show that the agents can carry out most of the required actions, and our failure analysis attributes only a minority of the failures to execution. Our failure analysis further finds that the agents often stop exploring too early as they make decisions before observing the required evidence for task completion. We also find that agents rarely prevent or repair the disturbances caused by their exploration. Moreover, learning by trial and error remains difficult for most models.

    embodiedmanipulationagentbenchmark
  32. arxiv:2610.10387 · cs.RO
    NeRFifyMesh: Optimizing Neural Radiance Fields from Textured Meshes for Robotics Scene Building
    Nillan Nimal, Mahboubeh Asadi, Sajad Saeedi

    In robotics, scene representation plays a pivotal role in understanding and interacting with the environment. The advent of Neural Radiance Fields (NeRF) and its variants, as a novel representation, has opened a new frontier of research. In applications such as semantic mapping and simulation, roboticists aim to build scenes using multiple NeRF models, each representing an object. While extensive datasets of 3D mesh models already exist, there is an urgent need to develop tools to convert these assets to NeRF models for rapid algorithm development and testing. This paper presents a new pipeline for converting existing mesh models to NeRF representations by artificially generating a ground truth point-based radiance field through sampling mesh geometry and texture. This approach alleviates the need for camera-based sampling or rendering multi-view images of the original mesh to train the NeRF model. Extensive benchmarking demonstrates that our method yields comparable rendering quality to the baselines. Additionally, the application of this representation is shown by constructing unified NeRF scenes and performing collision simulations with extracted geometry.

    benchmark
  33. arxiv:2610.10384 · cs.RO
    OpenViTac: Learning and Benchmarking Visuo-Tactile Policies in a Unified Sim-and-Real Framework
    Yifan Wu, Qin Li, Nan Min, Guojin Zhong +13

    Tactile feedback provides embodied agents with physical information beyond visual observations, enabling more reliable interaction with the real world. However, despite the rapid progress of vision-tactile-language-action (VTLA) policies, there remains a lack of unified benchmarks for evaluating tactile-enabled robot manipulation across simulation and the real world. To address this gap, we introduce OpenViTac, a visuo-tactile manipulation benchmark for evaluating robot policies across simulation and the real world. OpenViTac organizes contact-rich manipulation into four tactile-relevant capability dimensions and provides paired simulation-real-world settings for consistent evaluation of VLA, WAM, and VTLA policies. Building upon this benchmark, we investigate how different tactile representations and integration strategies affect the performance of pretrained VLA models. Correspondingly, we introduce OpenVTLA, a tactile augmentation framework that combines the best-performing representation and integration strategy. Furthermore, we leverage the paired benchmark setting to study sim-real co-training and analyze factors affecting cross-domain policy learning. Together, OpenViTac provides a unified platform for evaluating and advancing visuo-tactile robot manipulation.

    vlavla modelembodiedmanipulationtactileembodied agent
  34. arxiv:2610.10378 · cs.CL
    Document-Level Text Simplification in Estonian Using Large Language Models
    Meeri-Ly Muru, Eduard Barbu

    Document-level text simplification involves transformations that go beyond sentence-internal edits, addressing discourse coherence, anaphora resolution, and cross-paragraph consistency. Despite advances in sentence-level simplification for high-resource languages, document-level simplification in morphologically rich, low-resource languages such as Estonian remains largely unexplored. This study presents a comprehensive evaluation of five state-of-the-art multilingual large language models (LLMs) for document-level simplification in Estonian. Three prompting strategies are examined: single-pass generation, pipeline-based modular agents, and guideline-augmented pipelines. The evaluation framework integrates automatic metrics assessing readability, semantic preservation, and discourse coherence, alongside a structured manual annotation protocol. The findings indicate that Gemini-2.0 and LLaMA-3.3 produce outputs with near-native fluency and strong meaning preservation, whereas other models display notable grammatical and semantic limitations. This work contributes novel document-level coherence metrics, evidence-based prompting strategies, and publicly available resources for reproducibility.

    evaluation framework
  35. arxiv:2610.10374 · cs.AI
    TaoD2C-Bench: Benchmarking MLLMs for Industrial UI Code Generation Beyond Visual Fidelity
    Chengwei Shi, Yunnong Chen, Tingting Zhou, Qiang Lu +4

    A key challenge for multimodal large language models (MLLMs) is moving beyond visual recognition to constraint-aware cross-modal reasoning. This involves combining visual cues with information from other modalities to understand elements' relationships under domain-specific rules. This challenge is acutely evident in industrial design-to-code (D2C), which converts user interface (UI) designs into code and requires MLLMs to connect design images with disorganized layer metadata, infer component and layout implementation requirements, and realize them in code under target-library constraints. However, these capabilities remain insufficiently evaluated in realistic industrial settings. To fill this gap, we present TaoD2C-Bench, a benchmark for evaluating MLLMs' ability to generate UI code that satisfies implementation requirements in industrial applications. The TaoD2C dataset consists of 2,861 production designs from 17 commercial platforms with 97,652 expert annotations across four categories: Component, Group, Alignment, and Position. These annotations distinguish required constraints from permitted implementation choices. TaoD2C-Bench defines three tasks: end-to-end UI code generation, requirement inference, and requirement realization. Evaluating eight MLLMs reveals substantial gaps in generating UI code that satisfies implementation requirements, alongside distinct performance profiles in inference and realization. We further show that MLLMs' visual reconstruction ability does not necessarily imply an ability to generate code that meets these requirements. We release TaoD2C to support research on industrial UI code generation.

    benchmark
  36. arxiv:2610.10367 · cs.RO
    Temporally Interpretable Differentiable Decision Trees
    Eisuke Hirota, Aarav Sane, Rohan Paleja

    Interpretability offers a solution to safe autonomy by providing transparency into an agent's underlying decision-making model. Within sequential-decision making tasks, differentiable decision trees (DDTs) are one approach to such interpretability, maintaining automatic-differentiable policies while providing humans with a discrete tree-based visualization. Nonetheless, current implementations of DDTs are not well-suited for sequential-decision making domains, as there exists an inherent mismatch between a tree's single-timestep behavior and a human's multi-timestep planning. Our work thus introduces time as a new dimension of interpretability, coined as temporal interpretability, and demonstrates how temporal abstractions via action chunking improve it. We achieve this by first introducing two novel policy gradient algorithms that incorporate action chunking. Additionally, to maintain parameter-efficient trees, we develop an information-theoretic tree restructuring algorithm that modifies the tree during training. Across four simulation environments, we find that warm-starting action chunked DDTs from a distilled action chunked policy is the most effective way to obtain temporally interpretable trees: they match neural network policies in three of the four domains while using up to 80$\%$ fewer parameters. Our code is available at https://github.com/ei5uke/temp-interp.

    action chunking
  37. arxiv:2610.10359 · cs.RO
    MultiFly: A Real-World Multimodal Aerial Dataset with Annotation-Efficient Label Transfer and Cross-Modal Semantic Consistency
    Markus Gross, Andreas Greiner, Taehyoung Kim, Sivasubiramaniam Subbiah +11

    We introduce MultiFly, a real-world, low-altitude UAV dataset for semantic perception across RGB, thermal, LiDAR, and radar modalities. MultiFly provides 17,272 synchronized samples from four suburban scenes with frame-wise annotations for 15 semantic classes, together with calibration and GNSS-RTK/IMU measurements. To avoid costly and inconsistent modality-specific annotation, we propagate labels from only 115 manually annotated RGB images through shared geometric representations to all four modalities. This approach generates semantic labels for 17,157 additional RGB images, 17,272 thermal images, 840M LiDAR points, and 3.4M radar points. Transferred annotations achieve 89.93% average agreement with held-out manual annotations, and 90.94% average semantic consistency across all six modality pairs. We further establish semantic segmentation benchmarks for all four modalities, revealing distinct architectural behavior for dense LiDAR and sparse radar data. Taken together, MultiFly provides a scalable foundation for multimodal aerial perception and, to the best of our knowledge, the first public real-world low-altitude aerial benchmark that combines consistent frame-wise semantic annotations for RGB, thermal, LiDAR, and radar. Data at https://github.com/markus-42/multifly.

    benchmark
  38. arxiv:2610.10358 · cs.AI
    Open-MMUnlearning: Unifying Methods and Evaluation for MLLM Unlearning
    Junkai Chen, Yuhao He, Qianshan Wei, Junxiang You +18

    As multimodal large language models (MLLMs) become more capable and widely deployed, concerns about privacy and safety have become increasingly pressing. Machine unlearning offers one approach to addressing these concerns by removing designated information from trained models while preserving unrelated capabilities. However, fragmented implementations and evaluation protocols, incomplete robustness testing, and limited understanding of metric reliability make progress in MLLM unlearning difficult to assess systematically. We introduce Open-MMUnlearning, an open-source, extensible framework that integrates target-model preparation, multimodal data processing, unlearning, and evaluation through shared interfaces and structured configurations. The framework supports five benchmarks spanning privacy, safety, and copyright, eight MLLMs from four model families, and twelve unlearning methods. Its evaluation suite jointly assesses forgetting effectiveness, retained utility, and robustness to model interventions, adversarial inputs, and membership inference attacks. Using a common evaluation protocol, we compare ten representative unlearning methods. In this comparison, GD and MIP-Editor tie for the highest overall score: GD achieves the highest Forget Quality, while MIP-Editor preserves more Model Utility. We further introduce a metric meta-evaluation protocol that tests faithfulness using models with controlled exposure to target knowledge and robustness under quantization and relearning. Among the thirteen evaluated metrics, BLEU achieves the highest aggregate reliability score. KS-Test attains the highest faithfulness AUC but performs less well on robustness. Together, the framework and these findings support reproducible comparison of MLLM unlearning methods and systematic assessment of evaluation reliability.

    benchmarkevaluation protocol
  39. arxiv:2610.10355 · cs.AI
    MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent
    Zekai Liu, Zhilin Wang, Xuzheng He, Yu Cheng +1

    Text-to-music systems produce increasingly convincing audio, yet evaluation reveals little about whether the result matches user intent. A global text-audio relevance score can overlook the implicit intent in underspecified prompts and mask failures in specific requirements, such as instrumentation, structure, rhythm, or mood progression. To bridge this gap, we formulate text-to-music intent alignment as satisfying a per-request rubric of independently verifiable items covering both a request's explicit requirements and its implied musical intent. Scoring items individually makes evaluation diagnostic by intent source and musical dimension, rather than a single opaque score. We instantiate this as MuRA-Bench, a benchmark of real-world platform requests curated by music experts. We further propose MIRA (Musical Intent Refinement Agent), a test-time agent that first grounds a request's intent into rubrics, then searches over prompt revisions for a black-box generator under a bounded budget, iteratively generating music, verifying it against the rubrics, and using this feedback to guide a trajectory-aware tree search. Experiments across open-source and commercial backends show that MIRA improves intent alignment, enabling an open-source generator to achieve performance comparable to representative commercial systems (e.g. Suno and Mureka). Project page: https://mirareview.github.io/.

    agentbenchmark
  40. arxiv:2610.10346 · cs.RO
    Hall Effect-Based Tactile Force Detection Sensor for Robot-Assisted Minimally Invasive Surgery
    Charles DeLorey, Michael Brockdorff, Adam Metcalf, Benjamin Calmé +2

    Robotic minimally invasive surgery has revolutionized surgical practice. However, as the surgeons are mechanically separated from the surgical tools, loss of tactile feedback occurs. We present a compact force sensor with three, millimeter scale sensing elements (taxels) that can be affixed to the grasping face of a robotic surgical tool. The sensor features a miniaturized design using Hall effect sensors and magnets embedded in a deformable elastomer contact layer. Sensor calibration is achieved with a 6 degree of freedom (DoF) parallel robot. Each taxel can detect applied normal and shear forces with average RMSE of 2.133 kPa. The calibrated sensor was validated on phantom and ex vivo porcine tissue, demonstrating tactile sensing during retraction as well as slip. This work introduces a small-scale Hall effect based tactile sensor, enabling sensing for force-sensitive robotic surgical applications.

    tactilegrasp
  41. arxiv:2610.10345 · cs.AI
    SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic Routing
    Hui Zhang, Yachao Yuan, Jiayun Wang, Yuanzhuo Li +2

    Fine-tuning-as-a-service enables users to adapt aligned large language models (LLMs) to specialized tasks, but malicious fine-tuning can erode refusal behavior while preserving task performance on legitimate inputs. We revisit recent layer-wise safety diagnostics and find that safety sensitivity is signed: scaling different layers can strengthen refusal, weaken it, or have little effect. Motivated by this observation, we propose SLDR, a post-fine-tuning defense based on Selective Layers Recovery and Dynamic Routing. SLDR trains a LoRA recovery adapter only on the layers with the maximum and minimum sensitivity scores in the signed spectrum, and uses representation-based dynamic routing inference to activate the adapter only for malicious queries. Across four model architectures, five downstream tasks, and four harmful benchmarks, SLDR substantially reduces harmful outputs while preserving downstream utility. On Llama3.1/SST2, SLDR reduces the average harmful score from 11.54 to 0.08 while maintaining downstream accuracy, and the harmful score remains near zero under poisoning ratios up to 0.9. The code is available at https://github.com/Stardust457/SLDR.

    benchmark
  42. arxiv:2610.10324 · cs.AI
    Performance at What Cost? A Sustainability-Aware Performance Index for Cell and Nucleus Instance Segmentation
    Eiram Mahera Sheikh, Alaa Tharwat, Wolfram Schenck

    Pretrained models for cell and nuclear instance segmentation differ substantially in architecture, pretraining data and objectives, parameter count, inference strategy, adaptation requirements, postprocessing pipeline, and computational demand. Large pretrained and foundation models are increasingly adopted because of their strong zero-shot capabilities, but their use also imposes greater energy consumption, memory requirements, computational demands, adaptation costs, and operational carbon emissions. Whether these additional demands are justified by meaningful gains in segmentation performance remains unclear. We address this question by introducing the Sustainability-Aware Performance Index (SAPI), a configurable metric that combines segmentation performance, energy consumption, and model size. We benchmark 19 pretrained and foundation models across six CellBinDB datasets under zero-shot inference and evaluate 16 fine-tunable models using few-shot adaptation with both frozen encoder and full-model fine-tuning. We estimate energy consumption for GPU, CPU, and RAM using software-based monitoring tools. Our results show that larger and more computationally demanding models do not consistently achieve proportionate improvements in segmentation quality. While few-shot adaptation benefits several models, the gains and resource costs vary considerably across architectures, datasets, and adaptation strategies, causing SAPI-based rankings to differ from rankings based on performance alone. This study provides a practical framework for comparing segmentation models more comprehensively and supports more computationally accessible and environmentally responsible model selection in biomedical image analysis.

    memorybenchmark
  43. arxiv:2610.10320 · cs.AI
    LLM-Assisted Generation of Transparent, Open-Source Multiphysics Models of Electrochemical Devices
    Sebastian Castro, Maya F. Schuchert, Spencer A. McCluskey, Eric W. Lees +1

    Multiphysics continuum models are powerful tools for studying electrochemical devices, enabling in silico reactor design and resolution of local pH, potential, and concentration fields that govern device performance but are difficult to measure experimentally. However, constructing such models requires substantial numerical expertise or reliance on proprietary software. Here, we show that frontier large language model agents can remove this implementation burden while keeping the underlying physics under researcher control. Using one-dimensional electrochemical CO2 reduction to CO in a porous gas diffusion electrode as a test case, we develop a machine-readable, human-specified modeling harness containing governing equations, parameters, numerical methods, logical build stages, and human-verifiable checkpoints. From this specification, the agent reproducibly constructs complete multiphysics models in open-source Julia. Independently built models, including fully autonomous agent-built models, agree with an equivalent COMSOL implementation to within 0.7% of the peak CO partial current density, and with one another to within 0.04%. Systematically planted errors demonstrate the importance of explicit specifications for reproducibility and reveal the agent's capabilities and limitations in debugging model physics. This framework establishes a more transparent approach to multiphysics modeling in which physical descriptions and governing equations, rather than specialized code, become the primary inputs for computational model development.

    agentautonomous agent
  44. arxiv:2610.10304 · cs.AI
    SemanticFold: Latent Sequence Compression SeparatesLanguage Modeling, Decodability, and Reasoning
    Mingyan Liu, Min Huang

    We study whether latent sequence compression of prompt prefixes preserves the capabilities that large language models rely on during inference. We introduce SemanticFold, a compression scheme that folds prefix hidden states at learned boundaries, and evaluate it across five model scales: Qwen3-1.7B, Qwen3-8B, SmolLM2-1.7B, Pythia-1.4B, and Pythia-6.9B. We use a fixed-target protocol: a frozen prefix is executed natively or compressed, and both arms teacher-force identical continuation tokens. This design rules out target-selection explanations for likelihood changes. We examine five endpoint families: fixed-target negative log-likelihood, finite-label reasoning accuracy, linear probe accessibility, open-ended generation, and systems-level memory and latency. We find that compression moves these endpoints non-monotonically and that they do not share a single compression threshold. On Qwen3-1.7B at compression ratio R=1.7, compressed-minus-native mean NLL decreases by 0.135 under paired bootstrap with 10000 draws. On SmolLM2 at R=1.2, the mean change is 0.013 higher than native. On both Pythia checkpoints, NLL is effectively unchanged. An NLL decomposition separating sequence shortening from the learned residual transform shows that the favorable Qwen likelihood is attributable primarily to residual adaptation rather than to shortening alone. MLP-only, which applies the transform without shortening, achieves 0.082 lower NLL than Full SemanticFold. Linear probe accuracy and macro AUC change by less than 0.03 in absolute value across conditions, with confidence intervals crossing zero. We conclude that preservation under latent compression has no single scalar certificate: language-model fit, decodability, and reasoning behavior answer different questions and can move in different directions under the same compression operation.

    memory
  45. arxiv:2610.10297 · cs.RO
    Energy-Efficient Gait Adaptation via Hierarchical Reinforcement Learning for Quadrupedal Locomotion Across Diverse Terrains
    Ammar Issa, Anubhav Singh, Anton Tsaritsin, Sergey Kolyubin

    While energy efficiency is a critical objective for legged-robot locomotion control, achieving low energy consumption while maintaining robust performance across different velocity ranges and terrain conditions remains a key challenge. This is particularly true for end-to-end RL policies, where gait generation, motion execution, and energy optimization are tightly coupled, leading to high sensitivity to reward design. In this work, we propose a hierarchical reinforcement learning (HRL) framework that separates a high-frequency policy for stable and robust joint-level motion execution from low-frequency gait adaptation that explicitly minimizes the cost of transport (CoT). The three-stage Isaac-based training procedure enables zero-shot sim-to-real transfer with improved tracking accuracy, robustness, and energy efficiency. The learned hierarchy exhibits automatic speed-dependent gait adaptation, transitioning from pacing at low speeds to trotting at higher speeds. We validate the proposed approach in simulation against representative single-policy and hierarchical locomotion baselines, demonstrating reduced CoT over a broad range of commanded velocities, while maintaining robust locomotion across flat, uneven rough, and inclined terrains. We further demonstrate its practical feasibility through zero-shot deployment on a physical Unitree AlienGo quadruped.

    quadrupedsim-to-real
  46. arxiv:2610.10285 · cs.AI
    AI Safety Considerations for Agents With Limited Time to Act
    Leo Zeitler, Jack Richings, Victoria Nockles

    In the wake of the increasingly public discussion about AI alignment, recent work has tried to propose specific AI architectures that behave safely. However, the proposed arguments that seemingly demonstrate proved alignment mostly neglect the environment the agent needs to act in. We discuss theoretical bounds for agent-agnostic safety guarantees in environments that can only be partially observed and within which an action is required within limited time. We introduce two realistic scenarios, one with an infinite state space and one with signal mixture. In these scenarios, we prove that even a perfect agent cannot guarantee safe behaviour. It will be argued that for any proof of AI safety or alignment, the environment and associated safe actions need to be specifically considered together with the agent.

    agent
  47. arxiv:2610.10283 · cs.RO
    Temporal Visuo-Tactile Learning for Dexterous Grasp Stability
    Ken Nakahara, Aleksei Buvailik, Prokhor Kotov, Roberto Calandra

    Humans can grasp everyday objects with almost perfect success rates using fingertip tactile feedback, yet much of the robotic grasping literature emphasizes vision-based grasp selection with parallel grippers. In this work, we systematically investigate how high-resolution, dynamic tactile sensing contributes to grasp stability prediction and model-guided grasping in dexterous robotic hands. To this end, we collected a dataset of 10,000 grasp trials across 200 objects using a multi-fingered robotic hand equipped with four Digit 360 tactile sensors, recording external vision, proprioception, and tactile streams throughout each grasp. With this dataset, we trained end-to-end temporal multimodal models to predict post-lift stability from pre-lift grasp observations and compared sensing modalities and encoding backbones. Experimental results and controlled input ablations show that incorporating touch, and particularly high-resolution, dynamic touch, improves grasp stability prediction. Finally, we deployed the learned predictor as an online stability gate on the real robot, where visuo-tactile model-guided regrasping improved the success rate among executed lifts by 10.5 percentage points over a non-tactile gate. These results show how rich fingertip sensing and expressive temporal models that capture the dynamics of touch can support learned grasping with multi-fingered hands without explicit contact or force modeling, providing a scalable data-driven path from tactile experience toward stable dexterous manipulation. The dataset is publicly available at https://lasr-lab.github.io/dexterous-grasp-stability/.

    manipulationdexteroustactilegrippergrasp
  48. arxiv:2610.10281 · cs.RO
    Making Task Abstractions Executable: Control-Aware Layout Repair for a Fixed Controller
    Chiyoung Kim, Seungyeon Back, Sumin Shim, Doyoung Heo +1

    A task abstraction can specify the intended events while its spatial layout prevents a fixed agent and controller from completing them. Starting from a supplied structured task record, we compile whole-task tracking, clearance, and actuation requirements into auditable affine layout constraints. We repair only declared continuous coordinates, preserving event order, timing, topology, and the controller. A most-violated-row update admits conditional finite-certification and net-displacement bounds; a same-compiler quadratic projection separates the representation from the optimizer. On three researcher-authored task abstractions, both backends certify all three layouts and complete all 300 fresh paired rollouts per backend. A risk-target sweep also exposes fixed event tests that the chosen certificate cannot satisfy through layout edits alone.

    agent
  49. arxiv:2610.10276 · cs.CL
    PatchBench: Measuring Collateral Damage in Activation Patching
    Alexi Canesse, Mathis Le Bail, Maël Jenny, Clément Elliker +2

    An LLM safety patch can pass a benchmark while still being a poor repair. This risk is especially acute for jailbreak repairs, where the goal is to correct a specific unsafe behaviour without changing unrelated behaviours. A patch may block exact evaluation prompts yet fail on close harmful variants, or suppress harmful behaviour by over-refusing benign prompts that share its wording or structure. Existing protocols primarily test whether models can be broken, while aggregate metrics (attack success, refusal rates, global capability) cannot distinguish selective repairs from broader local suppression. To address this gap, we introduce PatchBench, a benchmark of empirically observed model-specific jailbreak failures inducing actionable harmful answers. Starting from 27,870 prompts from 37 public datasets, we curate 15,314 English prompts and query 8 open-source instruction-tuned models. Combining WildGuard filtering, pairwise Elo ranking, and manual verification, we retain a curated bank of 400 high-confidence jailbreak failures. We further introduce PatchBench-Local, an evaluation protocol testing whether a patch is behaviourally precise. For each harmful source prompt, PatchBench-Local generates three families of local neighbours: harmful variants preserving malicious intent, benign prompts with matched structure, and benign prompts reusing key harmful terms. It evaluates harmful-neighbour correction and benign-neighbour preservation, distinguishing selective repair from broader local suppression. Evaluating four activation steering methods with PatchBench-Local and MMLU shows that global capability can remain nearly unchanged while local benign regressions are severe, confirming aggregate metrics miss important collateral damage. PatchBench-Local provides a more precise basis for developing and comparing jailbreak repair methods.

    benchmarkevaluation protocol
  50. arxiv:2610.10270 · cs.RO
    Video Prediction Policy 2: Predict Better, Act Better
    Yanjiang Guo, Haodong Yan, Zhide Zhong, Zhongru Zhang +14

    World action models (WAMs) have emerged as an important class of generalist robot policies, aiming to transfer video prediction priors to action learning. However, we find that existing WAMs frequently produce incorrect motion predictions in open-ended environment, leading to erroneous actions. We attribute this limitation to two factors: (1) base video models are not optimized for manipulation, and (2) naively incorporating action components into video models can substantially degrade their generalization capabilities. We introduce Video Prediction Policy 2 (VPP2), a WAM that enables strong zero-shot generalization in both video prediction and action generation. First, we curate a large-scale, diverse dataset of manipulation videos to continue pretraining the base video foundation model. We annotate video clips with detailed captions and perform \textit{event-level} video pretraining to promote generalization across open-ended manipulation tasks. Second, we post-train and distill the video model into a single-step visual planner with fixed prediction horizon. Finally, we introduce action module via a mixture-of-transformers (MoT) architecture to learn implicit inverse dynamics model. Experiments demonstrate three key results: (1) VPP2-14B outperforms Cosmos3-64B by 11.0\% points in video prediction instruction-following success rate on open-ended tasks; (2) VPP2 surpasses the strongest baseline by 18.5\% points in success rate on real-world zero-shot ALOHA manipulation tasks; and (3) following benchmark-specific post-training, VPP2 achieves the highest success rates among evaluated methods on the challenging LIBERO-Pro, LIBERO-OOD, and RoboDojo benchmarks.

    manipulationliberopost-trainingbenchmark
  51. arxiv:2610.10266 · cs.AI
    LoomSC: Scalable Deep Subspace Clustering with Projector Factorization and Exact Spectral Reduction
    Nairouz Mrabah, Youssef Melki, Mohamed Bouguessa, Riadh Ksantini +2

    Dense self-expression matrices and full-affinity spectral clustering limit the scalability of subspace clustering. We introduce the Latent Orthogonal Optimization Model for Subspace Clustering (LoomSC), a framework that addresses both bottlenecks through projector factorization and exact spectral reduction. Motivated by the spectral structure of least-squares regression, LoomSC jointly learns latent features and a projector self-representation through two thin factors. Alternating Procrustes and least-squares updates preserve the sample factor's orthogonality while keeping the coefficient matrix implicit. We construct a nonnegative quadratic affinity that preserves the projector's support. An exact feature map then reduces its normalized spectral problem to an eigenproblem whose dimension depends only on the factor width. Neither the full affinity nor the sample Laplacian needs to be formed. Our analysis quantifies the projector approximation and identifies conditions for subspace preservation and within-subspace connectivity. For fixed dimensions and iteration budgets, the complete pipeline has linear time and memory complexity in the number of samples. Across five image-clustering benchmarks, LoomSC ranks first or second in all 15 dataset-metric comparisons against 9 state-of-the-art baselines. Its mean accuracy exceeds the highest baseline mean by 6.66 percentage points. Synthetic experiments scale to 500,000 samples while maintaining at least 99.8% accuracy.

    memorybenchmark
  52. arxiv:2610.10265 · cs.AI
    Stale, Misattributed, or Late: Where Personal Memory Fails Before Generation
    Haonan Deng, Park Sinchaisri

    Personal memory for language agents is usually judged by whether the final an- swer is correct. That score hides errors that arise before generation: the memory block may contain an obsolete value, a fact about the wrong person, or no use- ful fact before the serving deadline. We measure these failures directly. Using Personal Fact Memory (PFM) as a reference layer, we find that temporal validity is primarily a property of memory construction in our setting. On a controlled revision benchmark, serving only the active value of each correctly keyed slot eliminates observed stale exposure; without update resolution, 70.3% of prompts expose a superseded value. Once retrievers share the same active store and par- ticipant information, participant-aware BM25 is equivalent to the reference ranker within a prespecified 0.02 margin. The harder problem is assigning revisions to the right slot. Missed merges leave stale values active, whereas false merges silently remove current values; four LLM key assigners achieve higher key re- call than a rule extractor yet produce lower clean-retrieval rates, and open-domain merge recall on LongMemEval never exceeds 0.062. Misattribution survives va- lidity filtering: an entity posterior reduces same-name exposure on controlled data but cannot distinguish identically named speakers in LoCoMo. Two frozen lan- guage models reproduce prompt errors in generated text. Retrieval latency varies across rankers, but prompt prefill dominates turn-level latency on our hardware. These results argue for evaluating agent memory before generation, separating stored-state validity, identity resolution, abstention, and serving latency.

    memoryagent memoryagentbenchmark
  53. arxiv:2610.10258 · cs.AI
    QuSema: Detecting Silent Bugs in Quantum Libraries via Quantum-knowledge-enhanced Agents
    Yujin Song, Kaining Zhang, Qixin Zhang, Shuai Wang +2

    Quantum libraries are now critical infrastructure for quantum algorithm development, yet their correctness remains difficult to test. Existing testing techniques mainly rely on failure-based or comparison-based oracles, exposing bugs only when executions fail, violate runtime checks, or disagree with another implementation. Their applicability is limited when suitable execution-based oracles are unavailable, leaving some silent bugs undetected. Such missed bugs can produce incorrect results that propagate into experimental conclusions, simulation studies, and algorithmic designs. Here we present QuSema, an autonomous testing agent for finding silent bugs in quantum libraries. QuSema uses constraints from quantum semantics and documentation as a source-level semantic oracle to assess whether implementation logic can produce invalid outputs from valid inputs. It operates through an agentic loop that repeatedly inspects library API documentation and source code, reasons about the intended behavior of quantum operations, identifies potential semantic deviations, and validates them by generating executable tests through library APIs. Guided by quantum-domain reasoning, QuSema turns high-level behavioral mismatches into concrete, user-triggerable bug reports, enabling it to uncover non-crash defects. We implement QuSema for Qiskit and PennyLane. On a benchmark of 20 historical silent bugs, QuSema achieves higher mean bug relocation counts than Claude Code and Codex, with the DeepSeek configuration costing less than Claude Code. QuSema also discovers 40 previously unknown bugs confirmed by the developers, including 30 silent bugs.

    agentagenticbenchmark
  54. arxiv:2610.10232 · cs.AI
    LLM Persuasion Is in the Eye of the Evaluation
    Kamile Dementaviciute, Julija Vaitonyte, Tijl De Bie

    Large language models (LLMs) have already been shown to match or exceed human experts in persuasion. While their persuasive capabilities hold promise for beneficial uses such as education and health communication, they can also be used to manipulate and misinform, making their evaluation a growing priority for developers and regulators. That evaluation, however, remains fragmented: studies differ in what they treat as persuasion, and broad claims often rest on narrow, situation-specific assessments. Automated methods, often modelled on human studies, offer a way to compare such assessments directly, as they can be run on the same models at scale and can include high-risk forms of persuasion that would be difficult or unethical to test on people. In this study, we adapt nine published automated methods to a shared setup, run them on the same fifteen LLMs, and ask whether their rankings agree and why. We find that the methods agree only weakly (mean Spearman $ρ= 0.25$). Our analyses point to two contributing factors. Models that refuse some tasks but not others, directly or indirectly, lower agreement by about a quarter, and these refusals fall mostly on manipulation tasks. General capability also plays a part: most rational persuasion (non-manipulative) methods track it, whereas most manipulation methods do not. Together, these findings suggest that agreement depends more on the task a method sets than on how it scores persuasion, although this pattern is only indicative given the eight methods available for analysis. More broadly, our results suggest that persuasion scores combine a model's ability to persuade with its willingness to do so. A single score is therefore informative about its own setting, but says little about a model's persuasiveness across tasks.

    manipulation
  55. arxiv:2610.10198 · cs.RO
    Benchmarking Behavioral Steerability in Behavior Foundation Models
    Minghe Gao, Zhanxi Yan, Jiahui Liu, Wendong Bu +8

    Behavior Foundation Models (BFMs) are emerging as a paradigm for translating human intentions into executable humanoid behaviors. As these models evolve beyond behavior generation toward general-purpose behavioral systems, a fundamental question arises: can they be reliably steered according to user intentions? In this paper, we introduce the concept of behavioral steerability, defined as the ability of BFMs to faithfully generate behaviors that satisfy user-specified intentions. To study this capability, we present RoboSteer, the first benchmark for behavioral steerability in BFMs. RoboSteer organizes behavioral steerability into a three-level hierarchy-Conditional Steering, Constraint Steering, and Compositional Steering-and establishes a unified evaluation framework supported by a large-scale multimodal motion corpus. Using RoboSteer, we conduct the first large-scale empirical study of behavioral steerability across 9 existing BFMs. We view behavioral steerability as more than a capability for controlling motion: it concerns how embodied systems translate human intentions into purposeful actions. We hope RoboSteer will advance research on intention realization as a foundation for general-purpose embodied intelligence.

    embodiedhumanoidbenchmarkevaluation framework
  56. arxiv:2610.10184 · cs.AI
    Agentic AI-Assisted Modeling for Production Scheduling: Assessment in Constraint Programming
    Ángel Sánchez-Fernández, Javier Pernas-Álvarez, Diego Crespo-Pereira

    Developing optimization models for production scheduling requires substantial expert effort. Research on large language models (LLMs) has followed two directions: specialized approaches for automated modeling, mostly for mixed-integer linear programming, which often rely on dedicated training or problem-specific architectures that limit industrial deployment; and agentic artificial intelligence for operational decision support, which generally assumes that the optimization model already exists. This study bridges both directions by assessing whether general-purpose LLMs, orchestrated as agents without task-specific training, can formulate and implement constraint programming models from natural-language problem descriptions. Singleagent and multi-agent architectures are integrated with a Model Context Protocol server that provides context-aware retrieval of solver documentation to mitigate hallucinations during implementation. Both are compared with a direct LLM baseline on six industry-oriented problems covering flow-shop, job-shop, flexible job-shop and resource-constrained warehouse scheduling, using three LLMs and assessing modeling accuracy, execution success, latency and token consumption. Formulation proves largely within reach of current LLMs, whereas implementation is the main barrier. The multi-agent workflow raises the share of scripts that run correctly as generated from 14.8% with a direct LLM call to 59.3%, reaching 80.6% on the four less complex problems, while tightly coupled intralogistics models remain an open challenge.

    multi-agentagentic
  57. arxiv:2610.10183 · cs.AI
    VideoEvolve: Co-Evolving Memory and Retrieval for Long Video Understanding
    Yongchao Xu, Bowen Ye, Jiefeng Gan, Junkai Ma +4

    Long video understanding increasingly relies on external memory to organize massive visual streams into compact representations. However, most memory-based methods dynamically adapt how information is retrieved for different questions, while largely fixing what is remembered. This mismatch makes missing details costly to recover, whereas stored information is valuable only when it can be reliably retrieved. To address this issue, we propose VideoEvolve, a novel self-evolving framework that jointly evolves memory and retrieval for long video understanding. Specifically, starting from a coarse low-frame-rate overview, VideoEvolve couples a Memory Evolver for selective memory augmentation with a Retrieval Evolver for adaptive retrieval over the evolving memory. We then co-evolve the two Evolvers through alternating agentic reinforcement learning (Agentic RL), updating one while freezing the other. To steer this alternating evolution, Bottleneck-Aware Evolution Feedback (BEF) identifies whether the current bottleneck lies in memory or retrieval and directs optimization toward the more limiting side. Furthermore, VideoEvolve introduces Capability-Aware Evolution Feedback (CEF) to alleviate downstream feedback from over-specializing memory to a fixed set of training questions, shifting training toward underdeveloped yet learnable video capabilities. By integrating Agentic RL with BEF and CEF, VideoEvolve transforms downstream reasoning experience into transferable capability updates, providing a concrete path from static long-video systems toward experience-driven, self-improving multimodal intelligence. Extensive experiments on multiple long video understanding benchmarks demonstrate the effectiveness of VideoEvolve.

    memoryexternal memoryagenticself-improvingself-evolvingbenchmark
  58. arxiv:2610.10179 · cs.AI
    Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search Agents
    Wenyu Huang, Xinyu Hou, Pavlos Vougiouklis, Ruofei Lai +1

    Search agents enable Large Language Models (LLMs) to iteratively retrieve and use information for complex multi-hop questions. Reinforcement Learning with Verifiable Rewards (RLVR) offers a promising approach for post-training such agents, but its reliance on sparse, outcome-based supervision can make credit assignment difficult and limit learning efficiency. In this paper, we systematically investigate how intermediate supervision can improve reinforcement learning for search agents. We study a range of reward-shaping and credit-assignment strategies that provide learning signals from intermediate retrieval steps. Building on these insights, we develop a training framework that combines intermediate signals with final outcome rewards to improve learning from multi-step search trajectories. Experiments across multiple benchmarks under matched training conditions demonstrate improvements in aggregate search-agent performance and show that both the choice of intermediate signal and where its credit is assigned affect training behaviour. These findings show that reward design and credit assignment are important design dimensions for training effective search agents.

    post-trainingbenchmark
  59. arxiv:2610.10178 · cs.RO
    Do Vision-Language-Action Models Understand Instructions? A Mechanistic Interpretability Study on Language Grounding
    Theodor Wulff, Angelo Cangelosi

    Vision-Language-Action models are designed to generalise across environments and task descriptions, raising the question of whether their action generation actually depends on the language instruction, or whether they largely rely on visual cues and superficial correlations. Robustness to variance in the visual and linguistic observation space is critical for real-world deployment, yet VLAs lack explicit grounding modules and instead rely on the intrinsic language grounding capabilities of their Vision-Language model backbones. For this reason, we conduct a controlled mechanistic interpretability study on the language grounding capabilities of two state-of-the-art Vision-Language-Action models, $π_{0.5}$ and GR00T N1.7, by applying activation and attribution patching to the residual stream of the action generation modules. We systematically corrupt the task instruction of input samples of the LIBERO benchmark following five strategies: synonym replacement, semantic scaling, directional corruption, random object substitution, and empty string. Our experiments find that both models are comparatively insensitive to abstract rephrasing and to referencing non-existent objects, but react strongly to empty task descriptions and, especially, to directional language. During action generation, this sensitivity is concentrated in different loci for each model: mainly in the early, periodic cross-attention layers for GR00T N1.7, versus distributed across the earliest and selected later layers for $π_{0.5}$. For GR00T N1.7, directional perturbations drive some of the largest causal effects while leaving the internal representational geometry comparatively unchanged, a dissociation we do not observe clearly for $π_{0.5}$. Finally, the reliability of attribution patching is model-dependent: it closely tracks activation patching for GR00T N1.7 but not for $π_{0.5}$.

    vision-language-actiongr00tliberobenchmark
  60. arxiv:2610.10170 · cs.AI
    Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two Corpora
    Andrey Kuehlkamp, Priscila Correa Saboia Moreira, Samuel Rund

    Retrieval-augmented generation systems increasingly rely on document-structure treatments: structure-aligned chunking, LLM-generated chunk contexts, heading-path metadata, and hierarchical two-stage retrieval. Separate studies support each on different corpora, embedders, and metrics, and none control for a shared confound: any text prepended to a chunk perturbs its embedding. We present a mechanism-isolating ablation testing all four treatments under one protocol, matching chunk sizes across conditions and adding a semantically null placebo---heading paths that are structurally valid but shuffled across documents. We score retrieval with a coverage-aware nDCG and test four pre-registered contrasts via document-clustered bootstrap with Holm correction, on two distant corpora: 200 Wikipedia Featured Articles (951 queries) and 1,585 QASPER papers (4,303 questions). Organization helps, and the cause is content, not tokens: structure-aligned chunks with real heading paths beat contextualized fixed windows (+0.022 / +0.012 cov-nDCG@10) and the placebo (+0.010 / +0.016). Naive two-stage hierarchical retrieval hurts (-0.033 / -0.015), traceable to first-stage section recall. Gold structure beats LLM-induced structure on Wikipedia but not on QASPER. Effects are small ($dz$ 0.06-0.11) but Holm-significant and consistent across corpora.

    retrieval-augmented
  61. arxiv:2610.10138 · cs.CL
    LLM4Impact: Integrating Heterogeneous Information for Scientific Impact Prediction
    Yong Cao, Markus Flicke, Haoyu He, Katrin Renz +1

    Predicting the future impact of a newly published paper is challenging because it must be inferred from heterogeneous evidence available at publication time. Existing approaches often rely on a single source of information or combine multiple sources without accounting for their different predictive roles. In this paper, we present LLM4Impact, an evidence-aware method for scientific impact prediction that learns to represent, integrate, and calibrate heterogeneous information. LLM4Impact combines semantic, graph, LLM, and temporal representations, and injects graph information into a frozen LLM through continuous prefix tokens. A context aware gating mechanism adaptively weights different evidence, while a separate calibration module accounts for domain and temporal variation in citation scales. We further construct a large-scale benchmark dataset with 2 million papers, leakage-safe point-in-time heterogeneous ego graphs, temporal splits, and both year-level and month-level citation targets. Experiments show that LLM4Impact consistently outperforms strong semantic, graph, and LLM based baselines, with a 10.13% reduction in year RMSE on the in distribution test set and a 6.87% reduction under out-of-domain distribution. Our results reveal that the value of such evidence is context dependent: different papers benefit from different sources, while domain and publication time affect how evidence translates into citations. This finding motivates adaptive evidence selection and context-conditioned calibration rather than simply richer representations. We will release our code, benchmark, and an interactive web demonstration upon publication.

    benchmark
  62. arxiv:2610.10129 · cs.AI
    When Algorithmic Exploration Becomes Cheap: A Case Study of Agentic Research in EDA
    Keren Zhu, Yu Deng, Xiaoyu Hao, Liwen Jiang +5

    As EDA researchers, we conducted eight deliberate trials of agentic algorithm exploration, selecting several topics outside our areas of depth. One faculty member and seven students participated, including students without publication experience. With limited intervention in the algorithms, agents developed mathematical constructions, analyzed existing tools, and implemented improvements; some efforts fell short of their practical goals. We also used AI to collect, classify, and analyze 8,420 papers from four EDA conferences and two journals over 2022-2026. Among 2,380 primary-core papers, we classified 97.7% from titles and abstracts as computationally closed, including work on new formulations. Together, these observations suggest that much of EDA offers an executable environment for increasingly accessible algorithm research. We see an opportunity for tool developers to investigate ideas they previously lacked time to pursue. We also ask how EDA should validate and reward research when results become easier to produce than to examine, and what papers and venue labels will continue to tell us about a contribution.

    agentic
  63. arxiv:2610.10126 · cs.AI
    Know the Shape, Find the Fault: Topology-Conditioned Diagnosis of Multi-Agent LLM Failures
    Xinwen Liu, Zhuocheng Pan, Isabella Zhu, Jawei Zhang +2

    Multi-agent LLM systems coordinate task execution through exchanges of information among agents. When coordination breaks down, similar symptoms in execution traces can reflect different problems in how information is passed, used, or verified. Communication topology captures how agents exchange information and provides structural cues for distinguishing coordination failure modes. Using these cues for diagnosis requires establishing how topology relates to failure patterns and recovering the relevant structure from execution traces that lack explicit topology labels. We analyze the relationship between communication topology and failure patterns and introduce MAScope, a two-stage framework for topology-conditioned diagnosis. Its Trace Structural Extractor TSE recovers communication topology from heterogeneous execution traces by grounding an interaction graph in message evidence. The Topology-Conditioned Judge TC-Judge then classifies failures using the trace, predicted topology, an empirical failure prior estimated from separate labeled traces, and a short description of topology-specific failure patterns. Under a fixed orchestration structure, the recovered topology can be reused across executions. Experimental results show a statistically significant association between communication topology and failure type, with $χ^2 = 409.9$ and $p = 1.2 \times 10^{-70}$. On the \num{851} MAST-clean traces, ground-truth topology context raises gpt-mini's Macro-F1 from $0.173$ to $0.350$. With predicted topology, the pipeline achieves $0.346$, approaching the trace-only gpt-5.4 baseline of $0.372$. For \num{1000} traces under a fixed orchestration structure, the projected pipeline cost, including one topology extraction, is approximately $6\%$ of repeated gpt-5.4 diagnosis cost. These results show that topology-conditioned context improves failure diagnosis and supports lower-cost deployment.

    multi-agent
  64. arxiv:2610.10125 · cs.RO
    Lifelong small-object navigation in changing object layouts: a benchmark and method
    Jiagan Huang, Zikun Zhou, Zijian Ni, Hongpeng Wang +3

    Household robots need to continually navigate to different objects in the same environment, many of which are small and portable, such as tools and toys. Their small visual footprint and frequent occlusion make reliable observation difficult, and they may be moved by people without the robot observing the changes. We formulate this challenging task as Lifelong Small-object Navigation in Changing Object Layouts (LiSoNav-COL). Agents must seek suitable viewpoints for reliable observation, accumulate and reuse scene knowledge to efficiently locate subsequent targets, and update outdated memory after object relocation. To eliminate the need for prior scene scanning, we also require agents to start navigation with empty scene memory. Although practical, this task still lacks benchmarks designed around its defining assumptions. To bridge this gap, we introduce LiSoNav-Eval, a dedicated benchmark spanning 28 indoor scenes with 45 small-object categories. Its lifelong navigation sequences include both unchanged and relocated targets to evaluate memory reuse and adaptation to object relocation. To address this challenging task, we propose a navigation method based on multi-view Inspection with Viewpoint-Anchored Memory, dubbed IVAM-Nav. IVAM-Nav actively observes supporting surfaces from complementary viewpoints for reliable small-object perception and anchors the resulting memory to their observation viewpoints, supporting relational memory reuse and revalidation under similar viewing conditions. Extensive experiments on LiSoNav-Eval demonstrate favorable performance of IVAM-Nav against representative methods. Benchmark analyses also show that smaller objects, larger environments, and longer relocation distances pose greater challenges. The dataset and code are available here.

    memorybenchmark
  65. arxiv:2610.10120 · cs.AI
    RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward Adaptation
    Hengbo Xiao, Boyao Zhang, Purui Liu, Yuxuan Zheng +3

    Reinforcement learning with verifiable rewards (RLVR) has driven substantial progress in domains where task outcomes can be reliably evaluated, but long-horizon interaction remains challenging due to sparse terminal feedback and difficult credit assignment. Process rewards provide denser supervision, yet the capabilities most relevant for training can change as the policy evolves: a behavior that is easy to evaluate or frequently deficient need not be the bottleneck currently limiting task success. We introduce RewardWeaver, a self-evolving reward adaptation framework for language agents in long-horizon interaction. RewardWeaver maintains a validated capability space in which the semantics of admitted Rubrics remain fixed, and closes the loop between policy optimization, task evaluation, failure attribution, and reward adaptation. After each training stage, it performs outcome-grounded backward attribution on low-outcome trajectories, aggregates recurrent and policy-controlled capability bottlenecks, and dynamically selects the corresponding process rewards for the next stage. Recurrent failures not covered by the existing capability space trigger a separate, controlled expansion procedure. We evaluate REWARDWEAVER on SOTOPIA, Amazon?HistoryPrice, and a newly constructed Sales Benchmark. Across social interaction, bilateral bargaining, and domain-specific sales, REWARDWEAVER establishes new state-of-the-art (SOTA) results. Ablations further demonstrate the importance of dynamic reward allocation, failure-grounded attribution, and stable semantics for admitted capabilities.

    self-evolvingbenchmark
  66. arxiv:2610.10118 · cs.CL
    YANchor-4B: Effective Long-Horizon Reasoning in O(N) Time with O(1) Memory
    Huishan Ji, Hua Xu, Weiming Zhang, Qirui Ye

    Long-horizon reasoning demands access to earlier information at a manageable generation cost. Full-history attention incurs growing storage and computation, while recurrent compression can lose precise details. Therefore, we present YANchor-4B, a general-purpose recurrent model that preserves crucial memory as ANchors for retrieval during subsequent reasoning. Beyond $O(N)$-time generation and $O(1)$ memory, YANchor enables effective long-horizon reasoning through its multidimensional memory mechanism. For example, on challenging math problems, it achieves 82.93% mean pass@1 on AIME 2024--2026 and 63.64% on HMMT, substantially outperforming linear-time, constant-state counterparts, including larger models. It also delivers several-fold higher batched long-generation throughput than Transformer and hybrid baselines on H100. Furthermore, evaluations across dozens of benchmarks demonstrate YANchor's superiority in general-purpose capabilities.

    memorybenchmark
  67. arxiv:2610.10114 · cs.CL
    Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position
    Xiaoran Liu, Ziwei He, Xipeng Qiu

    The architectural design of Large Language Models (LLMs) is shifting from traditional full-attention-only models to hybrid models, which combine different attention modules to improve long-context efficiency and performance in length extrapolation and context extension. To explain why hybrid models work and how to design them better, we propose Mechanics of Long-Context Hybrid Models. As Part 1.1 of this series, we begin with hybrids of full attention and either sliding-window attention (SWA) or gated variants of linear attention (LA), represented by GLA and GDN. We first observe a Seesaw Effect in Context Extension: LA hybrids benefit more from long-context continual pretraining, whereas SWA hybrids perform better under length extrapolation. We attribute this behavior to differences in the positional inductive biases induced by these attention mechanisms. We find that SWA hybrids suffer from a Short-Context Learning Trap, Short-Window Weariness, and Long-Window Laziness, and require extended windows to enhance performance in continual long-context pretraining. For LA hybrids, we summarize the Matthew Effect of Hybrid Position Extrapolation and propose Sliding-Window Linear Attention, achieving 16$\times$ training-free length extrapolation while maintaining 100\% accuracy on NIAH-SK1 in 64k context length.

    long-context
  68. arxiv:2610.10100 · cs.MA
    The Cost of Classical Multi-Agent Path Finding
    Alvin Combrink, Sabino Francesco Roselli, Martin Fabian

    Multi-Agent Path Finding (MAPF) is the problem of planning conflict-free paths for multiple agents in a shared space, each from its start to its goal. Classical MAPF has been the dominant formulation for many years, with its assumptions of discrete time and graph-based conflicts presumably easing the search for solutions. These assumptions limit the physical environments and agents for which a solution is truly collision-free, and also place an upper bound on solution quality that no algorithmic improvements can lift. This work investigates how much solution quality, and in what contexts, the classical MAPF formulation forfeits. Continuous-time MAPF (MAPF$_R$) relaxes these assumptions, making it a natural counter-formulation to compare against across various agent counts and sizes, and graph connectedness, topologies, and resolutions. We find that continuous time and agent shape consideration are worth relatively little on their own; their value comes from enabling an expanded range of move actions, on average improving solution quality by at least $5\%$ on narrow and constrained maps and $17\%$ on maps with open spaces. In some cases, the improvements exceed $20\%$. Doubling the map resolution with classical MAPF recovers less than $3\%$, meaning that little of what is forfeited can be bought back through more compute. This work therefore provides insight on when classical MAPF is a reasonable simplification, and when MAPF$_R$ unlocks significantly higher-quality solutions.

    agentmulti-agent
  69. arxiv:2610.10092 · cs.CL
    I would rather quit NLP than read another paper like this: The rise of antithesis in NLP papers
    Olga Zamaraeva, Adrián Gude, Roi Santos-Ríos, Carlos Gómez-Rodríguez

    For better or worse, LLMs are by now used routinely for scientific writing.\footnote{This paper is no exception; we did use AI to assist with writing some of the sections (see Acknowledgments).} Many have noticed that recent models fill papers with unnecessary antithesis, stating over and over what the work does not do, in ways that do not contribute to its precision or quality of expression and annoy reviewers \emph{rather than impressing them}. We study the construction \emph{rather than} in ACL papers from 2019, ACL-style arXiv papers from 2026, and papers written by GPT models from the same titles and abstracts. Its rate in 2026 is seven times the 2019 rate, and higher still in the GPT papers. Two annotators, blind to the source, find almost no 2019 use \emph{annoying} and about one in ten 2026 uses; they seldom agree on which, yet about half of 2026 papers contain a use that annoys each of them. \emph{Annoying} uses present the rejected alternative less favorably than legitimate uses. Raters of preference data and open reward models favor the construction, and an instruction to be honest promotes it. We conjecture that it is a side effect of post-training on pairwise preferences, which credit a disavowal in a single response and cannot register its cost across a text.

    post-training
  70. arxiv:2610.10091 · cs.AI
    ExperienceIndex: Artifact-Grounded Memory
    Peter Baile Chen, Geoffrey X. Yu, Xinming Liu, Samuel Madden +4

    Knowledge-intensive tasks require answering many questions by reasoning about a shared corpus of artifacts (e.g., court cases, or scientific literature). As humans interact with these corpora, they naturally accumulate experiential knowledge about artifacts, enabling them to quickly identify the complete set of relevant artifacts for each new task. However, existing AI agents lack appropriate memory solutions to build or reuse such artifact-grounded experience, leading to lower answer quality and higher online cost. Existing memory solutions extract and reuse information from prior task-solving traces, but they primarily focus on user preferences, factual attributes, or abstract reasoning patterns rather than persistent artifact-specific knowledge. We introduce ExperienceIndex, a novel experience layer for AI agents that captures and reuses knowledge about artifacts based on prior reasoning traces. ExperienceIndex stores two complementary forms of experience: (i) single-artifact experiences that summarize an artifact's contribution to prior tasks and (ii) artifact-pair experiences that encode structural relationships discovered during past reasoning. Integrated as lightweight middleware, ExperienceIndex uses an experience retrieval mechanism to guide agents toward the complete set of relevant artifacts for new tasks, improving both answer quality and efficiency. Across diverse corpora and agentic solutions with different search frameworks, ExperienceIndex delivers consistent gains, raising answer quality by up to 11.0 points and reducing online dollar cost by up to 50.5%. We further demonstrate two benefits: (i) cross-task generalization, where experiences accumulated from text-to-SQL tasks transfer to factoid QA tasks over the same artifact corpus, and (ii) teacher-student learning, where experiences from a stronger model enable a weaker model to reach comparable performance.

    memoryai agentagentic
  71. arxiv:2610.10088 · cs.AI
    SkillSandbox: Skill Verification via Dynamic Scenario Synthesis
    Serin Kim, Kwangwook Seo, Dokyung Song, Jinyoung Yeo +1

    Self-evolving agents distill task-solving experience into skills for future reuse, but these skills can encode incorrect procedures or non-transferable knowledge. It is therefore critical to verify each skill's reusability: whether its guidance remains useful beyond the experience from which it was distilled. Such verification requires observing how a skill affects execution in new tasks, yet existing tasks may not expose the situations where the target skill can actually be exercised. To construct such situations, we propose SkillSandbox, a framework that dynamically synthesizes a task and its environment for each skill that are skill-relevant yet novel. A Proposer specifies the conditions to preserve and the source-specific details to vary, a Builder constructs an executable scenario, and a Verifier compares executions with and without the skill. The Verifier assesses executability, utility, and efficiency to assign a Keep or Reject verdict, determining whether the skill enters the library. Across ALFWorld and WebShop with three models, SkillSandbox consistently yields the strongest downstream performance and improved execution efficiency. Further analyses examine whether these gains reflect accurate assessment of skill reusability and identify which components of SkillSandbox contribute to them.

    self-evolving
  72. arxiv:2610.10087 · cs.RO
    Multi-Agent Coordination via Support-Preserving Distillation
    Sangmin Lee, Youngju Na, Chanmi Lee, Sung-eui Yoon

    Offline MARL increasingly relies on generative policies to model multimodal joint behavior, typically by distilling a centralized teacher into decentralized one-step actors under the CTDE. We identify a failure mode at the teacher training stage: standard flow-based teachers pair noise with replay targets independently, so nearby noise samples can be routed toward conflicting coordination modes. The teacher then produces samples between valid modes, and because the distillation loss regresses each local actor onto the conditional mean of the teacher's output given local input, this error is not absorbed but propagated to the student. To remove this teacher-side artifact, we propose Mode-Support Semi-Discrete Optimal Transport (MoSDOT), which summarizes multimodal replay into a finite mode support with prescribed capacities and uses conditional semi-discrete optimal transport to assign each noise sample to a single mode before teacher training. We additionally study a shared-randomness variant that uses a shared noise component at execution to expose the residual gap intrinsic to strict-product execution. On controlled diagnostics and offline MARL benchmarks, MoSDOT improves endpoint quality and routing consistency, particularly on datasets exhibiting multimodal joint behavior.

    multi-agentbenchmark
  73. arxiv:2610.10085 · cs.AI
    Activation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM Compression
    Alessandro Beatini, Marco Maronese, Emanuele Rodolà

    Post-training tensor-network compression replaces Transformer linear layers with Tensor Train (TT) or Tree Tensor Network (TTN) operators, but standard decompositions minimize weight-space Frobenius error rather than functional error under the layer's activation distribution. We propose Activation-aware Weight Tensorization (AWT), a training-free calibration wrapper that preconditions each weight matrix with a diagonal activation-derived scale before an unchanged TT/TTN solver and deploys the result with only an input-side elementwise rescaling. Across Llama 3.1 8B, Ministral 8B, and Qwen2.5 7B, AWT consistently improves vanilla TT/TTN tensorization at 2-6 times compression: under single-operator replacement, AWT closes 12-35% of the WikiText perplexity gap to the dense baseline across the three model families and 2-6 times compression settings; while under multi-operator Llama suffix replacement it closes 27-60% across attention-group and all-seven-matrix settings. The gains also transfer to downstream HellaSwag and ARC-Challenge evaluations. We further show that diagonal preconditioning is a robustness-modularity tradeoff rather than a diagonal-covariance assumption: a dense full-covariance oracle wins its own weighted objective in 80/81 cases, yet diagonal AWT gives better held-out functional fidelity in 53/81 cases. Together, these results position AWT as a principled, modular preconditioner for improving functional fidelity in fixed TT/TTN compression pipelines without modifying the decomposition solver.

    post-training
  74. arxiv:2610.10079 · cs.RO
    RealtimeWAM: How Fast Can I Run My World Action Model?
    Huanan Liu, Ye Li, Kangye Ji, Xiaoyu Chen +7

    World Action Models (WAMs) combine visual dynamics modeling with action generation, but their high inference latency limits responsive robot control. Recent efforts accelerate inference by removing explicit future-video generation at test time, as in FastWAM, an approach that requires a specially tailored architectural design. More general caching strategies exploit feature redundancy, but redundancy alone does not capture the changing computational demands of closed-loop control. To address these challenges, we present RealtimeWAM, a general, training-free framework that coordinates parallel execution with adaptive computation for low-latency inference across diverse WAM architectures. We exploit layerwise dependencies to overlap observation processing with prediction. However, concurrent branches still compete for GPU resources, limiting the benefit of parallel execution. We therefore adapt computation throughout the pipeline through selective reuse, caching observation features in visually stable regions and reusing Transformer residuals while reserving additional refinement for small predicted adjustments. We evaluate RealtimeWAM on FastWAM and OpenWAM across RoboTwin, LIBERO, and LIBERO-Plus. On an RTX 4090, measured mean inference latencies are 24.09 and 63.09 ms, corresponding to average speedups of 8.90$\times$ and 10.67$\times$. Average success rates are 82.75% and 87.41%, respectively, within 0.02 and 0.53 percentage points of native inference. Across five real-world tasks, RealtimeWAM improves average success rates over native inference by 17.2 and 37.2 percentage points on FastWAM and OpenWAM, respectively.

    liberorobotwin
  75. arxiv:2610.10071 · cs.AI
    HGP:An on-device personalized agent memory via hybrid graph storage
    Ran Zhou, Xueming Han, Jiaheng Liu, Yuyao Zhang +3

    LLM-based agents face challenges in personalized interactive tasks due to heterogeneous, multi-typed, and implicitly constrained long-term traces. Existing memory mechanisms struggle with accurate routing and retrieval, especially on-device where personalization is critical. Most methods use single-vector representations, blurring type distinctions and relational structure. We propose HGP, a hybrid graph memory framework. HGP employs a lightweight self-enhancement classifier for personalized memory routing and constructs episodic, semantic, and procedural memories as graphs. It also extracts working memory as a state trajectory to capture current state and implicit constraints, ensuring reliable decision-making. The classifier reduces large-model calls, enabling on-device deployment, while graph storage enables accurate retrieval and incremental user profile refinement. Experiments on two benchmarks show that on PAL-Set solution selection, HGP achieves an S-score of 35.58, nearly 7 points above the strongest baseline. Code and data are at https://github.com/Ouan6/HGP-.git.

    memoryagent memoryagentbenchmark
  76. arxiv:2610.10066 · cs.AI
    From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMs
    Zijian Chen, Zhengyu Chen, Bohan Liang, Lirong Deng +6

    Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in both visual understanding and code generation. However, existing benchmarks typically evaluate these two modalities in isolation, lacking a dedicated assessment of their unification, i.e., how a model can perceive complex visual structures and synthesize them into precise, executable code. Moreover, current visual code generation benchmarks often rely on simplified layouts within single programming environments, falling short of evaluating true unified multimodal reasoning. To bridge this gap, we propose FigCodeBench, a comprehensive framework for rigorously evaluating MLLMs on figure reproduction, integrating multimodal comprehension and generation. We first design a systematic dataset construction pipeline, resulting in a total of 6,194 instances that cover 7 functional categories and 4 types of programming languages. We further categorize figure reproduction into three tiers with visual and code complexity modeling, specifically targeting complex structural reasoning, varying aspect ratios, and dense geometric constraints. We introduce a multi-dimensional evaluation protocol, encompassing visual fidelity and syntactic isomorphism, that aligns highly with the Mean Machine Opinion Score (MMOS) and human preferences. Based on our framework, we conducted extensive experiments on 24 widely used proprietary and open-source MLLMs (e.g., Gemini 3.1 Pro, GPT-5.4, and Kimi-K2.5), where we observed a universal, non-linear performance cliff across different programming languages and difficulty scenarios for all models, and gained several insights, such as the significant metric decline in rigid declarative languages.

    benchmarkevaluation protocol
  77. arxiv:2610.10062 · cs.AI
    Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model Agents
    Obada Kraishan

    Tool-using agents are usually scored on whether they finish a task while the tools work. Deployments are less forgiving: services time out, endpoints disappear, parameter names change, and results come back well formed but wrong. Prior work has shown that language models over-trust tool outputs that fail silently; we ask how that over-trust plays out across the stages of failure handling in multi-turn agents. Wrapping the executable environments of an established function-calling benchmark in a fault-injection layer, we inject one of four typed faults at a controlled point in the trajectory and record whether the agent notices, changes plan, recovers the task, or repeats itself. Six models from three families, half of them reasoning variants, ran 1,920 trials over 24 multi-step tasks. Agents treat a failure as a problem in 91.3% of trials when the tool returns an explicit error, but in 58.8% of trials when it returns a plausible wrong value, against a 26.8% rate of reporting problems when nothing was wrong. Reasoning models are not better placed: paired against instruct siblings, they notice less (-9.3 points, p < .001) and change plan more (+10.4 points, p < .001), and recovery is unchanged (p = .512). Because agents are stochastic, two fault-free runs of the same task end in the same state only 63.3% of the time; against that baseline, only a missing tool clearly lowers recovery (39.9%), while timeouts, schema drift, and corruption stay within run-to-run variation. After a fault, agents return to the same tool three or more times in a row in up to 22.2% of trials, though strictly identical repeats are rare. A prompt line asking the agent to check each result did not move detection. Agents respond to the error channel rather than to the content of what a tool returns, so failures that stay inside the expected format pass through.

    agentbenchmark
  78. arxiv:2610.10058 · cs.CL
    Cache the Encoder Within:Compact, Reusable Memory across LLM Queries
    Hanzuo Liu, Chunyu Liu, Chaofan Lin, Alex Lamb +1

    Repeated queries over shared documents incur redundant encoding, while caching model states introduces persistent storage costs. Building on CoMem's intermediate-state interface, EncBank treats a pretrained LLM's lower layers as a reusable document encoder and compactly stores their outputs for an adapted upper-layer reader. A self-distilled suffix adapter is shared across storage precisions within each backbone, without quantization-specific retraining. Across five benchmark suites on three Qwen backbones spanning different sizes and full-attention and hybrid architectures, 4-bit storage keeps each reported benchmark aggregate within one score point of native-precision EncBank. In a fixed Qwen3-8B workload, it retains 28.1% of the native-precision persistent GPU store. Separate native-precision controls yield a 1.40x selected-pack prefill speedup over same-evidence, same-adapter text replay, at a 3.12-point RULER accuracy cost. A native-precision Qwen3.8-27B configuration also passes 70 of 89 Terminal-Bench 2.1 tasks. EncBank thus combines reusable computation with compact memory, while task fidelity and end-to-end benefits remain dependent on the workload, preparation costs, and reuse frequency.

    memorybenchmark
  79. arxiv:2610.10049 · cs.CL
    The Long Road to the Same Answer: Cognitive Bias Under Escalating Reasoning Budgets in Large Language Models
    Obada Kraishan

    Reasoning models allocate extra computation at inference time and present their answers as the product of deliberate thought. If this deliberation works the way dual-process accounts of human cognition suggest, longer thinking should weaken the classic decision biases that fast, intuitive judgment produces. Using 30 vignettes covering six biases (anchoring, framing, loss aversion, escalation of commitment, availability, confirmation) from an established benchmark, we run a dose-response study across four model families, pairing each reasoning model with a matched non-reasoning sibling and requesting thinking ceilings of 0, 1,024, 4,096, and 8,192 tokens, for 12,350 API calls. Because a requested ceiling is not the same as realized deliberation, we use the reasoning tokens each call consumed as the dose. First, reasoning models are not less biased than their siblings; the point estimate leans the other way in every family, but the item-level pooled contrast is not reliable (Delta = +0.031, t(29) = 1.45, p = .157). Second, bias magnitude does not reliably fall as realized deliberation grows: no slope is significantly negative, and where anything moves it is the signed score drifting further from the human direction. Third, anchoring is the only bias in the human direction (d = 1.89). Four of the other five lean the opposite way in all seven models; with five items per bias, that reversal is reliable for framing and directional for escalation of commitment, confirmation, and loss aversion, while availability is absent. A one-line instruction to restate the anchor before answering lowered anchoring on all five anchoring items, which no amount of additional thinking did, although the effect does not reach significance (p = .057). The results argue against treating test-time reasoning as a rationality guarantee and for auditing deployed models bias by bias.

    benchmark
  80. arxiv:2610.10044 · cs.MA
    CANDO: Cooperative Agentic Network for Layout Design Optimization
    Athanasios Masouris, Zheng Jing, Benjamin Sam Chandler, Hadi Jamali-Rad

    Layout generation for real-world facilities is a challenging problem, requiring reasoning over irregular site boundaries, heterogeneous orientations, access-aware placements, and motion-planning feasibility. Yet, most existing layout benchmarks in the generative AI space target simpler placements over rectangular domains and rely on distributional metrics such as FID and IoU that reward conformity to dataset priors, thus discounting design innovation. Motivated by these gaps, we introduce ALPS-Bench, a benchmark of $1,000$ professionally annotated real-world facility layouts paired with an instance-specific scoring protocol grounded in a structured design manual. As a strong baseline for ALPS-Bench, we propose CANDO, a training-free multi-agent framework in which specialized agents iteratively refine layouts through a verification-grounded loop, concentrating reasoning on strategic spatial decisions. We demonstrate that CANDO surpasses state-of-the-art trained and LLM-based baselines on the widely adopted PubLayNet, RICO, and PKU-PosterLayout benchmarks, establishing cooperative agentic design as a broadly effective recipe for constraint-aware layout synthesis.

    multi-agentagenticagent frameworkbenchmark
  81. arxiv:2610.10042 · cs.AI
    Learning to Accumulate Knowledge with Mutual Information
    Yuyang Zhao, Lizi Liao, Leyang Shen, Xiaoyan Zhao +3

    Large language model (LLM) agents can improve their performance by reusing knowledge distilled from past interactions. However, curating new experiences into a knowledge bank that becomes more useful as it grows remains challenging. Effective knowledge accumulation should limit redundant overlap among entries and ensure that new knowledge contributes beyond what the bank already provides. Yet training a curator with Group Relative Policy Optimization (GRPO) on standalone task success can reinforce general guidance even when it duplicates existing knowledge. Therefore, we propose Knowledge Weaver, a reinforcement learning framework that trains a language model to curate reusable knowledge from agent trajectories. We couple feedback inspired by token-wise mutual information (MI) with marginal success rewards to guide knowledge accumulation. Together, these signals encourage the curator to preserve distinct information from experience and produce entries that improve task success when added to existing knowledge. Standalone success rewards also favor entries that are useful on their own. On ALFWorld and WebShop, Knowledge Weaver achieves mean success rates of 54.0\% and 42.0\% with k=10 retrieved entries, exceeding GRPO by 16.9 and 18.7 percentage points, respectively. Its knowledge banks also outperform the evaluated prompt-based and established banks, including human-written banks, in overall ALFWorld success rate and WebShop score with the executor frozen. Our codebase is available at https://github.com/LaoKuiZe/Knowledge-Weaver.

    agent
  82. arxiv:2610.10037 · physics.app-ph
    Matching of signal, noise and hardware timescales for filtering and forecasting of correlated noise signals
    Joshua Donald, Alex Gabbitas, Arthur G. T. Coveney, Sergey Savel'ev +1

    Physical reservoir computing exploits the nonlinear dynamics of physical systems to process time-dependent data with greater energy efficiency than conventional machine learning approaches. However, physical reservoirs have fixed intrinsic response timescales, whereas real-world signals combine deterministic and stochastic components across multiple timescales. Here we show, using a nanoporous niobium oxide reservoir, synthetic noisy signals and cryptocurrency-price volatility, that the relationship among noise correlation time, reservoir memory and forecast horizon determines whether correlated noise is filtered or predicted. Noise varying faster than the relevant reservoir memory and forecast horizon is averaged by the reservoir, whereas the temporal structure of slower-varying noise is sufficient for algorithmic forecasting. We introduce the reservoir memory horizon and forecasting regime index to distinguish these operating regimes. These contributions demonstrate that timescale matching can guide the encoding of input time series and development of physical reservoir architectures that filter, analyse and predict stochastic signal components across distinct temporal scales.

    memory
  83. arxiv:2610.10020 · cs.RO
    Tactile Reconstruction of Contact Task Frames and Forces for Hybrid Force/Motion Control
    Antonio Rapuano, Simone Orelli, Barbara Bazzana, Antonio Franchi +1

    Hybrid force/motion control requires knowledge of the interaction force and of a task frame defining the force- and motion-controlled directions. These quantities are usually obtained from force/torque sensing or model-based residuals, often assuming also a nominal environment model. This work addresses the online estimation of the contact force and a possibly time-varying task frame using only soft optical tactile sensing, under the assumption of locally planar contact with a negligible contact moment. The proposed method maps a single image of the deformed elastomer of a soft optical tactile sensor to observable contact variables: indentation depth, two surface-to-sensor tilt angles, and 3D contact force, each with a per-sample uncertainty estimate. The mapping is learned through a self-labeling acquisition procedure, in which a manipulator imposes controlled contacts while an auxiliary Force/Torque sensor is used offline to provide ground-truth labels. The tactile measurement is then fused with robot proprioceptive data in an Extended Kalman Filter, producing a continuously updated estimate of the contact task frame and of the interaction force. Control experiments with a DigiTac sensor mounted on a UR10 manipulator demonstrate closed-loop contact force regulation against a flat rigid board in linear and angular motion by a human operator, with touch as the only exteroceptive feedback.

    tactilemanipulator
  84. arxiv:2610.10000 · cs.AI
    Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded Rewards
    Qirun Zeng, Manhin Poon, Xiangxiang Dai, Qixin Zhang +1

    Adversarial attacks on bandits aim to mislead a learner toward a target arm while keeping the attack cost small. Existing attacks typically achieve this by suppressing non-target arms. In practice, however, manipulation such as fake reviews often directly promotes the target item. We study this gap through bounded offline attacks on warm-start bandits, where an attacker can inject only valid action-reward pairs into the warm-start history before deployment. We show that target promotion is not merely a heuristic: when the target arm lies near the lower reward boundary, any order-optimal-cost attack against UCB that makes it selected in nearly all online rounds must allocate a nonvanishing fraction of its cost to the target arm. We then design an attack that achieves the optimal sublinear cost and characterize its allocation between target promotion and non-target suppression. We further extend the attack to Thompson Sampling, $ε$-greedy, and a broader class of bandit algorithms. Experiments on real-world and synthetic data validate the effectiveness of our attacks.

    manipulation
  85. arxiv:2610.09993 · cs.AI
    Efficient Patch-Based Anomaly Detection Fused with Diffusion Driven Generative Modeling for Semiconductor Wafer Bin Map Open Set Anomaly Detection
    Limon Bin Hossain, Md Sadib Rahman Ananta

    Spatial defect signatures on wafer bin maps (WBMs) trace yield loss to specific process faults, yet supervised classifiers recognize only the defect types seen during training, and one-class detectors built on a single mechanism tend to capture either local structural deviations or global distributional violations, but rarely both. This work proposes a hybrid one-class framework that couples a patch-based student-teacher detector (EfficientAD) with a denoising diffusion probabilistic model (DDPM) used for partial-diffusion reconstruction, and fuses their percentile-calibrated scores through a fixed convex combination. Trained on only 700 normal wafers from the WM-38K mixed-type dataset and evaluated on 18,658 held-out wafers, the fused detector reached an AUROC of 0.9985 and reduced misclassifications from 852 (DDPM) and 1,412 (EfficientAD) to 618, with all pairwise differences significant at p < 0.001. Beyond aggregate accuracy, the analysis shows that the gain arises from weakly overlapping errors between the two modules, yet fixed-weight fusion recovers only 40-70% of the correction available to an oracle selector. Under the benchmark's inverted class balance, average precision and F1 saturate, while the Matthews correlation coefficient and negative predictive value expose unreliable normal predictions. Pixel-level maps further show that strong image-level separability does not imply spatial localization, and the diffusion module succeeds as a local density prior rather than through global geometric reasoning. These findings motivate sample-adaptive fusion and imbalance-aware evaluation of hybrid wafer anomaly detectors.

    benchmark
  86. arxiv:2610.09977 · cs.RO
    Decoding Neural Population Dynamics through Robotic Analog
    Wenhui Chen, Jiyue Tao, Yitao Cheng, Yutong Shi +3

    Animal evidence shows that precise voluntary movements arise from rotational neural population dynamics in motor cortex, but their physical effects remain unknown. We developed a robotic analog of biological motor systems with artificial muscles, multimodal sensors, and a neural network controller trained via reinforcement learning. The robotic analog exhibited accurate movements, robustness to damage, and neural population dynamics akin to animals. This task-driven, embodied model illuminates the causal link between neural population dynamics and motor outcomes. We discovered that neural rotations generate oscillatory maneuvers orthogonal to the reaching direction, optimizing trajectory adjustments, which is confirmed by primate neural data. The model also revealed counterintuitive neural energy principles under sensor and motor redundancies, and striking Eureka moments during motor learning, bridging biological and artificial systems. These findings provide new perspectives on how neural dynamics contribute to accurate and flexible movement, inspiring future intelligent robots with animal-like mobility.

    embodied
  87. arxiv:2610.09973 · cs.AI
    From Expected Harmfulness to Likelihood: A Probabilistic Reformulation of Jailbreaking LLM Agents
    Juanyang Xu, Zheng Wang, Xingyu Zhao, Siddartha Khastgir +1

    When the harmfulness of an LLM agent's output can be quantified, a natural jailbreaking objective is to maximize expected harmfulness over admissible input modifications. An alternative approach constructs or selects harmful target outputs and modifies the input to increase their likelihood. We establish a precise connection between these two approaches through a probabilistic reformulation. Specifically, we show that the gradient of the logarithm of expected harmfulness with respect to the input equals the expected input gradient of the model's log-likelihood under a harmfulness reweighted output distribution. This identity provides a unified interpretation of expected harmfulness and target likelihood optimization. Building on this connection, we propose OPUR, a sampling distribution designed to generate highly harmful target outputs and use the resulting samples to guide likelihood-based input optimization. Experiments demonstrate the effectiveness of the resulting method in jailbreaking LLM agents.

    llm agent
  88. arxiv:2610.09967 · cs.RO
    Borrowed Eyes: Markerless Nano-UAV Flight with an Active Quadruped Observer
    Alejandro Lorite Mora, Dimitrios Arapis, Andrés Faíña

    Nano unmanned aerial vehicles (nano-UAVs) can navigate confined spaces that larger robots cannot, but their payload capacity severely limits the sensors and compute available for self-localization in global navigation satellite system (GNSS)-denied environments. We present a vision-based system that localizes a nano-UAV from a quadruped robot with an arm-mounted camera. The quadruped tracks the drone, estimates its position in its own coordinate system using segmentation masks and depth, and transmits that position over a real-time radio link. To ensure continuous tracking, we developed a perception-aware nonlinear Model Predictive Controller (NMPC) that dynamically adjusts the quadruped's body and arm to maximize the drone's visibility, treating observation reliability as a primary control objective. Relying solely on this external estimate, the nano-UAV executed predefined trajectories from takeoff to landing with a median 3D localization error of 59 mm. The system demonstrates robustness against short visual occlusions by smoothly transitioning to onboard inertial flight when line-of-sight is temporarily lost. Ultimately, this framework allows a quadruped to offload the localization burden of a nano-UAV, enabling inspection of complex spaces that neither robot could navigate alone.

    quadruped
  89. arxiv:2610.09964 · cs.AI
    Successive Training Stages and Large Language Model Persuasion: Effects of Misalignment, Supervised Fine-Tuning, and Preference Optimization
    Antony Dalmiere, Pascal Marchand, Guillaume Auriol, Vincent Nicomette

    Large language models (LLMs) can be tuned to influence human attitudes, yet the respective contributions of successive post-training stages remain un-clear. This study examines how three successive training stages affect LLM persuasiveness: (1) misalignment through supervised fine-tuning (SFT) on conspiracy data, (2) additional persuasive SFT on argumentative data, and (3) Identity Preference Optimization (IPO), a preference-optimization method. A total of 835 participants recruited on Prolific were randomly assigned to five between-subject conditions (neutral text, conspiracy-trained model, persuasion-trained model, preference-optimized model, and GPT-4) and were exposed to texts on 10 divisive political issues, personalized from their individual profiles in all model conditions. Attitude change was measured as the difference between pre- and post-exposure positions on continuous Likert scales and analyzed with an analysis of covariance (ANCOVA). A significant condition x baseline-attitude interaction, F (4, 825) = 5.33, p < .001, indicated that training effects depended on participants' initial attitudes. Persuasive SFT produced greater attitude change than conspiracy training alone, d = 0.30, whereas IPO provided no additional benefit, d = 0.03, and GPT-4 did not differ from neutral text, d = --0.01. These results show that targeted supervised training on persuasive data increases LLM persuasiveness, whereas preference optimization yields no significant gains beyond it.

    post-training
  90. arxiv:2610.09944 · cs.AI
    AgentTime: Can Agents Estimate and Control Their Own Runtime?
    Michael Ofengenden, Maksym Andriushchenko

    An essential control of AI agents is their ability to manage runtime. This ability requires a sense of time-awareness, to predict and estimate wall-clock time and to control their own actions. Prior work has focused on time-awareness, but duration-following and control in native agent harnesses remain unexplored. We present AgentTime, a benchmark for testing whether agents can work for a requested duration, predict their runtime, and estimate elapsed time afterward. It comprises 222 tasks from 18 sources spanning coding, computer use, agentic work, and automated research. Duration-following experiments append a single instruction specifying how long to work, with requests ranging from about a minute to multiple days. Accuracy on these instructions varies substantially: Fable 5.1 in Claude Code deviates from requested runtimes by a typical factor of 2.9$\times$, compared with only 1.2$\times$ for GPT-6 Astra in Codex. However, matching the requested runtime does not, by itself, establish continued work on the task. Among 158 reviewed Astra runs with classifiable transcripts, 14 explicitly slept after appearing to finish. In forecasting experiments, predictions tend to overestimate natural runtimes. In retrospective experiments, removing temporal information more than doubles deviation for Sol and Astra and nearly doubles it for Fable. An agent's ability to complete a task does not guarantee that it can control its own time or work for the whole requested duration. For agents to run reliably, safely, and autonomously over long horizons, we require the evaluation of both.

    agentai agentagenticbenchmark
  91. arxiv:2610.09943 · cs.RO
    Many Ways to Succeed: Diversity-Driven RL Fine-Tuning for VLA Generalization
    Haoru Li, Jinmei Liu, Zhiyong Wang, Xiaoming Li +4

    Reinforcement learning (RL) fine-tuning improves vision-language-action (VLA) policies through closed-loop experience, yet generalization beyond the fine-tuning distribution remains limited. Our analysis reveals a selective reshaping of exploration: RL contracts behavior globally, yet diversifies successful trajectories, elicits success with fewer rollouts, and covers more of the latent task-valid solution space than supervised fine-tuning. Broader successful-mode coverage may provide alternative strategies under distribution shifts. Inspired by this, we introduce DRIVE (Diversity-driven RL fIne-tuning for VLA gEneralization), which turns successful-behavior diversity into an explicit RL objective. DRIVE groups rollouts under matched task conditions, compares their trajectories with temporal alignment, and derives a success-conditioned intrinsic reward from relative behavioral diversity. This design encourages broader coverage of feasible solutions without rewarding diverse failures or superficial timing differences. Across LIBERO-Plus, ManiSkill3, and RoboTwin 2.0, DRIVE improves the average out-of-domain (OOD) performance over vanilla RL fine-tuning by 5.3 points on $π_0$ and 2.0 points on $π_{0.5}$. On a dual-arm AgileX PiPER-X platform, DRIVE further increases average OOD success from 64.1% to 73.3% (+9.2 points), demonstrating gains that persist under physical deployment.

    vision-language-actionvlaliberorobotwin
  92. arxiv:2610.09940 · cs.RO
    Juno: Taming Predictive Latents for Vision-Language-Action Models
    Yuchen Zhu, Chenyi Xu, Yulin Zhang, Gang Xu +1

    Joint-embedding predictive architectures (JEPAs) predict masked or future observations in representation space, offering a natural source of predictive latents for vision-language-action (VLA) models. Yet making these latents useful across pretraining, policy learning, and deployment requires addressing three failures: mismatch with embodiment-specific control, interference with action learning, and teacher miscalibration under distribution shifts. We introduce Juno, a unified framework built around one action-conditioned JEPA that serves as a control-aligned representation backbone, a predictive teacher, and an adaptable dynamics model. During pretraining, we train it on embodiment-matched trajectories and use a dynamic CLS loss to transfer motion-weighted patch dynamics to a compact global state. During policy learning, we fuse current-frame JEPA patches into VLA perception and use a decoupled reasoning branch with separate transformation parameters to distill future latent states for action generation. During deployment, we adapt the world model on all observed transitions, including failed rollouts, freeze the adapted teacher, and re-align the policy on verified executions using LoRA adapters and a trainable action head, without expert corrections or task rewards. On SimplerEnv, Juno raises average success from $60.9\%$ to $68.5\%$ over Qwen3GR00T, the strongest baseline, and test-time adaptation further reaches $72.7\%$; on a real robot, it retains $70\%$--$75\%$ success under background, height, and object shifts where the base policy collapses to $0\%$.

    vision-language-actionvlaaction headgr00tworld modelaction-conditioned
  93. arxiv:2610.09937 · cs.AI
    Where Can a Decision Model Diagnose HVAC Faults? Reasoning Demand, Physical Representation, and Robustness Under Shift
    Wooyoung Jung

    Artificial intelligence supports building operations in several forms, each with its own barrier. Expert rules must be tuned for every system, supervised models need labeled data that buildings rarely record, and language models return free text that requires human-in-the-loop checking, since their stated confidence is unreliable. A newer kind of pretrained model, here called a decision model, returns a probability for every allowed answer, so one model could serve many decisions without training. This study answers three open questions for fault diagnosis in heating, ventilation, and air-conditioning systems: which decisions such a model can make, what input it needs, and whether its probabilities hold when conditions change. On 128 fault days from four public datasets of real equipment, faults are graded by the reasoning their diagnosis demands, with data given raw, as physical features, or with Brick topology. The decision model Jev, open language models, and a supervised model face nine tests that change season, control configuration, or building. Given physical features, Jev and the larger open model diagnosed faults whose evidence one feature carries, but not faults that need operating context. Under shift they kept their accuracy and calibration, while the supervised model lost 0.33 macro-F1 yet led or tied within a building. Their probabilities still needed correction, and detection was weak. The study maps which faults a decision model can diagnose and from what input, and supports a division of work in which code computes the physics and the model ranks candidate faults for an operator.

    human-in-the-loop
  94. arxiv:2610.09927 · cs.AI
    KGATE : a Knowledge Graph Embedding Training Environment
    Benjamin Loire, Galadriel Brière, Célia Brahimi, Antoine Toffano +1

    Knowledge graph embedding (KGE) models encode the entities and relations of a knowledge graph into a low-dimensional latent space, enabling tasks such as classification or link prediction. Most KGE models follow an autoencoder architecture, in which an encoder projects the knowledge graph into the latent space and a decoder reconstruct it. Combining both encoder and decoder components is increasingly needed, yet existing libraries rarely support complete autoencoders, are often unmaintained, rely on undocumented default hyperparameters, and produce results that cannot be compared across libraries. Here we present KGATE (Knowledge Graph Autoencoder Training Environment), a modular Python library built on PyTorch Geometric and TorchKGE. KGATE lets users assemble initializers, encoders, decoders, losses, negative samplers, and evaluation metrics as building blocks, or plug in their own block. KGATE includes a preprocessing procedure that controls data leakage, a builtin training pipeline, and reproducibility by design. Benchmarks against six existing KGE libraries show that KGATE training time is comparable with the fastest libraries while offering a broader set of features.

    knowledge graphbenchmark
  95. arxiv:2610.09921 · physics.optics
    Beyond Spectroscopic Strong Coupling: Operational Benchmarks for Cavity-to-Magnon Quantum Transfer
    Huang Xinyi, Zhang Xiang, Zhao Dongxing

    Normal-mode splitting reveals coherent cavity--magnon hybridization but does not certify finite-time quantum-state transfer. We describe quantum transfer in a passive, linear cavity--magnon system coupled to thermal reservoirs as a thermal-loss channel specified by its coherent transmissivity $η$ and output-referred thermal population $ν$. For single-rail qubits, we calculate the phase-corrected average fidelity and compare it with the deterministic measure-and-prepare benchmark of $2/3$. A Bell pair shared by the cavity and an isolated reference retains reference--magnon entanglement if and only if $η>ν$. An input squeezed vacuum of strength $r$ yields sub-vacuum magnon fluctuations if and only if $ν<η(1-e^{-2r})/2$. When the initial magnon and both reservoirs have the same occupation, an analytically determined peak-transmissivity time optimizes all three tasks. These task-dependent benchmarks show that a conventional linewidth-based strong-coupling criterion does not guarantee quantum-transfer performance. Conversely, entanglement or squeezing can survive below that spectroscopic reference when the added noise is sufficiently low. These benchmarks provide quantitative targets for transfer timing and thermal-noise control in intracavity-to-magnon quantum interfaces.

    benchmark
  96. arxiv:2610.09920 · cs.CL
    Inverting Multi-Vector Visual Document Indices
    Zhuchenyang Liu, Yao Zhang, Yu Xiao

    Prevailing multi-vector visual document retrievers store each page as about a thousand patch vectors, often in vector databases run by a third party. Since no one can read a page from its vectors, this index is easily treated as less sensitive than the page. However, because the index keeps one vector per patch in raster order, and each vector is computed by a vision-language model pre-trained to read documents, we hypothesize that whoever runs or breaches the store can reproduce a page from its index alone. We frame inversion as conditional document image generation and infer from the vectors what the attack needs: the encoder, the page shape and, for shuffled vectors, their order. On the ViDoRe v3 benchmark, pages inverted from raw indices recover 47% of the words and 45% of the sensitive tokens. Used as queries against the stored indices, they rank their source page first 98.4% of the time. We test two cheap protections, token pooling and shuffling, which both cut word recall to about 8%. A model that restores the order of a shuffled index raises the share of source pages ranked first from 3.8% to 93.5%, while inverting a pooled index remains open. To test generalisation, we apply the same attack unchanged to another multi-vector retriever: its inverted pages still rank their source page first 70.2% of the time, though its word recall stays below a nearest-neighbour baseline. Multi-vector visual document retrievers are therefore vulnerable to inversion through their stored index, which should be protected like the documents it encodes.

    benchmark
  97. arxiv:2610.09906 · cs.AI
    Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails Proxy
    Georgios Koutidis, Nikolaos Kekatos, Tom Nianios, Alexios Lekidis

    Security Operations Centers (SOCs) for information technology and operational technology share one incident-response problem: a flood of correlated alerts and too few analysts. Large Language Models (LLMs) are increasingly proposed as reasoning engines that triage alerts and, in autonomous deployments, issue commands that block IPs, kill processes, or quarantine files on production hosts. This coupling introduces a new risk: a single adversarial alert can become a remote code path through the LLM's reasoning, leading it to recommend an action the SOC then executes. We present a constrained-action architecture with two coordinated layers: (i) a SIEM/XDR control plane that grounds remediation in correlated host events and confines the LLM's output to a closed intent vocabulary whose templated commands are executed by thin endpoint agents, backstopped by an argument validator; and (ii) a NeMo-Guardrails proxy that wraps the SOC-analyst LLM with input- and output-rail policies, evaluated out-of-the-box against a SOC-specific adversarial corpus we release. The stock proxy lifts injection recall from 25.0% to 94.5% at a 0.1% false-positive rate, and a live red-team exercise confirms that the closed intent vocabulary and argument validator contain the observed LLM failure modes before any command crosses the trust boundary. As an architectural fit (not yet a measured operational-technology deployment), the constrained-action property suits critical-infrastructure settings where a wrong remediation has physical, not merely operational, consequences. The loop is best run human-in-the-loop or delayed: the measured rail latency keeps inline control out of scope.

    human-in-the-loop
  98. arxiv:2610.09896 · cs.AI
    NL2Hull: A Natural Language-Driven Constrained Ship Design Decision Framework
    Wenhua Huo, Fenglei Han, Wangyuan Zhao, Jialin Wu +1

    Ship-form design combines smooth geometric representation, local shape editing, and constraints on the resulting hull. We present the Natural-Language-to-Hull Framework (NL2Hull Framework), which formulates ship-form editing as a typed discrete decision problem and connects language decisions to numerical geometry. Its Constrained Free-Form Deformation Engine (CFFD Engine) represents hull waterlines with non-uniform rational B-splines (NURBS), applies free-form deformation (FFD) to their control points, reconstructs the hull, and checks geometric constraints. We construct the Ship Design Decision Dataset (SDD Dataset) with 134,558 cleaned records and evaluate compared models on its subset Ship Design Decision Benchmark (SDDBench), containing 5,000 records and 43,496 typed questions. We propose Chip, a constrained ship-design decision model for processing natural-language requests. Chip reaches 95.90\% question accuracy and 99.32\% FFD exact match, with a negative log-likelihood of 0.0951, an expected calibration error of 0.0032, and a Brier score of 0.0551. The NL2Hull Framework provides a reproducible interface for evaluating language-based ship-form decisions while identifying the geometry and continuous-control components that require further development. Our code and dataset is available at https://github.com/wenhuahuo/NL2Hull.

    benchmark
  99. arxiv:2610.09891 · cs.RO
    A Scoping Review and Experimental Study on Reinforcement Learning from Human Feedback for Human-Robot Collaboration
    Alexandra Coroiu, Andrea Vogt, Viktor Werbilo, Andreas Poppele +2

    Human-Robot Collaboration (HRC) can facilitate mass customisation in Industry 4.0, with Reinforcement Learning from Human Feedback (RLHF) representing a promising approach for developing safe AI-based robots. Practical challenges remain regarding safety during AI development, human feedback quality, and bidirectional human-robot adaptation. We conducted a scoping review of RLHF in HRC systems, mapping methods that address these challenges. Following PRISMA guidelines, we screened 199 records and included 20 peer-reviewed publications (2020-2025) spanning multiple HRC domains. To our knowledge, this is the first review focused on the bidirectional, closed-loop design of RLHF. Our review found multiple feedback modalities enabling data collection in various feedback formats. Collected data can be integrated at different stages of AI training, resulting in a multi-step development process. Pilot experiments are commonly used to evaluate HRC systems based on both human and robot metrics. To empirically test a key gap identified in the review, we conducted a between-subjects VR experiment comparing system- and user-initiated feedback on robot proxemic behaviour for safe navigation. Using Bayesian models, we analysed the relation between the collected feedback and safety metrics: psychological safety (post-experiment questionnaire) and physical safety (inverse time-to-collision). Results show that user-initiated feedback captures perceived safety better than system-initiated feedback, indicating that feedback timing directly affects feedback quality. Our review and experiment findings show that RLHF relies on appropriate feedback methods to ensure AI safety in HRC, and future RLHF research should prioritise realistic HRC experiments evaluating the effects of feedback collection methods on relevant human and robot metrics.

    rlhf
  100. arxiv:2610.09890 · cs.AI
    Outperformance Inverse Optimization: Learning Objective Functions that Outperform Agent Decisions
    Akira Kitaoka

    Inverse optimization estimates the weights of an objective function that explain observed decisions as optimal solutions, and is used in a variety of fields. For mixed-integer linear programs (MILPs), existing methods aim to reproduce the observations as optimal solutions, and thus learn compromise weights when the observations are suboptimal. We propose outperformance inverse optimization, which instead seeks weights that induce, at each state, an optimal solution outperforming the observed action in every component. We give a loss function that can be evaluated with forward-problem oracles alone and is thus applicable to MILPs, together with gradient-based and DC optimization algorithms for minimizing it. For weights inducing a unique outperforming optimal solution at all observations, we prove that the probability of failing to induce such a solution at a new state (the generalization error) is bounded by a quantity inversely proportional to the number of observations, and that this bound is tight in the number of observations up to logarithmic factors. In experiments on synthetic and real data, the proposed methods improve the prediction of solutions outperforming the actions over existing methods.

    agent
  101. arxiv:2610.09872 · cs.AI
    LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets
    Jun Zhao, Leiming Fu, Yanbo Wen, Yiding Wang +8

    Evaluating agents by outcomes alone can obscure the capabilities that produce them. This problem is especially pronounced in evolving environments, where outcomes reflect a closed-loop interaction between agent behavior and changing external conditions. We introduce LiveMACEBench, a process-aware benchmark that uses live financial markets as a naturally evolving testbed for persistent LLM agents. Five frontier LLMs operate along continuous trajectories under matched Tool Use, Persistent Memory, Rule Following, and Multi-Agent Collaboration configurations. We evaluate them through both realized outcomes and mechanism-specific diagnostics derived from complete decision traces. Across 30 days of live evaluation, we find a pronounced outcome-capability gap: realized returns often diverge from capability-specific measurements, and similar outcomes can arise from markedly different patterns of mechanism use. Trace-level diagnostics further expose distinct bottlenecks across capabilities, demonstrating that mechanism access, effective mechanism use, and downstream performance are not interchangeable measures of agent capability. LiveMACEBench makes this distinction measurable, turning live markets from a performance leaderboard into a diagnostic environment for agent capability

    persistent memoryagentllm agentmulti-agenttool usebenchmark
  102. arxiv:2610.09870 · cs.AI
    Deadline-Aware Multi-Agent Reinforcement Learning for TSN-Based Vehicular Edge Networks
    Bernardo A. C. Pereira, Marcos Carvalho, Fatih Temiz, Shavbo Salehi +4

    Vehicular edge computing (VEC) enables latency-sensitive applications by bringing computing and networking resources closer to vehicles. However, existing approaches often overlook network contention among co-located services with heterogeneous and dynamic latency requirements. While time-sensitive networking (TSN) provides bounded-latency communication, conventional and reinforcement learning-based schedulers struggle to adapt to highly dynamic vehicular environments and inter-queue dependencies. To address these limitations, we propose a multi-agent reinforcement learning (MARL) approach for queue-level scheduling in TSN-enabled VEC. Each TSN queue is assigned an autonomous agent that jointly learns the queue service order and time-slot duration to minimize deadline misses under speed-dependent latency requirements. We employ multi-agent proximal policy optimization (MAPPO) to enable coordinated yet autonomous scheduling decisions. Evaluation against single-agent, multi-agent, and non-learning-based baselines shows that MAPPO provides robust performance across different traffic profiles. Compared with centralized single-agent methods, it reduces service latency by up to 66.2% and improves reliability by up to 271.8%. Furthermore, unlike urgency-based heuristics, MAPPO ensures balanced scheduling while achieving lower inference times compared to other MARL methods.

    agentautonomous agentmulti-agent
  103. arxiv:2610.09858 · cs.AI
    Training Advisors for LLM Agents from Task Outcomes
    Sergei Polezhaev, Barys Liskavets, Ori Press, Alexander Golubev

    Large language model agents tackle multi-step tasks by interleaving reasoning and tool calls with observations from the environment. Prior work has shown that natural-language feedback can help these agents revise their decisions during task execution. We introduce Caddie, a method for training critics to provide natural-language analysis and advice as agents work through a task. Unlike approaches that rely on step-level labels or reference critiques, Caddie learns from whether the agent ultimately succeeds after receiving the critic's feedback. We optimize the critic through reinforcement learning while keeping the base model frozen. Trained on multi-hop question answering with a single base model, our Qwen3-4B critic improves success rates across four base models of different scales and architectures, including three not used during critic training. On the MuSiQue benchmark, the trained critic improves Qwen3-4B's success rate by more than 25 percentage points, surpassing the performance of Kimi K3 without a critic. The same critic also yields gains on out-of-domain interactive benchmarks, including $τ^3$ and DeepDive, with no additional training. Our results show that agents can decide when to seek help from a critic at inference time and that outcome-based critic training can produce guidance that transfers across base models and task domains.

    agentllm agentbenchmark
  104. arxiv:2610.09857 · cs.RO
    Towards Accurate End-Effector Localization for UMI-Style Robotic Manipulation Teaching
    Junjie Zhang, Deteng Zhang, Zhisong Xu, Bo Sun +3

    Robot demonstration learning requires accurate and temporally complete end-effector localization during close-range manipulation and camera occlusion. Existing SLAM benchmarks emphasize navigation motions, whereas manipulation datasets prioritize policy learning over localization evaluation. We introduce MILD, a Manipulation-Interface Localization Dataset with real-world and simulation sequences. The real-world subset provides 86 sensor sequences from Insta360 X5 and Insight9 across 15 repeated tabletop tasks, calibration assets, and a per-execution robot end-effector reference trajectory. The simulation subset, MILD-Sim, extends task coverage in Isaac Sim for controlled manipulation-replay studies. Benchmarking visual-inertial and fiducial-aided systems on instrumented real-world recordings reveals large differences in both TCP-relative trajectory error and temporal coverage, even under the same nominal task. To support marker-augmented teaching workspaces without a pre-surveyed fiducial map, we present AprilVINS, which combines fisheye visual-inertial estimation with sequence-local AprilTag geometry and separates prior admission from guarded export of the jointly optimized state. On Insta360 AprilTag4 recordings, AprilVINS(full) under a unified protocol with sequence-specific profiles reaches millimeter-level SE(3)-aligned TCP-relative APE RMSE with high time completion and lower reported error than the tested routes under their respective protocols, whereas fisheye VIO without tag factors remains at centimeter scale. Ablations separate accuracy from exportability, and a MILD-Sim replay study provides task-specific tolerance references for interpreting those error magnitudes. Together, MILD and AprilVINS provide a diagnostic benchmarking framework for UMI-style demonstration collection. Code, datasets, and evaluation manifests will be released upon acceptance.

    manipulationbenchmark
  105. arxiv:2610.09856 · cs.AI
    Self-Evolve With a Reference:Anchored Training of Tool-Integrated Agents
    Wenjie Liao, Liangjie Zhao, Zehong Cao

    Self-evolving tool-integrated agents learn from tasks and feedback generated within their own training loop. A Curriculum Agent generates tasks, while an Executor Agent learns from self-consistency signals through reinforcement learning. However, relying solely on the current Executor for feedback has two limitations: group-relative advantages vanish under full consensus, while uncertainty-based curriculum rewards favor disagreement without showing whether the generated tasks support further learning. These limitations motivate an additional reference beyond the current Executor. We propose \textit{AnchorLoop}, which introduces a frozen copy of the previous iteration's Executor as a historical reference and reuses it on both sides of the training loop. For the Executor, the anchor provides a cross-reference advantage that evaluates current outputs against both current and historical majority answers. For the Curriculum, it provides an agreement-based reference based on differences in sampled majority agreement. Since the Executor and anchor have identical parameters during Curriculum training, this comparison serves as a proxy for task selection rather than evidence of inter-version improvement or correctness. Across 13 reasoning benchmarks, AnchorLoop improves over Agent0 by 2.5\% on mathematical reasoning and 2.8\% on general reasoning tasks. It also maintains higher effective-advantage variance and continues improving in later iterations as the unanchored baseline shows diminishing gains. These results demonstrate the benefit of introducing a lightweight historical reference into self-evolving tool-integrated agents without external task or answer supervision.

    agentself-evolvingbenchmark
  106. arxiv:2610.09832 · cs.AI
    SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
    Yuyao Ge, Yiwei Wang, Yuchen He, Baolong Bi +4

    Memory-augmented reinforcement learning strengthens LLM agents' ability to solve complex long-horizon tasks. Skills are one such form of memory, pairing instructions with an applicability condition over task types. However, retaining every skill indiscriminately as the policy improves lets obsolete or harmful entries accumulate and mislead the agent. We propose SkillForge, an agentic RL method that compiles and evolves the skill library through a fitness-driven skill lifecycle of trial, active, stable, and retired states, so that the skills and the model co-evolve throughout training. A pre-RL evaluation phase first uses the base model's own rollouts to pre-retire low-fitness skills, yielding a filtered library that then seeds supervised fine-tuning. Reinforcement learning takes over from this checkpoint, and at each iteration selective retirement, stabilization, and LLM-guided mutation continue to forge the skill library alongside policy optimization. Across multiple interactive agent benchmarks, SkillForge achieves the highest aggregate success rate, delivering up to 7.8% relative improvement over the strongest baseline while keeping the skill library compact throughout training. We introduce SkillFurnace, a dataset of 5k+ annotated records bundling retirement-filtered SFT trajectories, evolved skill libraries with fitness annotations, and retirement events with human-annotated failure categories to support research on skill quality and lifecycle management.

    agentllm agentagenticagent benchmarkbenchmark
  107. arxiv:2610.09823 · cs.AI
    UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image Generation
    Deyuan Liu, Yihao Hu, Jingxuan Zhang, Xingying Li +12

    Dense visual text requires image generators to reproduce long strings across multiple regions with correct placement and legibility. As short-string rendering improves, evaluation must test sustained performance across more demanding scenes. We introduce UltraText Bench, a bilingual benchmark for prompt-only generation of dense visual text. It contains 432 prompts spanning 24 real-world scene categories and three difficulty levels, split equally between English and Chinese. Each human-reviewed prompt supplies exact strings for four to twelve text regions, paired with structured references for their content, placement, and visual attributes. We use the Q-Judger vision-language model to assess each image against the complete reference, reporting text fidelity, text clarity, spatial quality, and scene quality. Across 24 model configurations, these dimensions reveal different strengths: Z-Image-Turbo gains 3.81 clarity points over Z-Image-Base while losing 14.76 fidelity points under the reported settings. Performance also varies with workload; Qwen-Image-2512's English composite falls from 86.50 at L1 to 42.86 at L3. Ten participants took part in human evaluation of the automatic scores. Repository: https://github.com/LINs-lab/UltraText_Bench.

    benchmark
  108. arxiv:2610.09802 · cs.AI
    DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation Models
    Adam Pardyl, Siddhartha Gairola, Sukrut Rao, Adam Wróbel +3

    Concept-based vision models represent images through an intermediate layer of human-inspectable concepts, so what a model relies on can be traced to those concepts. However, those models are often limited to fixed categories or depend on language to define their concepts. We introduce DisParQ (Discrete Parts with Quantized attributes), a method that learns spatially grounded, discrete concept representations from a powerful frozen vision-only self-supervised backbone. It requires no class labels and no language supervision. Each image patch is assigned to exactly one concept from a learnable prototype dictionary, and only a sparse subset of concepts may activate per image. To capture how each concept varies across images (e.g., the type of a "wheel"), we learn continuous residuals alongside the concepts and then quantize them into discrete attributes. A spatial decoder reconstructs the backbone's representation from the concepts and attributes alone, so successful reconstruction means that the discrete representation preserves the backbone's information. We evaluate DisParQ across seven datasets, from general recognition (ImageNet, PartImageNet, Places) to fine-grained benchmarks (CUB, Cars, Dogs, Flowers). We show that DisParQ closely matches its frozen DINOv2 teacher on ImageNet linear probing (83.2% top-1), achieves higher concept consistency than language-aligned models, remains competitive on fine-grained recognition, and enables cross-category part-based retrieval.

    benchmark
  109. arxiv:2610.09795 · cs.AI
    MIRROR: From Imitation to Internalization in LLM Personalization
    Huayi Lai, Jicheng Yang, Min Yi, Chong Meng

    The demand for personalized LLMs is shifting from style imitation toward content quality. We investigate whether self-distillation can bridge this gap in existing fine-tuning paradigm. To address this limitation, we introduce MIRROR(Meta- personalization by Internalizing Reference-Revealed On-policy Reflections), a novel self-distillation framework that shifts LLM personalization from imitation toward preference internalization. First, we replace reference-token imitation with reference-revealed on-policy self-distillation, aligning the model's next-token distributions along its own generation trajectories with those of its reference-conditioned self, thereby internalizing user preferences rather than reproducing reference wording.Second, we introduce MIRROR-F, a focal plug-in that augments on-policy distributional alignment with selective supervision over informative reference tokens, thereby strengthening content generation while preserving user-specific expression. Across three personalized generation benchmarks, two model scales, and complementary reference-based and LLM-based evaluations, MIRROR and MIRROR-F achieve leading overall personalization performance and superior text quality, while exhibiting less catastrophic forgetting than SFT-based baselines on three unseen personalized generation tasks. The gains are consistent across model scales and application scenarios, translating to improved performance in LLM personalization tasks.

    benchmark
  110. arxiv:2610.09788 · cs.CL
    Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving Compression
    Mingqing Yuan, Xiaobo Liang, Junwei Yang, Ziwei Chen +4

    Reward modeling often requires jointly representing and reasoning over multiple evaluation criteria, yet verbalizing this process token by token can incur substantial inference cost. Recent work on latent reasoning suggests that continuous states may support this computation more compactly. We introduce LatentGRM, a latent evaluation framework built on semantic chunking, compression, and reconstruction. By using the structure of rubric-guided evaluations to guide compression, LatentGRM learns compact continuous trajectories that support autonomous pairwise judgments without generating textual assessments. A separate interpreter reconstructs evaluation text from these trajectories, providing an offline view of the information retained under compression. Under matched training data and backbones, LatentGRM achieves competitive aggregate preference accuracy relative to explicit Supervised Fine-Tuning (SFT) judges at both 4B and 8B scales. Across four benchmark domains, LatentGRM-8B compresses evaluation trajectories by 8.9--9.2x and reduces total judge inference time by 6.1--7.0x at vote@5. Controlled rubric interventions show that criterion-dependent preference information is carried through the latent sequence. Together, these results demonstrate that continuous latent evaluation can substantially reduce inference cost while preserving competitive judgment quality.

    benchmarkevaluation framework
  111. arxiv:2610.09785 · cs.RO
    UltraWorld: Learning Interactive Ultrasound World Models from Untracked Clinical Videos with Acoustic Sampling Map
    Keke Yang, Erqi Wang, Sainan Guan, Hongliang Ren

    World models can enable autonomous ultrasound scanning by predicting the outcomes of probe motions from local observations. Learning this action--observation relationship typically relies on synchronized video--pose pairs, which are costly to collect at scale and largely unavailable in routine clinical recordings. Reliable action following further requires modeling ultrasound's cross-sectional sampling geometry. We present UltraWorld, a self-distillation recipe that transfers priors from clinical ultrasound videos into interactive world models without real action annotations. Starting from clinical videos, we adapt a video foundation model into an ultrasound generator conditioned on reference images and anatomical masks. Anatomical masks sampled along programmable trajectories through 3D anatomy provide spatial guidance for synthesizing action--video pairs. We then use these synthetic pairs to self-distill the generator into a world model that predicts future observations from local observations and actions, without requiring anatomical masks or other 3D assets at inference time. To further improve action following, we introduce the Acoustic Sampling Map (AsMap), which represents probe poses and imaging settings as pixel-wise 3D sampling positions, beam directions, and depths. Experiments demonstrate improved prediction fidelity and action following. Across nine simulated closed-loop local planning episodes, UltraWorld reduces the mean final distance to the goal and orientation error by 29\% and 38\%, respectively, compared with visual servoing. Project Page: https://ultraworld-project.github.io/.

    world model
  112. arxiv:2610.09781 · cs.RO
    End-to-End Autonomous Generation of Human Assembly Plans
    Faustin Arion von Arx, Millicent Schlafly, Mark D. Fuge

    Turning a CAD design into an assembly plan is still largely done by hand, requiring engineers to reason about geometric feasibility, tool access, stability, and the ergonomics of human assembly. In this work, we encode long-established design for assembly (DfA) principles into a contained, end-to-end approach for generating assembly plans. Our approach takes only a mesh assembly and produces either a step-by-step assembly manual or a structured failure report, requiring no joint metadata, fastener annotations, or additional information. Four major components of a manufacturing plan are addressed autonomously: an assembly tool list, the assembly sequence and subassemblies, an assembly manual, and design feedback for improving assemblability. For determining the sequence plan, we systematically disassemble the object in a physics simulator and apply a cost function that encodes DfA principles. Manual generation, tool labelling, and assembly feedback rely primarily on multimodal large language models. Compared with a baseline that always removes the outermost part first from Tian et al., DfA-aware sequence planning reduces simulated assembly time, measured with a robot-arm assembly-time proxy, by 35% on 136 assemblies of 5 to 30 parts. The correct tool is selected for 88.6% of assembly steps. A vision-language model judge compares the generated manuals against ablated variants, identifying which page elements carry the information a reader needs. The presented approach and open-source code are available for use by engineers or AI agents looking to rapidly accelerate the creation of manufacturing plans for a given product design.

    ai agent
  113. arxiv:2610.09777 · cs.RO
    On-Demand Robotic Assembly via Differentiable Geometric Part Repair
    Millicent Schlafly, Fabio Schaub, Diogo Costa Pais, Luca Lelli +4

    Transitioning from a digital design to a robotic assembly process currently requires months of expert manual tuning to reconcile part geometries with robotic constraints. This paper presents an end-to-end, autonomous pipeline for the design and physical construction of bespoke wooden assemblies. A generative AI agent translates user prompts into initial 3D geometries, balancing the visual fidelity of the design with select physical constraints. The assemblability of the design is further improved by a gradient-based repair stage that backpropagates through a graph attention network surrogate to adjust component geometries. In addition to correcting for disjointed and overlapping components, we demonstrate hardware-specific corrections, differentiably optimizing the geometry of components to enable robot screwdriving for 86.7% of 60 novel natural language inputs, significantly outperforming prior work by a factor of ten. For ten of the structures, we physically demonstrate assemblability with two UR5e robots. This work marks a meaningful step toward on-demand robotic manufacturing, enabling the rapid production of customized, low-volume goods.

    agentai agent
  114. arxiv:2610.09772 · cs.AI
    Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context Pollution
    Masaaki Nakatsu, Reno Wang

    Small language-model agents on edge devices must hold a persona and reason correctly at once, inside one context window that fills with conversational history and persona instructions. We study what happens to the logical part of such an agent when that history is long, misleading and persona-heavy (persona-logic interference), and present a Decoupling Architecture (AO-DA) that separates logical inference ("What") from persona expression ("How") into two inference paths on one INT4 base model with hot-swappable LoRA adapters. The logic path receives only the core turn and emits a verifiable structured state (Micro-State); the persona path renders it in character with the full history. In same-base-model ablations on an Apple M2 laptop (Llama-3.1-8B-Instruct and Gemma-3-4B-it, 4-bit; 480 runs over 4 pollution levels x 3 arms x 2 tasks x 2 personas x 5 seeds) we find: (i) the decoupled logic path is structurally invariant to pollution: its prompt stays at 180 (Llama) or 167 (Gemma) tokens while the mixed single-pass prompt grows from 242 to 1,203, and its outputs are byte-identical across levels (40/40); (ii) the mixed single pass degrades monotonically (composite logic score 0.669 to 0.150 on Llama, 0.487 to 0.150 on Gemma), mostly by failing to emit the required structured output (80-95% of runs on Llama, 100% on Gemma at the two highest levels); (iii) with the same pollution fed into the decoupled logic path, the dedicated-adapter, dedicated-format path is still more robust than the single pass on the 8B model (failure 0-20% vs 80-95%; paired $Δ$ +0.30 to +0.50, Cliff's $δ$ 0.50-0.85, Holm-adjusted $p \le 0.03$) but not on the 4B model, where both collapse. Separation costs one extra decode on a topic's first turn (28.2 s vs 18.2 s on Llama) and buys persona hot-swapping in 1.7 ms without re-running the logic path. Code, rubric, fixtures, adapters and logs are released.

    agentllm agent
  115. arxiv:2610.09769 · cs.AI
    From Expert-Guided Proof Search to Automated Open-Problem Solving
    Adrián Zámečník, Matěj Kripner, Martin Koutecký, Martin Balko +4

    Large language models are increasingly contributing to mathematical research, where progress often depends on efficient proof search, incremental improvements and careful verification. We describe Bolzano, a multi-agent open-source system that uses parallel prover agents with a verifier agent and maintains a human-readable research state. Initial manual use on expert-selected problems yielded 8 results whose proofs were checked by domain experts. Motivated by these case studies, we ran Bolzano without problem-specific human guidance on about 3,800 open problems extracted from four sets of papers, solving about 200 open problems. One experiment used papers accepted to STOC 2026, a top conference in theoretical computer science. There, we answered four questions raised in the papers, as confirmed by their authors.

    agentmulti-agent
  116. arxiv:2610.09764 · cs.RO
    AeroEval: Staged Program and Execution Validation for AI-Generated Drone Missions
    Kautuk Astu, Naina Rabha, Yogesh Simmhan

    Large Language Models (LLMs) can generate drone programs from natural-language mission descriptions, but syntactically valid programs may still violate user intent, environmental constraints, and mission-level behavior. This problem is pronounced in cyber-physical applications, where correctness depends on the interaction among generated code, mobile sensing, environmental geometry, event-driven analytics, and physical execution. Existing drone code-generation systems primarily use prompt guardrails or simulator outcomes and provide limited failure localization. We present AeroEval, an agent-assisted middleware for staged validation of AI-generated drone missions. AeroEval combines deterministic program analysis with context-grounded LLM agents. It first validates program syntax, platform API usage, and mission intent, and then evaluates the realized behavior using execution trajectories, mission requirements, and environmental context. Each stage returns structured failure information for iterative regeneration. In our evaluation using 20 navigation tasks and five analytical mission types over AirSim and Gazebo simulators, AeroEval improves navigation success from 55% to 95%. In a stagewise ablation study, our Code and Trajectory Validators by themselves achieve mean run-level success rates of 44% and 56%, respectively, while the full AeroEval pipeline achieves 88%; the stages detect complementary failures in program structure, API usage, mission intent, obstacle avoidance, altitude, coverage, and event-driven transitions and the guided regeneration corrects for them. Across the main analytics missions, AeroEval increases aggregate run-level success from 34% for one-shot AeroGen to 88% within the regeneration budget. These results demonstrate the benefit of combining program-level and execution-grounded agentic validation for AI-generated drone applications in the evaluated environment.

    llm agentagentic
  117. arxiv:2610.09763 · cs.RO
    Beyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous Driving
    Mahmoud Selim, Cristina Cipriani, Karl Henrik Johansson

    Offline reinforcement learning enables reward-driven policy improvement from fixed datasets without requiring online exploration, making it particularly attractive in safety-critical domains. A central challenge, however, is distribution shift: policy optimization may favor actions that are weakly supported by the offline data, rendering value estimates unreliable. Existing approaches primarily control this shift in the policy's own action space. In interactive environments such as autonomous driving, this can be insufficient: a candidate ego trajectory may remain well supported under the marginal behavior distribution while being poorly supported jointly with the surrounding-agent behavior observed in the logged interaction. We refer to this degradation in interaction support as \emph{interaction distribution shift} (IDS), and introduce \emph{Interaction-Constrained Drive Policy} (ICDP), an offline reinforcement learning framework that explicitly controls interaction-level distribution shift. Starting from the joint data distribution over ego and surrounding-agent futures, we show that joint-support degradation decomposes exactly into an ego-support component and a residual interaction-support component. We recover the latter through contrastive density-ratio estimation, isolating interaction compatibility without explicit joint-density modeling, surrounding-agent prediction, or rollouts in reactive simulators or learned world models during policy optimization. Closed-loop evaluations on nuPlan, Interplan and real-world truck experiments show that ICDP suppresses high-value yet interaction-unsupported trajectory selections and improves performance in interaction-critical driving scenarios. Project webpage: https://mahmoud-selim.github.io/ICDP/

    world model
  118. arxiv:2610.09759 · cs.AI
    Unrolled Flow Models for Reasoning
    Faissal Izermine, Hanru Bai, Oscar Davis, T. Konstantin Rusch

    Flow matching enables language generation in few steps, but whether additional integration steps improve reasoning remains unclear. We prove that a flow parameterized by a two-layer Transformer can solve graph reachability, with the required number of integration steps increasing with the target's distance from the root. Yet, standard flow language models can fail to benefit from additional steps on reasoning tasks. We attribute this limitation to objectives that supervise each time point independently, without explicitly training successive steps to build on one another. To address this, we instead train through the model's own latent rollout over a randomly sampled subinterval of [0, 1], decoding only at the endpoint. On ProsQA, this raises accuracy to 97% and enables performance to improve with additional integration steps. For the longer rollouts required by reasoning tasks such as Sudoku and Maze, retracting the latent state onto a sphere stabilizes the dynamics and yields substantial gains over baselines with more than three times as many parameters. Sampling multiple rollouts further improves performance when paired with a parameter-free selection score, although reliable selection remains challenging for longer answers. Together, these results establish a theoretical basis for reasoning with flows and show how rollout training, stable latent dynamics, and rollout selection help realize this capacity in practice.

    latent dynamics
  119. arxiv:2610.09734 · cs.RO
    ΔWAM: Distilling Action Tangent Fields into World Action Models
    Ke Wu, Hanwen Huang, Bo Gu, Kaizhao Zhang +5

    World Action Models (WAM) improve robot policies by augmenting sparse action supervision with dense future prediction. However, much of the predictable future is dominated by appearance and scene persistence rather than action-dependent dynamics. We observe that several recent WAM designs, including optical flow, motion-centric representations, and latent actions, can be understood from a common perspective in which world supervision becomes more efficient as it contains a higher proportion of action-relevant variation. Based on this insight, we introduce Action Tangent Fields, which reformulate world supervision through a local Taylor expansion of how actions induce changes in future dynamics. We represent future dynamics in Residual-VAE space, where the future latent remains recoverable from the current latent and its residual, and use a strong action-conditioned world model (ACWM) to probe the local correspondence between action variations and residual-world variations. This local first-order structure is distilled into the WAM to guide its denoising supervision toward dynamics that are more tightly coupled to action, rather than merely predictable from appearance. Across LIBERO-Plus, RoboTwin, and RoboTwin2.0-Plus, our method consistently improves robustness to lighting, background, camera, layout, and other environmental perturbations. Despite using no large-scale embodied pretraining, it achieves stronger robustness under several distribution shifts than pretrained policies. We further distill multi-step VideoDiT denoising into a single step for efficient inference. Our results suggest that effective WAM supervision should remain information-rich while concentrating its predictive capacity on the directions along which actions change the future.

    embodiedliberorobotwinworld modelaction-conditioned
  120. arxiv:2610.09718 · cs.RO
    YUBI-STAG: Contact and Semantic-Rich Alignment for VLAs via Automated Video-Language Grounding
    Masatoshi Tateno, Takehiko Ohkawa, Yueh-Hua Wu, Hanlong Li +3

    Vision-Language-Action (VLA) models acquire broad manipulation capabilities via large-scale pretraining, yet eliciting them through language requires fine-grained alignment between instructions and physical interactions. Existing robot demonstrations typically provide only coarse task descriptions, omitting how actions are executed, including which gripper acts, which object is contacted, and how it is grasped and moved. We introduce YUBI-STAG, a framework for Spatio-Temporal Annotation and Grounding that automatically enriches manipulation demonstrations with interaction-rich semantics to align pretrained VLAs with fine-grained manipulation language. Combining contact-object segmentation with vision-language models, YUBI-STAG annotates object identities, attributes and states, per-gripper actions, bimanual coordination, and spatially grounded interactions. To address YUBI-STAG's reliance on localized sequences and multi-stage VLM inference, we distill it into YUBI-VLM. YUBI-VLM directly recovers action structure and annotations from raw, unsegmented video in few inference calls and operates from wrist views alone. We evaluate both frameworks on YUBI-STAG-Bench across temporal, semantic, and spatial grounding tasks. YUBI-VLM retains much of YUBI-STAG's annotation accuracy with fewer inference calls and shorter runtime while generalizing to unseen manipulations. Finally, post-training VLA policies on these annotations aligns them with fine-grained language and contact-aware structure. Bimanual experiments demonstrate improved performance and instruction following, including control over object identity, acting gripper, target location, and spatial relations absent from original labels.

    vision-language-actionvlamanipulationgrippergrasppost-training
  121. arxiv:2610.09716 · physics.optics
    Phonon-Enabled Collective Strong Coupling of Color Centers in a Plasmonic Cavity
    Bharti Garg, Prabhdeep Singh, Masoud Taleb, Nahid Talebi

    Quantum emitters in hexagonal boron nitride (hBN) are promising building blocks for solid-state quantum photonics because of their bright room-temperature emission. These emitters strongly interact with lattice vibrations, which partially underpins their excitation efficiency. Here, using complementary cathodoluminescence (CL) and photoluminescence (PL) spectroscopy, we demonstrate cavity-mediated interactions between hBN quantum emitters coupled to the same plasmonic Au void cavity at the room temperature. Cathodoluminescence measurements reveal that a vibronic transition of the 443 nm emitter hybridizes with the cavity mode, giving rise to a spectrally resolved splitting, while the neighboring 537 nm emitter remains in the weak-coupling regime despite spectral overlap. The energy split of the CL peak is at the order of 36.2 meV, whereas the PL-resolved peak is approximately 24.1 meV, which is due to the collective excitations of multiple emitters per electron excitation and their mutual interactions. Maxwell-Bloch simulations reproduce the experimental spectra and identify the observed splitting as the result of cavity-induced hybridization. Excitation-dependent PL further shows that the hybridized state can be accessed through phonon-assisted excitations below the zero-phonon transition. These results demonstrate that vibronic transitions provide an effective pathway for controlling interactions between multiple quantum emitters in hybrid plasmonic nanophotonic systems.

    quantum photonic
  122. arxiv:2610.09710 · cs.CL
    SpikingVLA: Asynchronous Spiking Vision-Language-Action Models
    Jingya Wang, Dehao Zhang, Shuai Wang, Malu Zhang +2

    ANN-to-SNN conversion offers a practical route toward energy-efficient spiking Vision-Language-Action (VLA) models by bypassing the substantial cost of training large-scale SNNs from scratch. However, existing methods often require many timesteps to maintain competitive performance, resulting in substantial inference latency for real-time VLA deployment. To address this challenge, we introduce SpikingVLA, an ANN-to-SNN conversion framework that enables accurate and low-latency spiking VLA inference. Specifically, we propose a Dendritic Integrate-and-Fire (DIF) neuron that alleviates channel-wise activation outliers through dendritic mixing and adaptive somatic firing, enabling accurate ANN-to-SNN conversion with fewer timesteps. Building on DIF neurons, we further introduce an asynchronous execution mechanism that overlaps temporal computation across VLA components, reducing synchronization overhead and latency. Extensive experiments demonstrate that SpikingVLA achieves competitive navigation performance with substantially improved inference efficiency. Compared with existing spiking VLA methods, SpikingVLA improves SR and SPL by 11.9\% and 12.6\%, respectively, while reducing first-action latency by 11.2$\times$. These results establish SpikingVLA as a practical framework for deploying pretrained VLA models with high-performance and low-latency spiking inference.

    vision-language-actionvlavla model
  123. arxiv:2610.09696 · cs.RO
    RoboPace: Contact-Aware Time-Optimal Retiming for Action-Chunk Policies
    Mimo Shirasaka, Takehiko Ohkawa, Takuya Okubo, Nicola Scianca +2

    Robot manipulation data collection has been shifting from teleoperation toward robot-free demonstrations, through interfaces such as the Universal Manipulation Interface (UMI) or directly from human hands. Vision-Language-Action (VLA) policies trained on such data inherit the demonstrator's timing. Yet human timing does not directly transfer to robots: compliant hands tolerate fast contact, whereas robots may overshoot due to actuator and tracking limitations; conversely, robots can move faster in free space. This motivates a unified approach that reconciles execution speed with contact safety. We present RoboPace, an online retiming layer that preserves the policy's geometric path while adapting its timing, respecting the target robot's kinematic and dynamic constraints. It adapts execution speed based on predicted contact, jointly accounting for contact-dependent speed limits and the robot's motion constraints. The method requires no policy retraining and operates in real time. Across three contact-rich tasks on a dual-arm robot, faster uniform execution and physical-limit-only retiming largely fail. RoboPace instead achieves higher overall success than slow uniform execution while completing four of five commands in approximately half the time, retaining the reliability of slow execution without its time cost.

    vision-language-actionmanipulationteleoperation
  124. arxiv:2610.09693 · cs.AI
    A Tale of Two Error Categories: Exploring Concealed Trade-Offs in the Errors of Automated Judges in Evaluation of Uncertainty Quantifiers
    Evgenia Ilia, Wilker Aziz

    The wide adoption of LLMs across broad NLG applications heightens the importance of providing users with the means to avert errors and hallucinations. Uncertainty quantification is poised to fill that gap; with low uncertainty (high confidence), as a proxy for correctness, allowing users to be selective (e.g., reject low-confidence, likely incorrect responses). Correlation between confidence and correctness then serves as a useful criterion for evaluation of uncertainty quantifiers (UQs). But in NLG, where diverse responses can be adequate to a prompt, obtaining reliable correctness judgements is not simple, especially without human intervention. Errors in automated judgement are hardly avoidable and known to diminish the reliability of evaluation protocols (Santilli et al., 2025; Ielanskyi et al., 2025). In a meta-analysis of published work, we show that automated judgement is the present norm. Besides, automated judgements are rarely validated against human ones, and the validation of the UQ evaluation they automate is even rarer. With experiments in question answering, using 4 LLMs, human and automated judgements and 7 popular UQs, we find that i) a judge's performance can only coarsely predict the observed impact of its errors on the reliability of UQ evaluation, and that ii) judgement errors tend to misrepresent informative UQs most. We link these observations to patterns of correlation between confidence and categories of judgement error.

    evaluation protocol
  125. arxiv:2610.09692 · cs.AI
    Few-Shot Learning for Personalised Automated Pain Assessment
    Heinke Hihn, Ibrahim Eisawy, Patrick Thiam, Hans A. Kestler +1

    Pain perception varies substantially across individuals, making it difficult for population-based classifiers to generalise across all subjects in a dataset. One way to account for subject variability is to train personalised classifiers. In this work, we evaluate Few-Shot Learning, a sub-area of Meta-Learning, as an approach to personalisation in automated pain assessment. We re-interpret the shift from population-level to subject-level evaluation as a task-domain shift, where the observed classes remain fixed but the target subject changes. We evaluate our method on the BioVid Pain Database, the SenseEmotion Database, and the PainMonit Experimental Dataset (PMED), reaching 85.75% and 35.49% accuracy on BioVid and 82.37% and 41.88% on SenseEmotion in the binary and multi-class settings under a Leave-One-Subject-Out CV protocol respectively, and 90.47% on PMED, for which only a binary benchmark exists. Using samples to implement k-shot conditioning, the accuracies can be improved to 86.25%, 40.06%, 83.43%, 44.08%, and 91.25%, respectively. To further evaluate the effects and robustness of our method, we provide additional ablation experiments and investigate the personalisation effects. Our results suggest that support-conditioned few-shot adaptation can improve average performance under inter-subject variability.

    benchmark
  126. arxiv:2610.09684 · cs.AI
    From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy Discovery
    Xinglin Wang, Zishen Liu, Tong Zheng, Shaoxiong Feng +8

    Test-time scaling (TTS) improves the reasoning capabilities of large language models by allocating additional inference computation. Existing approaches to improving TTS efficiency largely optimize accuracy against one resource dimension at a time, advancing either the accuracy--cost or accuracy--latency Pareto frontier. Yet user requirements are multidimensional: users may specify accuracy, latency, and inference-cost requirements jointly, and different requirements can favor different controllers. We formulate Personalized Test-Time Scaling as discovering executable controllers that maximize the joint satisfaction rate of user-specific requirements. To reduce the overhead of repeated policy discovery for new user profiles, we propose PersonTTS, an amortized agentic policy-discovery framework that reuses prior search experience through requirement-matched controller initialization and source-distilled procedural guidance, while retaining target-profile evaluation for every candidate. Experiments on AIME and HMMT show that PersonTTS substantially outperforms strong TTS baselines in joint requirement satisfaction on unseen user profiles and held-out problems. Under the same candidate-evaluation budget, cross-user experience reuse further improves policy quality while substantially reducing discovery-agent time and cost.

    agentic
  127. arxiv:2610.09683 · cs.AI
    System Switch: When Should a Fast Decision Model Stop and Think?
    Gian Luca Bailo

    Dual-process agents pair a fast policy with a slow deliberative model. In real-time settings the slow model usually runs continuously; in turn-based agents and robot planners it is invoked on events such as uncertainty or a detected failure. We study a fast learned actor that takes every decision and hands control to a reasoning vision-language model only when a gate opens, while the game keeps running. We use closed-loop Doom and the new open "System One" typed-decision models, served through a common llama.cpp interface. On 900 held-out questions, (i) zero-shot decision models from 0.15B to 9B parameters choose to collect items 1.6-1.8 times more often than chance among their errors, in any option order, although the order changes some models' accuracy; (ii) accuracy, calibration and sensitivity (how well confidence separates right from wrong answers) are distinct: models of similar accuracy differ widely in AUROC, and the confidence of the most sensitive one tracks which kinds of situation it fails, not which answers are wrong; (iii) offline, deferring the least confident 30% of decisions to a reasoning model gains over random deferral in proportion to the actor's AUROC (rank correlation 0.87); with actor and rate chosen on held-out games the gain is +0.13 [0.08, 0.18] with doomLaya's option order and +0.08 [0.02, 0.14] with shuffled options, and reasoning carries about half of it; (iv) in closed loop (33 games, three seeds) no variant reaches the exit. Committing to plans, the reasoner's or a fixed explore rule's, opens more doors and makes an actor that stands still play; with the rule the agent dies more often. Told that some doors need keys, the reasoner takes ordinary doors for locked ones, which the state cannot tell apart; without that knowledge it goes back to collecting. We release code, prompts, data and logs.

    agent
  128. arxiv:2610.09681 · cs.AI
    Cost-Efficient Theorem Proving via Agent Orchestration in Program Verification
    Shuangjie Yao, Nikolaus Holzer, Mark Paul Santolucito, Baishakhi Ray +2

    Program verification establishes software correctness through machine-checkable proofs constructed in theorem provers. It's a guarantee especially valuable for code generated by large language models (LLMs), which is fluent but carries no assurance of correctness. Almost all existing provers, however, pursue pass rates alone at whatever sampling or search budget it takes, and overlook the success-vs-cost frontier; yet real software often carries hundreds of interdependent proof obligations, so what matters at scale is not whether one theorem can be proved, but how many can be proved economically. We introduce CoCo-Prover, which formalizes cost-efficient program proving as metalevel decision-making under cost, grounded on two-level proof graphs: an AND/OR proof hypergraph within each declaration is joined to a lemma-dependency graph across declarations; and at each step, it answers two questions: which open goals to select, and which actions to purchase on these goals. Selection stays symbolic as a topological pass over the proof graphs. Action choice is agent orchestration via metalevel decision-making: an agentic router treats every bounded specialist invocation as a separately priced, best-effort computation, matching heterogeneous specialist agents together with configurations, under evolved routing rules as evidence accumulates. On five program verification benchmarks in Lean 4 including function-level CLEVER, VERINA, and AlgoVeri, and repository-level NTP4VC and Vero, we show that CoCo-Prover achieves a better success-vs-cost frontier than baselines including frontier coding agents and state-of-the-art LLM-based provers: it achieves the best solve rate on every benchmark and up to 100% on two benchmarks. It also reduces cost by up to 30.9% compared to the strongest baseline with the strongest LLM in our evaluation.

    agentagenticbenchmark
  129. arxiv:2610.09679 · cs.AI
    CERO: Where and When to Allocate Rollouts for RL Post-Training
    Yiming Zong, Yige Wang, Xing Hu, Jiashuo Jiang +1

    Adaptive rollout methods for group-relative reinforcement learning typically allocate a fixed per-update budget across prompts. We instead study how to coordinate a finite rollout budget over the entire training horizon. We formulate this problem using a concave surrogate utility of cumulative prompt exposure and introduce CERO, an online primal dual scheduler for prompt admission and budget pacing. In our experiments, each admitted prompt receives a fixed-size response group. CERO instead adapts which prompts are selected, how often they are revisited across rounds, and how many groups are generated in each round. A compact Fenchel representation linearizes the dependence on cumulative exposure, while projected online gradient descent updates prompt-specific supporting slopes and a shared budget price using reward-variation feedback and budget deviations. We establish pathwise guarantees for the surrogate allocation objective against fixed-rate and same-path time-varying benchmarks, with explicit terms for proxy discrepancy and rate variation. Under matched training-response budgets, CERO attains the highest avg@16 macro-average on each of three backbones across five mathematical reasoning benchmarks. Mechanistic analyses link CERO's prompt choices to within-group reward contrast, while multi-seed ablations show gains from adaptive pacing over both uniform and preset spending schedules.

    post-trainingbenchmark
  130. arxiv:2610.09671 · cs.CL
    InsClaimBench: Benchmarking Insurance Claim Adjudication Across the Decision Chain
    Linqi Zhang, Chong Qi, Yan Cheng, Wanqing Cao +3

    Recent advances in reasoning-oriented large language models (LLMs) have motivated increasing evaluation of their ability to perform professional decision tasks. Insurance claim adjudication is one such task, requiring models to connect case evidence, insurance rules, intermediate judgments, and payout calculations across a structured decision process. We introduce InsClaimBench, an end-to-end benchmark for evaluating insurance claim adjudication across the decision chain. Grounded in real claim materials and structured insurance rules, InsClaimBench contains 3,780 cases in 375 case families across auto, property, and health insurance, comprising 86,656 atomic rule judgments. It evaluates each claim from atomic rules through adjudication modules to payout decisions and amounts, with controlled factual variants testing whether required changes are correctly propagated across levels. Evaluation of six LLMs reveals a progressive loss of reliability along the decision chain. Payout-decision accuracy ranges from 74.23--80.19%, while joint decision--amount accuracy drops to 47.54--73.15%. Strong local performance also fails to ensure case-level correctness: atomic-rule accuracy reaches 95.48%, whereas rule-vector exact match peaks at only 36.90%, and the most frequent module errors are not necessarily those most associated with final-decision failure. Under factual changes, these inconsistencies further become propagation failures: module updates are less reliable than rule updates, correct local judgments can still yield incorrect payouts, and correct payouts can conceal intermediate errors. These results show that reliable claim adjudication requires consistent composition and propagation across the decision chain.

    benchmark
  131. arxiv:2610.09667 · cs.AI
    Shared and structured inputs undermine collective random choice by reasoning AI agents
    Takahiro Ezaki, Naoto Imura, Katsuhiro Nishinari

    Random selection is widely used in resource allocation and auditing, making reliable implementation essential for AI-agent systems. Behavioural tests across six reasoning models uncovered threshold and divisibility rules used in identifier-based choices. For threshold-following GPT-6 Sol and Gemini 3.8 Flash, single-agent measurements prospectively predicted correlated participation under shared identifiers and biased participation under distinct identifiers with common timestamp bits. Changing dates, formats and identifier labels revealed when these predictions held. Explicit instructions to randomize independently reduced but did not eliminate shared-input correlation. To test implications for oversight, we asked four models to select customer requests randomly for human review. GPT-6 Sol approached the target rate while selecting predictably from identifiers; the others rarely selected requests. All four closely followed supplied random draws. These findings expose collective and audit vulnerabilities that selection rates alone miss, making input-dependent bias, correlation and predictability central targets for agent evaluation.

    agentai agentagent system
  132. arxiv:2610.09665 · cs.CL
    SAPD: Step-Aligned Privileged Distillation
    Tianle Wang, Jiayu Liu, Ruizhi Zhao, Ning Miao

    On-policy post-training can improve large language models by learning from their own trajectories, but requires costly rollout generation. We ask whether fixed demonstrations can support competitive off-policy learning through better supervision. Our premise is that their usefulness depends not only on the training trajectories, but also on whether supervision provides informative preferences among continuations and connects this guidance to the reasoning decision being learned. We introduce Step-Aligned Privileged Distillation (SAPD), a rollout-free self-distillation method that turns demonstrations into step-aligned distributional supervision. Its key insight is to use the known progression of a reference solution to associate each reasoning transition with targeted privileged guidance, rather than treating the solution as undifferentiated context. On mathematical reasoning benchmarks, SAPD outperforms supervised fine-tuning and label smoothing on average while remaining competitive with on-policy reinforcement learning and self-distillation. Analyses support both the value of context-dependent distributional guidance and the benefit of aligning privileged information with the current step. SAPD also largely preserves out-of-domain coding performance and achieves approximately 2x training-loop speedups over the on-policy baselines. These findings suggest that carefully constructed supervision can make fully off-policy post-training a competitive and computationally efficient alternative. Our code is available at https://github.com/Miaow-Lab/SAPD.

    post-trainingbenchmark
  133. arxiv:2610.09661 · cs.CL
    Alice: A Large-Scale German Benchmark for Rubric-Based Multi-Dimensional Automatic Short Answer Scoring
    Zhifan Sun, Sebastian Gombert, Jannik Lossjew, Tobias Wyrwich +5

    Automatic Short Answer Scoring (ASAS) is central to NLP for Education. However, openly available benchmarks remain scarce, and existing datasets largely address how well students answer a question directly rather than how well they master underlying concepts (knowledge elements) such as thermal energy or epistemic activities (skills) such as reasoning or claim. To address this gap, we introduce Alice, a large-scale, rubric-based German ASAS dataset that is pedagogically aligned and comprises three subtasks: (i) learning performance (Alice-LP), (ii) knowledge elements (Alice-KE), and (iii) skills (Alice-SK). We further formulate rubric-based ASAS as a rubric-retrieval task and benchmark the dataset with a range of language models, from encoder-only models to lightweight LLMs. We also benchmark the dataset with zero-shot prompting via LLMs and a standard classification baseline. The experiments show that LLMs, in particular, struggle to score knowledge elements and skills in the zero-shot setting. They also indicate that rubric text is often useful, especially for Alice-KE and Alice-SK, while on Alice-LP gains over sample-solution-focused inputs are more modest and vary by model and input format.

    benchmark
  134. arxiv:2610.09660 · cs.CL
    Rubric Spans are Label Representations: Joint LLM Encoding for Short Answer Scoring
    Zhifan Sun, Sebastian Gombert, Fabian Zehner, Leon Camus +2

    Automatic Short Answer Scoring (ASAS) requires models that can score student responses against question-specific criteria while remaining efficient and transferable across rubric sets. We propose RUSPAN, a rubric-conditioned ASAS framework that treats rubric descriptions as semantic label representations. RUSPAN serialises the question context, student answer, and all candidate rubric levels into a single sequence, then scores the levels listwise from the rubric-span and whole-sequence representations produced in a single LM pass. We further introduce RUSPAN-RIM, in which a Rubric-Independent Mask prevents rubric spans from attending to one another, making rubric representations depend only on the answer and question context and preventing overfitting to rubric patterns during training for zero-shot transfer. On six ASAS benchmarks spanning English, German, and Portuguese, RUSPAN improves mono-benchmark scoring over discriminative and generative baselines, while RIM with position reindexing delivers consistent and substantial gains on PT-ASAG, the held-out benchmark with the strongest combined language and rubric-structure shift.

    benchmark
  135. arxiv:2610.09652 · cs.RO
    MeshSIPP: Efficient Lattice Planning in Dynamic Environment
    Marat Agranovskiy, Konstantin Yakovlev

    Autonomous navigation in dynamic environments requires computing spatiotemporal trajectories that satisfy non-holonomic motion constraints. When the trajectories of the moving obstacles are predictable or known, a promising approach is to rely on the combination of state lattices constructed from precomputed feasible motion primitives and Safe Interval Path Planning -- a search-based algorithm with strong theoretical guarantees. While this approach yields feasible paths, the rich primitive sets needed for smooth navigation induce a large branching factor, which becomes costly when coupled with time-dependent obstacle intervals. To this end, we present MeshSIPP, an efficient planner that removes the computational bottleneck by exploiting the fact that many primitives sweep the same regions and can therefore be validated together. MeshSIPP propagates primitives as spatial bundles, screens them with lightweight bounding-interval checks, and defers the expensive exact departure-time search until a primitive reaches its terminal state. A time-aware pruning rule additionally discards redundant space-time branches early in the search. We prove that the resulting search is complete and optimal. Extensive experiments over more than 6,000 benchmark instances and real-time ROS~2 simulations show that MeshSIPP achieves up to a 3$\times$ speedup over state-of-the-art spatiotemporal planners.

    benchmark
  136. arxiv:2610.09647 · cs.CL
    When Rank Rises as LLMs Degrade
    Zhaohui Geoffrey Wang

    Post-training adapts language models in non-stationary environments. Practitioners monitor representation health with RankMe and related spectral statistics, often assuming that rank falls when representations degrade. We show that this assumption is unsafe for LLM post-training. In a controlled study of Qwen3-0.6B with four degradation modes and three seeds, data duplication worsens held-out loss by 75% relative to healthy while increasing both original and centred RankMe; the latter changes by 13.5 pooled standard deviations. Covariance effective rank rises to nearly twice its healthy value. This failure is spectral dispersion rather than collapse, so a one-sided monitor rates the worst checkpoint as the healthiest. By contrast, a learning-rate misconfiguration lowers centred RankMe and k95, while uncentred RankMe is inconsistent across seeds. Direction is therefore a property of the regime-statistic pair and cannot be fixed by recalibration alone. We also distinguish two often-conflated statistics: RankMe normalises singular values, whereas covariance effective rank normalises eigenvalues. On raw intermediate-layer states in the pretrained model, massive activations pin the latter near 1 out of dimension d while RankMe retains usable range. We then test a two-sided, multichannel sequential monitor with separate calibration and test data. In a pre-registered shared-prefix, leave-one-seed-out evaluation, it detects all three damage regimes in every fold 10 to 60 steps after the fork and separates dispersion from downward-rank damage by firing direction. However, it never precedes held-out probe loss, and calibration with two seeds produces false alarms on the held-out healthy seed. Spectral monitoring can diagnose failure regimes, but it does not warn earlier than held-out loss, and validity claims require held-out healthy data.

    post-training
  137. arxiv:2610.09644 · cs.AI
    Automatically Building and Updating a Knowledge Graph of MLIP Models
    Alexis Beer, Liudmyla Klochko, Mathieu d'Aquin

    Complementing the many efforts in providing semantic representations of concepts, notions, and entities in materials science, we report and illustrate a process by which we can automatically build a knowledge graph of the fast evolving field of machine learning applied to the prediction of material properties, focusing on MLIP (Machine Learning Interatomic Potential). This LLM-based process relies on multiple steps, from information extraction in documents and articles to a validation loop using SHACL constraints to detect and correct errors. It is carried out on a model-by-model basis, focusing on the consistency of representation, therefore enabling an iterative construction where the addition of new models is facilitated. We illustrate the process by showing a few interesting aspects that can be queried from a knowledge graph built from the models listed in the Matbench Discovery leaderboard.

    knowledge graphleaderboard
  138. arxiv:2610.09643 · cs.AI
    CircuitATLAS: Agentic reasoning over a systems neuroscience knowledge graph for target discovery in circuitopathies
    Gabriel Ocana-Santero, Marko Tvrdic

    Drug discovery for neurological disease has traditionally centered on the molecules altered by disease. But the molecules that cause pathology are not necessarily the best points from which to reverse it. Here, we ask which otherwise unaltered molecular control points can be engaged to restore pathological neural circuits toward functional states. We present CircuitATLAS, a provenance-grounded systems-neuroscience knowledge graph and agentic framework for target discovery in circuitopathies. It structures literature-derived relationships across diseases, phenotypes, electrophysiology, circuits, brain regions, cell types and molecular effectors, while deliberately excluding direct disease-gene and disease-protein edges to reduce shortcut reasoning. The graph contains 3.83 million nodes and 7.66 million edges, including 5.31 million LLM-extracted relations, and incorporates structured datasets such as the Human Cell Atlas and new multimodal in vivo measurements. We then introduce an agentic workflow that reasons from measurable disease phenotypes through their circuit and cellular substrates to molecular interventions, therapeutic feasibility and clinical constraints. Finally, we introduce a human-governed in vivo lab-in-the-loop linking hypothesis generation to experimental iteration. Within this framework an agent nominated ATP1A3, the neuronal alpha3 Na+/K+-ATPase, as a control point on cortical excitability; interneuron-restricted expression of ATP1A3 abolished the beta- and gamma-band response to a focal 4-aminopyridine challenge in vivo, and the validated target was then carried into a structure-guided small-molecule campaign terminating in a defined assay to resolve the direction of modulation. CircuitATLAS thus provides a framework for discovering therapeutics based not only on what is molecularly disrupted in disease, but on what can be controlled to restore circuit function.

    knowledge graphagentagentic
  139. arxiv:2610.09639 · cs.CL
    On-Policy Distillation Teaches New Skills but Not New Knowledge
    Yixuan Tang, Yi Yang

    On-policy distillation (OPD) strengthens language-model reasoning, yet whether students acquire new factual knowledge or compositional skill for multi-step reasoning remains unknown. We separate these capabilities using a controlled synthetic framework that measures the student's initial capabilities and independently controls the teacher's additional facts, compositional skill, or both. Across four models from three families, reverse-KL OPD reliably transfers compositional skill across unseen reasoning structures, but transfers minimal factual knowledge. Decoupling the distillation recipe reveals the source of this asymmetry: replacing reverse KL with forward KL restores factual transfer, whereas student rollouts specifically improve the execution of multi-step reasoning. Experiments on recent factual QA and competition mathematics show a similar asymmetry under reverse-KL OPD, yielding notable reasoning gains without factual memory expansion. Together, these results demonstrate that on-policy distillation does not expand a model's parametric knowledge, but instead teaches it to organize and compose the knowledge it already possesses.

    memory
  140. arxiv:2610.09633 · cs.AI
    Coding-Agent Benchmarks Should Match Their Users' Task Flows
    Igor Slinko, Yaroslav Golubev, Sergey Titov

    The evaluation of coding agents generally strives to be as realistic as possible. In our study, we collect 4,782 agent sessions of real software engineers in JetBrains IDEs, which we call Production Sessions. Since our subject is interactive agents, we study the sessions with at least three user messages (33% of the sample). These long sessions differ from issue-derived benchmark tasks in two ways: (i) user requests span a far wider mix of task types - questions about the project's code, planning, review, refactoring, execution - and (ii) users switch between types throughout a session. Long-session samples from three public interaction corpora exhibit markedly different Task Flows (the distributions of session lengths, task types, and type-to-type transitions), so no single interaction distribution is universally realistic: benchmarks should name a target use case and calibrate to measurements from it. We present SWE-TaskFlow, an approach for transforming any issue-derived benchmark: it preserves the verified tasks and tests while steering the interaction toward a target Task Flow through prompt splitting and verifiable repository QA, with a TaskFlow Alignment Score (TFAS) for selecting among generated trajectories. In a pilot on 700 SWE-Bench Pro tasks, solving the task sequentially in several steps approximately doubles agent cost without a stable change in resolve rate: the interaction protocol itself is an important dimension of evaluation.

    agentagent benchmarkbenchmark
  141. arxiv:2610.09624 · cs.AI
    How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by Suppression
    Xijie Gong, Tingxu Han, Jiahao Zhang, Wei Song +4

    Tool calling, invoking external tools on demand, is central to agentic LLMs, yet the mechanism that decides whether a model calls a tool or responds directly remains poorly understood. Agentic prompts are long and heavily scaffolded, combining role instructions, tool schemas, format templates, and the user's request across hundreds of tokens, creating a noisy, highly entangled context in which no single controllable variable for mechanistic analysis is obvious. To obtain such a variable, we propose a method that converts complex agentic prompts into minimal contrastive pairs in which a single request verb determines the tool-call decision: replacing an execution-verb (e.g., \textit{write}) with an analysis-verb (e.g., \textit{discuss}) reliably flips the decision, suggesting it is mediated by a compact internal state. We construct 500 such paired prompts across Python, Java, and C++ (300 for mechanistic analysis, 200 held out for evaluation). We trace the decision to a vector, $μ_Δ$, that is both causally necessary and sufficient and generalizes beyond the discovery prompts to native multi-turn $τ^2$-Bench trajectories and verb-free requests. Behavioral ablations show that the scaffold establishes a tool-call prior; Transcoder decomposition then reveals that analysis verbs suppress this prior through features signaling that tool use is unnecessary, whereas execution verbs largely leave it intact. Downstream scaffold-reading attention heads and MLP features read out the resulting state, and the same mechanism recurs across seven models from the Qwen, Mistral, and Granite families. Our code is available at https://github.com/XijieGo/MI4ToolCalling.

    agentictool usetool calling
  142. arxiv:2610.09607 · cs.AI
    Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning
    HyeonSeok Lim, SeungWoo Song, Inho Won, Hoyun Song +2

    Skeleton-based reasoning prompting is a promising training-free approach for structuring LLM reasoning, but prior work largely assumes an English-centric setting. We propose the Language-Aware Skeleton Exploration Framework (LASEF) to study skeleton-language choice in multilingual mathematical reasoning. Across math benchmarks, model scales, and languages, we show that English skeletons yield a small positive tendency on average, most visible for smaller models and low-resource languages. However, few language-level gains remain significant after correction, and English is not universally optimal. Combining greedy decoding, multi-rollout evaluation, translation ablation, and cross-benchmark validation, we further find three patterns of skeleton-language effects: directionally consistent, evaluation- and benchmark-dependent, and asymmetric negative. These effects cannot be fully explained by generation quality alone. Overall, skeleton language is a context-dependent design variable that requires multi-level exploration. All resources are released at https://github.com/lhsstn/LASEF.

    benchmark
  143. arxiv:2610.09590 · cs.RO
    Learning Situation-Conditioned Thinking Policies for Long-Term LLM Agents
    Hong Su

    Long-running autonomous agents must reuse accumulated reasoning experience without allowing explicit historical memory and LLM context to grow indefinitely. However, existing memory mechanisms mainly retrieve, summarize, or compress past content and do not directly learn when particular kinds of thinking should be activated or discover new thinking knowledge from temporally dispersed experiences. This paper proposes a situation-conditioned thinking memory framework that transforms historical reasoning experience into a lightweight policy for predicting what should be thought about in the current situation, while leaving detailed reasoning to a large language model. Situations may represent temporal or spatiotemporal evolution rather than only current states. Temporary experiences are also periodically analyzed across multiple independent episodes to identify repeated long-range regularities, which are consolidated into new thinking knowledge and further internalized by the lightweight policy. Experiments show that the learned policy achieves 1.000 F1 on temporal-rule generalization, improves DeepSeek reasoning F1 from 0.789 to 0.868, reduces online processing time from 0.3636 ms to 0.0382 ms per query at 30,000 historical situations, and reaches 1.000 relation-discovery F1 and future-thinking accuracy after sufficient repeated cross-experience evidence.

    memoryllm agentautonomous agent
  144. arxiv:2610.09588 · cs.RO
    Adaptive Code Generation for Controlling Robots
    Justus Flerlage, Thorsten Wittkopp, Alexander Acker, Odej Kao

    Deploying robots as Complex Adaptive Systems (CAS) in unknown and dynamic environments necessitates a transition from rigid command libraries toward intention-based autonomy, as natural language represents the only medium capable of articulating complex goals beyond the capacity of finite instruction sets. While Large Language Models (LLMs) offer a path toward natural language goal description, their integration introduces significant challenges: the formalization gap between imprecise intentions and executable actions, the taxonomy gap induced by unpredictable environments, and the challenge of maintaining temporal state and progress awareness. This work introduces an architectural framework that enables robotic control by leveraging generative AI. The system follows a dual-AI design: an LLM translates high-level intentions into executable program code restricted to a formal robotic library and constrained by verifiable syntax, while a Vision-Language Model (VLM) provides semantic grounding via a distillation process. To ensure robustness, the framework incorporates environment-driven replanning triggers based on geometric and semantic thresholds, complemented by continuous runtime monitoring and an adaptive planning loop. Benchmarked across frontier models, our framework architecture demonstrates that grounding generative AI in a reactive, constrained loop enables robust fulfillment of complex intentions in dynamic and unknown environments.

    benchmark
  145. arxiv:2610.09581 · cs.AI
    Correct Answers, Unsupported Findings: Evidence Binding in Forensic Reconstruction of LLM Agent Logs
    Taehyeon Yun, Dongho Kim, Geonwoo Kim, Juyoung Seo +2

    Forensic reconstruction of LLM-agent actions requires not only recovering the correct value, but establishing which preserved record supports that finding. Tool logs, generated explanations, and local citation identifiers capture different parts of this evidence, yet a citation identifier does not establish a source unless its binding to a record is preserved. We audit this distinction using 64 mechanically checkable cases from saved AgentDojo Banking executions. Two LLM readers reconstruct source relationships under controlled variations in visible evidence and identifier-to-record bindings. We separately evaluate complete-record agreement, evidence-grounded findings, justified abstention, and unsupported assertions. With original identifiers and no binding table, Sonnet recovered every literal source location but made unsupported citation-source assertions in 26 of 28 cases requiring the missing relation; 22 nevertheless matched the complete reference. Adding explicit bindings improved grounded reconstruction for both readers, whereas identifier renaming alone provided no consistent remedy. A deterministic same-packet comparator correctly resolved the bounded task or abstained throughout. These results show that factual agreement alone is insufficient for evaluating forensic reconstruction of agent logs and motivate preserving explicit record bindings to distinguish supported findings from correct guesses.

    agentllm agent
  146. arxiv:2610.09573 · cs.RO
    Point It, Strike It: Direction-Conditioned Dynamic Manipulation of Deformable Linear Objects
    Yi Yang, Xiang Fei, Lehong Wang, Zilin Dai +8

    Goal-conditioned dynamic manipulation of deformable linear objects has mainly specified goals as positions for a rope tip to reach. Many tasks, however, depend on how the tip arrives. We therefore study single-swing rope striking with goals that specify the tip's 3D position and arrival direction, across the workspace and on different ropes. This is challenging because rope dynamics are hard to model, no demonstrations exist, distinct swings reach the same goal with different reliability, and the sim-to-real gap extends beyond the rope. To address these challenges, we extend the state-of-the-art DLO simulator DeformX with GPU acceleration, a stable Cosserat rod solver, and a cross-flow aerodynamic model, yielding DeformX2.0, which is more than $20{,}000\times$ faster. We then propose TRACE (Trace-rooted Adaptive Cross-Entropy), which generates striking data by warm-starting each new target from the stored swing whose tip path passes closest to it. Its cost penalizes rope bending and abrupt tip motion to favor repeatable swings. A conditional flow-matching policy trained on this data reaches 92.1% accuracy in simulation. Finally, we propose RECAP (Residual Calibration Policy), which fits the simulator's rope and rig parameters to a few calibration swings and adapts actions with a correction policy trained in simulation. On a real robot, across three ropes, RECAP raises success within 5cm from 72% to 87% for position goals, and within 10cm and 10° from 50% to 79% for goals that also specify the arrival direction.

    manipulationsim-to-real
  147. arxiv:2610.09571 · cs.AI
    How Do LLMs Change Predictions Under Negation?
    Jongwook Yoon, Jongwon Lim, Sungjib Lim, Woojin Cho +1

    Negation is an essential feature of human language, yet large language models (LLMs) remain unreliable in processing it. We evaluate recent open-source and closed-source LLMs on our negation benchmark and find that, in 37-71% of cases, they repeat the same answer under negation (e.g., "Madrid" for "What is not the capital of Spain?"). To understand and address this brittleness, we mechanistically examine how models operate under negation. Our main finding is that specialized attention heads and MLP neurons jointly implement negation by (1) suppressing retrieval of the original answer (e.g., "Madrid") while (2) promoting a favored candidate within the answer category (e.g., "Paris"). This contrasts with accounts of human negation processing, in which information about the original answer helps to determine what should be excluded. Furthermore, we find that this difference from human processing is a key source of negation failures: the model's mechanism relies on suppressing the original answer rather than using it to determine what to exclude, so the model can repeat the original answer when suppression is too weak or when a bias toward particular answers prevents it from selecting an alternative. To address this weakness in the model's negation mechanism, we propose a training objective that requires larger shifts in answer preference for more confident original predictions, and show that it reduces negation failures with less degradation of general capabilities than standard fine-tuning baselines. Together, our results demonstrate how mechanistic analysis can reveal why a linguistic capability fails and guide training that targets the underlying limitation.

    benchmark
  148. arxiv:2610.09569 · cs.CL
    RELATE: An Evaluation Framework for measuring Relational Orientation of Large Language Models
    Shivam Shukla, Jihye Kim, Shubham Gaur, Mahnaz Roshanaei +1

    Large language models (LLMs) are increasingly used for emotional support, raising concern that sustained use may draw users away from their real-world relationships. Yet existing evaluations primarily focus on the safety, empathy, or helpfulness of responses, leaving under-examined a relational question: where does the model orient the user for continued support? To address this question, we introduce relational orientation, a property operationalized through two non-exclusive dimensions: inward-facing (IF) language, which positions the AI as the user's ongoing source of support, and outward-scaffolding (OS) language, which encourages real-world human connection. Grounded in psychological and sociological literature, we formalize a taxonomy of relational orientation and present RELATE, a persona-conditioned framework for measuring inward-facing and outward-scaffolding language at the sentence level in multi-turn dialogues. RELATE pairs 76 help-seeking situations adapted from naturally occurring questions with three simulated user styles, providing 228 evaluation stimuli. In our experiments, we evaluate seven LLMs using dialogues with six assistant turns each, yielding 1,596 dialogues and 69,194 assistant sentences. We assess these sentences using a primary rubric-based LLM judge and apply a secondary judge to a subset. Under automated evaluation, we find that the proportion of sentences labeled as IF is higher at the sixth assistant turn than at the first, while the proportion labeled as OS is substantially lower for hesitant, indirect simulated users than for explicit, reassurance-seeking users. RELATE provides a reproducible framework and a sentence-level signal for auditing and steering the relational orientation of supportive LLMs.

    evaluation framework
  149. arxiv:2610.09566 · cs.RO
    Targeted Modality Dropout for Real-Robot Manipulation Robust to Intermittent Vision Loss
    Genki Shikada, Kazuki Osamura, Masaru Ide, Tetsuya Ogata +1

    Imitation learning policies that integrate multiple sensory modalities are prone to overreliance on a dominant modality, such as vision, during training, which can disrupt policy execution when that modality is lost at inference time. In this paper, we introduce Targeted Modality Dropout (TMD), in which the dependence on each modality is estimated using attention and the most dominant modality is selectively dropped. This is combined with entropy regularization over the dependence distribution. Through real-robot evaluation using a bimanual manipulator, we show that under vision loss the success rate of the baseline policy drops substantially, whereas TMD sustains task execution. In contrast, a conventional dropout that selects the dropped modality at random, without the entropy regularization, fails on many tasks even without vision loss.

    manipulationmanipulator
  150. arxiv:2610.09560 · cs.AI
    World Potential Model: Pretrained World Knowledge as Progress Potentials
    Jun Zhao, Jixin Tang, Yang Shu, Jinyang Wu +5

    Long-horizon language agents often receive supervision only from terminal task outcomes, leaving little signal for distinguishing productive intermediate behavior from stagnation or even regression. Rather than learning a separate value function or process reward model for every task, we ask whether pretrained models can recognize task progress from their existing world knowledge. We formalize this capability with a World Potential Model (WPM), a goal-conditioned evaluator of task-relative realized progress in agent contexts. In ALFWorld and ScienceWorld, off-the-shelf pretrained models substantially outperform chance at recovering realized-progress structure without task-specific evaluator fine-tuning. We further anchor these progress judgments to task-specific milestones to obtain scalar world potentials, whose temporal differences provide process-sensitive step-level credit for policy optimization. Under matched comparisons, WPM-guided optimization improves success over outcome-only GRPO across all evaluated configurations. Together, these results provide initial evidence that pretrained world knowledge can support reusable realized-progress evaluation and provide useful supervision for long-horizon agents.

    agentevaluator
  151. arxiv:2610.09558 · cs.AI
    DrugTargetWorld: A Synthetic Biobank for Training and Benchmarking AI Scientists
    Samuel Margolis, Paul Schmiedmayer, Alan Huang, Ethan Chen +11

    Drug target discovery requires distinguishing molecules that causally drive disease from those that are merely associated with it. Training and evaluating AI agents to perform this workflow end-to-end is difficult because real world biobanks lack known causal ground truth and participant-level data is access controlled. We introduce DrugTargetWorld, a framework that procedurally generates simulated biobanks, or "worlds," with known but concealed causal structure. Each world contains genotypes, proteins, health records, outcomes, and synthetic magnetic resonance imaging (MRI) for 54,000 participants. Agents must construct a disease phenotype, identify causal driver proteins, infer the beneficial direction of modulation, and optionally conduct virtual 'wet lab' experiments. We evaluated nine agents in 540 episodes across 20 cardiovascular worlds and three experimental budgets. Opus 5 and GPT-5.6 Sol achieved the highest mean composite scores, 39.98 and 35.38 of 100, respectively, and both recovered 64% of causal drivers on average. However, no agent reliably distinguished misleading non-causal proteins, and performance remained limited by the integrative judgments required to connect phenotype construction, causal evidence, and intervention decisions. By making each world's causal structure known to the evaluator but hidden from the agent, DrugTargetWorld turns end-to-end drug target discovery into a scalable training and evaluation problem with verifiable reward.

    agentai agentbenchmarkevaluator
  152. arxiv:2610.09554 · cs.AI
    Reliability of LLM Judges for Evaluating Entity Alignment
    Vaibhava Lakshmi Ravideshik, Mayank Kejriwal

    Entity Alignment (EA) identifies equivalent entities across knowledge graphs and is critical for knowledge base integration and ontology merging. Evaluating EA systems at scale requires expensive expert annotation, making systematic assessment across diverse domains practically infeasible. LLM-as-judge evaluation offers a potentially scalable alternative, yet its reliability for structured prediction tasks like EA remains unstudied. We present the first systematic benchmarking study across three frontier models, three datasets, and four EA systems, using perturbation bias diagnostics, meta-evaluation across all dataset-judge-prompt combinations, and counterfactual label-flip tests. We identify anchor bias, a failure mode in which judges invert discrimination when the system's decision label is visible. Label exposure causally collapses judge discrimination (J-ROC-AUC 0.12-0.87), while a label-free protocol recovers near-ceiling capability on distinctive-name datasets (0.93-1.00) and significant recovery on biomedical pairs (0.93-0.95). Counterfactual experiments confirm causality (FSR 53-99%) and reveal a frontier model paradox: stronger judges exhibit greater label sensitivity, not less. A blinded two-annotator human evaluation (102 pairs, Cohen's kappa=0.902) confirms this mechanism directly. We release the first biomedical EA benchmark (MeSH-SNOMED CT, 15K pairs) and a reproducible auditing framework for LLM judge reliability in EA. Code and data are available at https://github.com/vaibhavalakshmiravideshik/llm-as-a-judge-entity-alignment.

    knowledge graphbenchmarkllm-as-judge
  153. arxiv:2610.09552 · cs.CL
    Constitution-Guided Watermarking
    Toluwani Aremu, Samuele Poppi, Nils Lukas

    Watermarking enables language model providers to identify text generated by their models. However, its desired properties can conflict (\ie~stronger watermark signals can degrade text quality), while designs that resist editing may also facilitate forgery. Providers address these trade-offs by choosing configurations that balance competing objectives or prioritize particular properties. Either approach imposes a shared operating point on requests with different requirements, potentially sacrificing quality where wording preservation matters or robustness where reliable attribution is essential. To allow flexible and adaptable designs, we introduce \emph{Constitution-Guided Watermarking}, a framework that selects request-appropriate trade-offs from provider requirements, listed as natural-language principles. \emph{Offline}, a pretrained reasoning agent examines constitutional rules alongside watermark implementations and iteratively refines rule-specific configurations using empirical feedback. \emph{At deployment}, a separate monitor identifies applicable rules and retrieves the corresponding policy, including watermarking exemptions, without modifying the serving model. Furthermore, our framework supports offline parallel optimization and refinement of rule-specific configurations based on evolving provider requirements without affecting deployment, and binds each deployed configuration to its evaluation evidence, making deployment decisions auditable. In a proof-of-concept evaluation using KGW and a five-rule constitution, our framework selects configurations responsive to provider priorities and improves post-paraphrase detection on robustness-prioritized requests by up to $14$ percentage points over fixed configurations, while matching or exceeding all baselines in aggregate quality and clean detection at a nominal $0.1\%$ false-positive rate.

    agent
  154. arxiv:2610.09541 · cs.CL
    Certified by Abstention: Distribution-Free Guarantees for Chain-of-Thought Verifiers at Small Calibration Budgets
    Arjun Balaji

    Signals that predict whether a chain-of-thought (CoT) trace is correct are compared by AUC, but deploying one requires a threshold with a guarantee. We ask what distribution-free selective guarantees deliver for CoT verifiers at realistic calibration budgets of tens to a few hundred labelled problems, using seven open models, five verifier signals and 37,000 graded traces. The central observation is validity by abstention: an $(α,δ)$-valid procedure that issues a certificate with probability $P_{\rm fire}$ bounds the failure probability of an issued certificate only by $δ/P_{\rm fire}$, so a certificate that rarely fires can be valid and wrong every time it is used. In a simulation with known risk the standard certificate fails in at most 0.3% of calibration draws but in up to 69% of those in which it fires. A certification floor and a lattice condition for Benjamini-Hochberg conformal selection explain why certificates abstain at these budgets, and the data bear them out: the standard certificate returns nothing or a large accepted set, and an unreadable residual-stream probe buys two to three times the coverage of the readable signals, an edge a cross-fitted reconstruction cannot recover linearly from the readable features. We then give a floor-started fixed-sequence certificate, valid without monotonicity assumptions, that covers more than the Bonferroni certificate on every model-signal pair and raises coverage at the non-vacuous target $0.75π_0$ from 0.05 to 0.16, although the floor keeps absolute coverage small. Finally, a certificate cannot see what matters after deployment: under benchmark shift the error among accepted traces tracks the new task's base error, and under best-of-$n$ selection against the verifier it rises past the target while the empirical failure frequency stays below $δ$, because abstention absorbs the failures.

    benchmark
  155. arxiv:2610.09536 · cs.RO
    MagCilia: A Compact Magnetociliary Tactile Sensor with 3D Force Sensing for Robotic Contact Perception and Grasping Feedback
    Yu Feng, Hao Wu, Haotian Guo, Haoming Liu +6

    Robotic grasping and surface exploration benefit from simultaneous measurement of normal and tangential forces and from surface information obtained through contact. Here, we present a compact magnetociliary tactile sensor (MagCilia) that combines a flexible magnetic-cilia structure with a Hall sensor for 3D force sensing. Quasi-static finite element analysis is used to investigate structural deformation and magnetic responses under multidirectional loading. To reconstruct forces from the coupled magnetic channels, we propose causal history fusion regression (CHFR), which combines current magnetic-field measurements with their recent changes. Five-fold cross-validation grouped by calibration record yields root-mean-square errors of 0.40, 0.57, and 0.69 N for Fx, Fy, and Fz, respectively, with corresponding coefficients of determination of 0.93, 0.90, and 0.92. Robotic experiments demonstrate tangential-force-guided gripper adjustment and multi-axis load monitoring under external perturbations. Frequency-domain features of the reconstructed forces distinguish six surface categories with 99.39% accuracy in three-fold cross-validation grouped by acquisition session. An online robotic demonstration additionally identifies all six tested surfaces. These results demonstrate 3D force reconstruction, grasping feedback, and surface recognition using a single compact tactile unit.

    tactilegrippergrasp
  156. arxiv:2610.09533 · cs.RO
    Contact-Aware Imitation Learning Through Contact Factorization
    Jiho Hong, Daeun Song, Sanghyun Kim, Mingyo Seo

    Generalizable contact-rich manipulation requires robots to preserve intended task behavior while adapting its physical realization to changing contact conditions. However, interaction forces can vary substantially with small changes in surface geometry, orientation, and friction, making policies trained directly on raw force measurements difficult to transfer beyond demonstrated conditions. We introduce FACE, a contact-factorized imitation learning framework that separates intended task behavior from environment-dependent contact factors. Our representation expresses interaction forces in normalized, contact-relative coordinates, while a learned contact-normal estimator and an online friction estimator infer the local contact normal and effective friction scale. Together, these estimators enable force observations to be encoded and policy outputs to be decoded into physical motion and force commands during execution. In this way, FACE adapts execution to current contact conditions while preserving the intended task behavior, without updating the policy parameters. We evaluate FACE on real-robot contact-rich manipulation under unseen variations in surface properties and geometry, demonstrating robust generalization across contact conditions through controlled comparisons with variants that adapt prior approaches to our setting. Videos and additional materials can be found on the project page: https://rcilab.khu.ac.kr/face.

    manipulation
  157. arxiv:2610.09529 · cs.CL
    A Comparative Study of Evaluation Metrics for Long-Document Financial Narrative Summarization with Transformers
    Nadhem Zmandar, Mo El-Haj, Paul Rayson

    There are more than 2,000 listed companies on the UK's London Stock Exchange, divided into 11 sectors who are required to communicate their financial results at least twice in a single financial year. UK annual reports are very lengthy documents with around 80 pages on average. In this study, we aim to benchmark a variety of summarisation methods on a set of different pre-trained transformers with different extraction techniques. In addition, we considered multiple evaluation metrics in order to investigate their differing behaviour and applicability on a dataset from the Financial Narrative Summarisation (FNS 2020) shared task, which is composed of annual reports published by firms listed on the London Stock Exchange and their corresponding summaries. We hypothesise that some evaluation metrics do not reflect true summarisation ability and propose a novel BRUGEscore metric, as the harmonic mean of ROUGE-2 and BERTscore. Finally, we perform a statistical significance test on our results to verify whether they are statistically robust, alongside an adversarial analysis task with three different corruption methods.

    benchmark
  158. arxiv:2610.09525 · cs.AI
    Align Before You Combine: Reference Space Calibration for Supervision Without Ground Truth
    Jackson Eshbaugh, Jorge Silveyra

    We introduce a calibration-first framework that produces supervision scores without access to ground-truth labels or a shared annotation space. Our framework aligns subset-specific scorers using a synthetic ordinal reference space before fusion. This reference space is constructed from ordered calibration features that represent the latent concept, providing a common scale on which otherwise incomparable scorer outputs can be aligned. Because our calibration procedure uses the reference space rather than training samples, it is independent of the training set's empirical distribution. Across three benchmark datasets, our framework consistently outperforms uncalibrated averaging and achieves higher primary-metric point estimates on the evaluation metrics than the best individual scorer. Performance relative to sample-dependent baselines varies by domain, with absolute differences below 0.02 on Ames Housing and below 0.01 on Breast Cancer Wisconsin and Wine Quality. After Bonferroni correction, differences remain significant for all three comparisons on Ames Housing and one on Breast Cancer Wisconsin. Additionally, we show that using fewer calibration levels per feature can closely approximate higher-resolution results at substantially lower computational cost. Together, these results support our framework as a viable approach to construct supervision scores when neither ground-truth labels nor a shared annotation space is available.

    benchmark
  159. arxiv:2610.09518 · cs.RO
    ActiveLang: Active Open-Vocabulary 3D Mapping with Semantic-Uncertainty-Guided Exploration
    Liyan Chen, Hairong Yin, Huangying Zhan, Yi Xu +2

    As robots increasingly assist humans with diverse tasks, they need both geometric and semantic understanding of their surroundings. Moreover, robots often operate in unfamiliar environments and take on new tasks without knowing the relevant concepts ahead of time. This motivates language-annotated 3D maps that support open-vocabulary scene understanding and human-robot interaction. We introduce ActiveLang, an autonomous system for active open-vocabulary 3D mapping with semantic-uncertainty-guided exploration. ActiveLang performs online language-feature adaptation on a compact dual-Gaussian representation to jointly reconstruct scene geometry, appearance, and open-vocabulary semantics with modest memory overhead. Its planner efficiently selects informative viewpoints, enabling effective mapping with fewer observations and lower computational cost. Experiments on Replica and ScanNet++ demonstrate substantial improvements in 2D and 3D open-vocabulary segmentation over both online and offline baselines, highlighting that actively exploring scenes builds language-annotated 3D maps more efficiently.

    memory
  160. arxiv:2610.09509 · cs.RO
    TERRA: Learning Transportable Latent Actions through Temporal Effect Representation and Relational Alignment
    Tianxingjian Ding, Mubarak Shah, Yu Tian

    Latent actions supervise robot policies with action-like codes inferred from visual transitions, and their usefulness hinges on two questions: what a code keeps from a transition, and whether it still means the same thing when reused in a different initial state. The first is a tension in time: an endpoint difference discards how motion unfolds, while the full sequence admits nuisance variation. The second is left open by reconstruction, which only ever observes a latent together with the state it came from. We argue that both questions can be answered in the same place. TERRA (Temporal Effect Representation and Relational Alignment) describes a transition by a compact temporal effect, its net feature change together with a low-order within-window dynamics component, and learns a continuous latent from this effect. The same effect space then serves as the reference for reuse: Effect-Anchored Transport (EAT) decodes a latent in other initial states and anchors the resulting effect to the one observed at its source, so that the latent is shaped by what it does across contexts rather than only by the transition it came from. With frozen linear readers, TERRA predicts actions more accurately than UniVLA and a LAPA-style baseline, degrades more slowly under visual distractors, and keeps transported transitions faithful to the donor action as the recipient context moves farther away; a same-budget control shows that these gains come largely from EAT. At matched pretraining scale, the complete system reaches 93.4% average success on LIBERO, compared with 91.8% for UniVLA.

    libero
  161. arxiv:2610.09497 · cs.AI
    Ream: Unfolding Mutual Awareness in Human-Agent Workspaces
    Peiling Jiang, Sangho Suh, Varsha Kishore, Jonathan Bragg +5

    As AI agents work alongside humans in shared workspaces, a mutual awareness challenge arises: agents act at speeds that outpace human monitoring, and users' evolving interests are not always expressed in chat. This challenge is especially pressing in literature review, where both parties retrieve, read, and synthesize a growing body of papers. We present Ream, a literature review workspace that supports mutual awareness through structured artifacts, bidirectional engagement tracking, and localized visualizations. Users can see each party's activity within these documents, and agents can retrieve the same history to guide their work. In studies with eighteen researchers, participants used these traces to inspect evidence, steer agents, communicate through annotations, and reflect on their research focus. Shared histories also helped agents build on earlier work. These findings inform how engagement traces within shared documents can support transparency, personalized assistance, and coordination in human-agent knowledge work.

    ai agent
  162. arxiv:2610.09496 · cs.RO
    Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models
    Jiho Lee, Jeongeun Park, Heayoun Choi, Taekyung Kim +1

    Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by leveraging rich representations from pretrained vision-language models. However, their deployment in real-world environments remains limited by recurring unreliable behaviors. In this work, we study state hallucination, a recurring failure pattern in which a VLA continues acting as if an unrealized robot-object state had been achieved. Our analyses find that state hallucination coincides with weakened attention to task-relevant visual regions, and a mechanistic interpretation via sparse autoencoders reveals that hallucination-associated sparse features are activated when these failures occur. Based on this analysis, we propose SOUL (Sparse feature pOlicy UnLearning), which selectively unlearns policy knowledge associated with state hallucination behaviors, where sparse features identified from hallucination failures and successful behaviors serve as explicit forgetting and retention targets, respectively. Experiments across VLA architectures in simulated and real-world environments show that our method substantially reduces hallucinated failures and improves task success without substantially compromising the existing manipulation capabilities. These results suggest that interpretable feature analysis provides a practical basis for selectively modifying undesirable knowledge in robot policies.

    vision-language-actionvlamanipulation
  163. arxiv:2610.09493 · cs.AI
    The Attribution Blind Spot: Layerwise Trajectory Diagnostics for Source Reliance in Retrieval-Augmented Language Models
    Zhe Yu, Wenpeng Xing, Yunzhao Wei, Bo Yang +3

    A retrieval-augmented model can match a document without relying on it. Controlled knowledge conflicts make source choice observable and let us ask a second question that prediction alone cannot answer: which internal-state properties define useful intervention directions? We study paired hidden-state changes with Latent Trajectory Shift (LTS), a signed projection onto a training-fitted first principal component (PC1), and keep verified training exposure separate from behavioral source choice. Across the evaluated conflicts, state-change magnitude is often the stronger predictor, whereas signed PC1 is the stronger selective controller: equal-norm interventions change source preference while better preserving non-target behavior, and the frozen direction transfers across the tested datasets and aligned model pairs. A same-system OLMo study further combines positive choice and control results with inconclusive exposure detection at the achieved power. The central result is a separation: representations that diagnose what a model will choose need not be the representations that best control that choice.

    retrieval-augmented
  164. arxiv:2610.09489 · cs.CL
    Goldsmith: Gold-Loss-Guided Definition Optimization with an Agentic Annotation Harness
    Yihan Li, Hanyi Zhang, Xiaoxi Jiang, Man Guo

    Many annotation projects begin before experts have a stable guideline or enough labels to train a task-specific model. We present Goldsmith, an agentic pipeline that turns a small gold set---expert-annotated calibration examples representing the intended task boundaries---into a reusable structured annotation definition. Goldsmith treats this definition as a trainable textual object. Candidate definitions are run on the same gold examples and scored with an executable structured loss, while the output schema, formatting, retrieval, repair, judging, and human review remain in an external harness. A large language model (LLM) editor converts the highest-loss failures into textual-gradient revisions, which are accepted only when the measured loss decreases. In prompt-optimization comparisons, Goldsmith improves over direct rewriting, OPRO, APE, and PromptBreeder under matched evaluation protocols. The resulting definition also improves downstream annotation when combined with retrieval, score-based routing, and human review across typed span, pair-level relation, and fixed-trigger event-argument tasks. These results show that scarce expert supervision can support both task-definition learning and scalable annotation.

    agenticevaluation protocol
  165. arxiv:2610.09488 · cs.RO
    SiGNgapore - An Interactive Dataset for Sign-based Visual Navigation
    Nicky Zimmerman, Joel Loo, Zishuo Wang, David Hsu

    The future of autonomous robots in human-oriented environments depends on their ability to navigate in the absence of prebuilt maps; exploiting navigational aids, such as navigational signs, designed by humans for humans is critical for enabling autonomy. This manuscript introduces a unique dataset collected using a handheld device, at various public spaces across Singapore, representing environments that humans frequent daily, and focusing on sign-centric decision making for mapless navigation. The dataset includes RGB, sparse depth, odometry and IMU measurements of scenarios centered around navigational signs and the complex environments where they are placed. Additionally, we provide 56 long-horizon navigation missions and over 450 sign-centric scenarios. All data is provided in a human- readable format, as well as utility scripts for conversion to ROS 2. Lastly, we provide venue maps and GPS aligned scene graphs of the test environments. We discuss the potential use cases for this dataset.

    scene graph
  166. arxiv:2610.09487 · cs.AI
    Correspondences as Decisions: JevNexus for Decision-Centric Schema Matching
    Runze Li, Hanchen Wang, Ying Zhang, Wenjie Zhang

    Schema matching increasingly uses generative language models to rerank retrieved column candidates, although the underlying task is a bounded correspondence decision. We present JevNexus, which combines typed pairwise decisions with schema/instance evidence and invokes listwise refinement only when the evidence disagrees and the fused margin is small. The evaluation covers 561 cases from six benchmark families. JevNexus obtains dataset-macro MRR and Hits@1 of 0.930 and 0.909, compared with 0.926 and 0.903 for Magneto, while reducing mean latency from 123.452 to 15.929 seconds (7.750). Paired analysis finds no statistically significant difference in either MRR or Hits@1. The gate invokes listwise refinement for only 5.665% of source columns and avoids the degradation caused by unconditional refinement. Code and experimental artifacts are available at https://github.com/RazeenLI/JevNexus.

    benchmark
  167. arxiv:2610.09484 · cs.AI
    MIMESIS: Learning User Simulators as Training Environments for Interactive Agents
    Hoang Phan, Dat Huynh, Andrey Zhmoginov, Qi Zeng +6

    Training and evaluating interactive language agents typically requires rich user interactions, yet collecting human feedback is expensive and difficult to scale. Simulated users offer a scalable alternative, but they must both resemble real user behavior and provide useful learning experiences for agents. In contrast, most agent-training frameworks rely on off-the-shelf assistant LLMs, whose helpfulness can make them overly cooperative, explicit, and behaviorally homogeneous compared with real users. We introduce MIMESIS, a purpose-built user simulator trained on human conversations with explicit reasoning supervision and 13 realistic behavioral patterns derived from real user interactions. Empirically, our 9B model achieves a SOUL-Index of 65.7, surpassing the strongest frontier model. Compared with Claude-Opus-5, the strongest baseline on RealUserSim and SimulatorArena, MIMESIS improves behavioral fidelity by 13.4 points and reduces Turing distance by 3.6 points, respectively. We then freeze the simulator and train an agent by interacting with the frozen simulator using multi-turn reinforcement learning. Across eight environments, training with MIMESIS yields better agent performance than training with GPT-5.5 under all nine unseen user simulators, demonstrating stronger generalization to new user simulators. Moreover, we propose Coached On-Policy Self-Distillation (CSD), which leverages simulator-generated private reasoning traces and subsequent utterances as feedback on how well the agent addresses user needs. A coach converts this information into concise coaching notes that describe how the agent can better anticipate user needs and adapt its behavior over the course of an interaction. CSD turns this feedback into dense, token-level supervision beyond sparse task rewards, yielding further gains across all nine evaluation user models.

    agent
  168. arxiv:2610.09479 · cs.RO
    Precise SE(3) End-Effector Tracking in Whole-Body Humanoid Control
    Joohwan Seo, Xiaofeng Guo, Jinkun Cao, Roberto Horowitz +3

    Precise end-effector tracking during humanoid whole-body motion is challenging due to floating-base oscillations, gravity, dynamic coupling, and locomotion-induced disturbances. We propose ResGAC, a whole-body humanoid controller for precise end-effector pose tracking that combines geometric admittance control (GAC) with residual reinforcement learning. GAC provides structured $\SE$ task-space feedback and generates nominal arm joint-position targets, while residual RL compensates for unmodeled dynamics and coordinates locomotion and balance in the shared joint-position action space. The left-invariant geometric formulation allows the same GAC law to be used across manipulation reference frames. This enables the use of a ground-attached heading frame that preserves planar locomotion while removing pelvis roll, pitch, and heave from the manipulation reference, thereby reducing reference-induced end-effector motion during locomotion. ResGAC is validated on a real Unitree G1 humanoid. Across four standing end-effector tracking benchmarks, ResGAC consistently outperforms representative baselines, including SONIC, achieving lower translational and rotational errors. Real-world experiments further demonstrate reduced propagation of pelvis motion to the desired end-effector pose using the proposed ground-attached heading frame. ResGAC achieves $90\%$ success in a standing peg-in-hole task compared with $50\%$ for SONIC, and accurate world-frame $\SE$ end-effector pose tracking during lower-body motion. Experimental videos are included in the supplementary material and are also available on the project website: https://resgac.github.io/ResGAC-website/.

    manipulationhumanoidbenchmark
  169. arxiv:2610.09473 · cs.AI
    MORA: Modeling Observed Changes for Drift-Robust Time-Series Anomaly Detection
    Xudong Mou, Tiejun Wang, Rui Wang, Hui Wang +4

    Time-series anomaly detection (TSAD) identifies deviations from patterns learned from historical data. In non-stationary settings, distribution drift and true anomalies can cause similar local changes, making it difficult to tell whether a deviation reflects abnormality or evolving context. Existing methods typically adapt to detected shifts or learn drift-insensitive representations, but do not resolve this ambiguity. We define this problem as \emph{temporal change disambiguation}: determining whether a local deviation is explained by broader temporal evolution. We introduce MORA, a drift-robust TSAD framework that reconstructs the same local target from paired short- and long-term views. The reconstruction gap measures contextual support for a local deviation, and a data-dependent correction mechanism conservatively adjusts the primary local anomaly score. Context can only reduce the score when it improves reconstruction of the same target. MORA needs neither drift annotations nor online adaptation. Experiments on four TSAD benchmarks show strong robustness to non-stationarity while preserving sensitivity to genuine anomalies.

    benchmark
  170. arxiv:2610.09467 · cs.CL
    Boundary-Free Contextual Biasing: Depth-Adaptive Gating and Reading-Space Matching for Unsegmented Languages
    Muhammad Huzaifah, Yu Pan, Zachary Yeo, Ningjie Bai +1

    Contextual biasing supplies an ASR system with a list of expected words at inference time, but existing methods rely on word boundaries that Japanese and Chinese do not provide. We present a boundary-free biasing decoder for frozen public CTC models, built on a character-level Aho-Corasick automaton, with no training and no second pass. Two evidence-based mechanisms replace the boundary: a depth-adaptive gate that sets how hard to push from match depth, and reading-space matching for when the audio is right but the characters are wrong. On Aishell-1 NE's hard R1 subset we reach 66.5% recall, above the trained CLAS baseline (64%), transferring to WenetSpeech and to a second architecture without retuning. We release the first open Japanese contextual-biasing benchmark, where biasing lifts rare-word recall by 25 points at precision above 97%, and still by 19 and 22 points against 1,000-word lists.

    benchmark
  171. arxiv:2610.09466 · cs.AI
    LLM-Enabled UAV Dispatch: A System-Level Survey and Taxonomy
    Xiao Han, Aoyang Quan, Xiangyu Zhao, Xiangjie Kong +1

    Unmanned aerial vehicle (UAV) dispatch is beginning to move beyond isolated path planning and optimization-driven resource allocation toward system-level coordination supported by semantic reasoning and LLM-based interfaces. This survey provides a unified characterization of LLM-enabled UAV dispatch systems that bridges semantic intent, symbolic decision-making, and physical UAV execution. Rather than treating LLMs as standalone add-ons, we conceptualize them as a cross-layer semantic orchestration layer connecting human instructions, external solvers, and distributed control modules. We organize the literature into four representative dispatch paradigms: pipeline dispatch, global assignment dispatch, decentralized agentic dispatch, and divide-and-conquer dispatch. For each paradigm, we analyze its decision logic, system structure, control flow, representative methods, and potential LLM roles. We further examine how LLMs support semantic parsing, retrieval-grounded planning, solver orchestration, local agent reasoning, multi-agent coordination, safety assessment, and human-facing explanation. We discuss the implications of these paradigms for scalability, robustness, coordination burden, and verification requirements, and identify open challenges including latency-aware reasoning, grounding reliability, physical feasibility guarantees, edge deployment, privacy protection, and distributed consistency. This survey provides a system-level taxonomy and design perspective for integrating LLMs into safety-critical UAV dispatch systems.

    agentmulti-agentagentic
  172. arxiv:2610.09464 · cs.CL
    BanglaRhet: Benchmarking Classical and Transformer Models for Rhetorical and Persuasion Detection in Bangla Political Speech
    Rohit Kumar Sen, Anik Chowdhury

    Political discourse often uses rhetorical and persuasive language to frame narratives, influence public opinion, and mobilize audiences. While Bangla natural language processing has made progress in sentiment analysis and opinion mining, systematic benchmarking of transformer models for fine-grained rhetorical and persuasion technique detection in Bangla political speech remains largely underexplored. This paper presents a benchmark study of transformer-based models for detecting rhetorical form and persuasive intent in Bangla political discourse. Using BanglaRhet, a manually annotated corpus of 30,289 Bangla political speech segments collected from publicly available political news sources, we formulate two supervised single-label classification tasks: rhetorical technique detection (contrast, repetition, exaggeration, metaphor, rhetorical questions) and persuasion technique detection (blame assignment, call to action, unity call, moral, emotional, and logical appeals). We evaluate four transformer-based models, BanglaBERT, BanglaBERT-Base, SahajBERT, and XLM-RoBERTa-Base, against classical TF-IDF baselines. BanglaBERT achieves the highest performance, with 65.40% macro-F1 for rhetorical technique detection and 66.46% for persuasion technique detection, outperforming the best tuned classical baseline by 19.2 and 13.8 macro-F1 points, respectively. Class-level analysis indicates that errors are mainly associated with semantic overlap among labels, figurative language, and class imbalance. The results provide initial benchmark baselines for Bangla rhetorical and persuasion-aware political discourse analysis and highlight the need for context-aware and multi-label modeling.

    benchmark
  173. arxiv:2610.09462 · cs.RO
    TMT: Runtime Backdoor Detection for Vision-Language-Action Policies on Unseen Tasks
    Zirun Zhou, Jingfeng Zhang, HaoChuan Xu, Xizhe Zhang +3

    Backdoored vision-language-action (VLA) policies can preserve benign task performance while producing malicious actions when a trigger appears. Detecting such activation is difficult because malicious behavior can comprise individually plausible actions, while unfamiliar tasks introduce legitimate changes in observations and behavior. We introduce TMT, a runtime backdoor detector based on Token Manifold and latent Transition modeling. Trained on benign rollouts, its two branches assess input-token structure and prediction errors in adjacent-layer latent dynamics. A suspicious rollout identified by the token manifold branch, once confirmed through latent deviations, guides transition selection for subsequent monitoring. We further explore policy purification through self-distillation: a frozen copy of the backdoored policy provides benign-input actions to supervise a student on paired benign and triggered observations, without requiring a separate clean reference policy. For evaluation, we adapt traditional backdoor detectors and repurpose anomaly and failure detection methods as VLA backdoor detectors. In a post-hoc comparison with ten baselines, TMT achieves state-of-the-art backdoor detection performance on unseen tasks across three VLA backdoor attacks. Our project page is available at https://zzr42.github.io/tmt/.

    vision-language-actionvlalatent dynamics
  174. arxiv:2610.09457 · cs.RO
    DSReg: Provably Recovering Individual World Latents without Reconstruction
    Yujia Zheng, David Klindt, Randall Balestriero, Bernhard Schölkopf

    Methods that recover individual latent variables of the world, from nonlinear ICA to dictionary learning and causal representation learning, anchor the latents to observations through reconstruction, auxiliary supervision, or distributional asymmetries such as non-Gaussianity. Methods without these anchors, including joint-embedding predictive architectures (JEPAs), identify the latent state only up to a linear transformation, so individual latents remain mixed. We close this gap: individual world latents can be provably recovered with no reconstruction, no decoder, and no labels. The key condition is Structural Diversity: different latents leave distinct dependency footprints on observations, just as no two snowflakes are alike. Building on the linear identifiability that LeJEPA provides, we prove that under Structural Diversity, DSReg (Dependency-Sparsity Regularization) recovers individual world latents up to signed permutation, without reconstruction or a decoder. It applies post hoc to any linearly identified representation, reusing trained checkpoints at no loss over joint training, and establishes the first fully identifiable JEPA that recovers every world latent. Moreover, as a condition on dependency footprints, Structural Diversity is strictly weaker than all structural conditions of prior identifiable latent variable models. Across synthetic regimes, world model probes, learned visual encoders, and external renderers, DSReg preserves dense prediction while improving individual-latent recovery and downstream use with scales.

    world model
  175. arxiv:2610.09456 · cs.AI
    GeoPrior-Mamba: Structured Process Priors with Mamba for Fine-Resolution XCO2 Reconstruction
    Zhao Meng, Yinan Cai, Siru Zhong, Juepeng Zheng +1

    Reconstructing fine-resolution column-averaged dry-air CO2 (XCO2) fields from sparse satellite observations requires models to infer spatial structure that is only weakly constrained by direct measurements. Existing learning-based methods typically treat environmental covariates as ordinary numerical inputs and must therefore learn heterogeneous source-sink relationships largely from sparse supervision. We introduce GeoPrior-Mamba, a multi-directional Mamba framework augmented with offline language-model-induced structured process priors. Rather than using a language model to predict XCO2, we use it before training to organize relative process knowledge for biospheric uptake, ecosystem respiration, and anthropogenic emissions into deterministic prior tables. These priors are spatially instantiated using geographic, ecological, emission-related, and seasonal information and are adaptively injected into the reconstruction backbone through a lightweight knowledge adapter. Using OCO-2 observations from 2018-2020, GeoPrior-Mamba achieves an RMSE of 0.81 ppm and an R2 of 0.93 on held-out observations, reducing RMSE by 48.2% relative to CAMS background interpolation and by 3.1% relative to Trans-XCO2 under the same evaluation protocol. Ablation experiments show a measurable contribution from the knowledge-prior branch and substantially faster convergence than the knowledge-free Mamba backbone. Independent TCCON evaluation further supports the consistency of the reconstructed fields with ground-based column CO2 measurements. These results suggest that language models can provide a practical mechanism for constructing structured process priors when globally consistent process-response representations are difficult to obtain directly, while remaining outside the numerical prediction loop.

    evaluation protocol
  176. arxiv:2610.09455 · cs.RO
    RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning
    Seungjun Moon, Subin Jeon, Sangwoo Kim, Hanbyul Joo +1

    Recently, approaches that leverage human video datasets for robot policy training have become increasingly prevalent. However, most existing hand trackers regress pose from cropped frames with limited priors on hand motion and object interaction, resulting in inaccurate and physically inconsistent estimates. Moreover, the lack of physical cues, e.g., contact and force, limits the use of human videos for robot policy training. To this end, we propose RLHND, a video foundation model-based hand tracking model that jointly estimates hand pose and realistic tactile information from monocular egocentric videos. RLHND turns the pre-trained Cosmos 3 video diffusion backbone into a deterministic clip-level feature extractor via clean-latent conditioning, carrying its learned priors on hand motion and hand-object interaction into tracking. For pose estimation, RLHND (i) predicts hand poses with anatomically plausible joint angles and (ii) enables optional conditioning on the shape parameter to maintain consistent hand shape within the same video and even across videos recorded by the same actor. For tactile estimation, a separate tactile expert stream, trained with the pose stream frozen, predicts dense contact and force over the hand surface. We further adopt LBS-based feature spreading to enable vertex-wise feature extraction without costly per-vertex attention. RLHND achieves state-of-the-art performance across various benchmark datasets for pose estimation, while also achieving state-of-the-art performance in contact and force estimation. Moreover, we demonstrate the utility of RLHND for robot learning through retargeting results and real-world robot experiments. The code will be publicly available at https://seungjun-moon.github.io/rlhnd/.

    tactilerobot policybenchmark
  177. arxiv:2610.09454 · cs.RO
    RobotAPO: Adversarial Physics Preference Optimization for Robotic Manipulation Video Generation
    Kerui Li, Zhe Jing, Chenyi Huang, Xiaofeng Wang +3

    Robotic manipulation videos are increasingly used as visual plans for embodied agents, but optimizing purely for visual plausibility often fails to capture the fragile physical manifold of real-world interactions. Even minor physics-violating errors at the interaction boundary, such as interpenetration or premature object motion, can completely invalidate the inferred timing and pose needed for downstream execution. Because standard supervised fine-tuning lacks the direct pressure to penalize these localized failures, we introduce AgiBot-PhysPref. This rigorously curated 10,000-sample preference dataset isolates condition-matched physics violations, turning the generator's own failure distribution into a foundational signal for physical consistency. Building upon this, we propose RobotAPO, an adversarial physics preference optimization framework operating in the continuous flow-matching denoising space. To prevent the policy from merely memorizing static curated failures, RobotAPO employs a lightweight adversarial counterfactual proposer that learns a condition-dependent, physical-failure-biased direction in denoising space. This encourages the model to explore and better respect the physical interaction boundary, all while maintaining a pure prompt-and-reference inference interface without requiring external structural conditioning. Comprehensive evaluations demonstrate that explicitly correcting these localized physics violations improves downstream robot execution from generated videos. On held-out AgiBot conditions, RobotAPO outperforms the strongest controlled internal baseline in physical consistency by 6.8% hard score and 10.0% soft score. Crucially, in real-robot replay, it translates these physical-consistency gains into a 37.4% relative improvement in task success over the strongest controlled internal baseline.

    embodiedmanipulationembodied agent
  178. arxiv:2610.09451 · cs.RO
    TempoBridge: Language-Guided Tempo Control for Vision-Language-Action Policies
    Yeonseo Lee, Hyosup Shin, Guebin Hwang, Sungho Jo

    Vision-Language-Action (VLA) models are effective at understanding what task to perform, but provide limited control over how it should be executed, such as moving quickly or slowly. We introduce TempoBridge, a lightweight framework that uses frozen VLA representations to modulate actions according to tempo cues in the instruction at each task phase, without additional tempo-conditioned robot demonstrations or tempo-specific base-policy fine-tuning. TempoBridge extracts tempo cues from contextual VLM representations, aligns them with task progress through a causal phase router, and modulates nominal motion commands during execution. Across LIBERO tasks, TempoBridge improves Tempo Success Rate from 52.6% to 89.7% under canonical tempo instructions while retaining high task success. It also preserves near-baseline performance when no tempo cue is present and generalizes to unseen tempo expressions without additional training. Experiments on a physical robot further demonstrate language-conditioned tempo modulation in real-world manipulation.

    vision-language-actionvlamanipulationlibero
  179. arxiv:2610.09450 · cs.AI
    Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-Tuning
    Hanqiu Li Cai, Chema Garabito

    Pixel-space diffusion models avoid the lossy VAE of latent models, which suggests an advantage on downstream tasks where fine-grained detail matters. We test this claim along both routes to a pixel-space backbone. We pretrain Iris-3B, a 3B-parameter pixel-space text-to-image transformer, from scratch through a $256\to512\to1024$ curriculum, after first ablating the prediction target and representation alignment at $256^2$ to decide what to scale. We also convert a pretrained latent model, FLUX.2 Klein base 4B, to pixel space. We fine-tune both families for monocular depth estimation and for image restoration/super-resolution. We find no significant improvement from using a pixel-space generative prior. Fine-tuned for depth with one matched direct-regression recipe, Iris-3B is level with the latent FLUX.2 Klein and the converted pixel FLUX.2 Klein falls behind it, and on $4\times$ DIV2K restoration neither pixel model beats a latent FLUX.2 Klein fine-tune, the converted one trailing it slightly. We document the recipes, the failure modes and the remaining confounds behind this negative result. Nevertheless, Iris-3B shows that pixel-space pretraining with the pixel-transformer (PiT) head of PixelDiT scales to 3B parameters and to text-to-image quality competitive with latent models, matching Qwen-Image on OneIG under the official evaluators at $1024^2$. We release its weights and training code in the hope that they help pave the way for further work on pixel-space generation.

    evaluator
  180. arxiv:2610.09446 · cs.AI
    Arctic Questions, Missing Answers: A Dataset and Benchmark for LLM Abstention in Arctic Science
    Benjamin Wilcox, Dawei Gao, Pradeeban Kathiravelu, Douglas Causey +2

    Large language models (LLMs) should abstain from scientific multiple-choice questions when no option is valid, but frequent abstention alone does not demonstrate sensitivity to answer availability. We introduce ArcticQA, a dataset of 194 questions derived from primary Arctic research, with automated checks of answer support and distractor contradiction against source evidence. We further develop ArcticAbstain, a paired benchmark comparing answer-present and answer-absent conditions, with the correct answer replaced by a distractor in the latter and an explicit abstention option in both. We evaluate eight models from the Gemini, Claude, and ChatGPT families at high reasoning effort, with three trials per condition, yielding 9,312 recorded responses. Answer-present abstention rates range from 0.0% to 63.0%, whereas replacing the correct answer increases abstention by 5.05 percentage points on average. These findings highlight substantial baseline differences and the need to evaluate abstention frequency and responsiveness jointly. The dataset and benchmark are available at https://github.com/BenWilcox8/arctic-qa.

    benchmark
  181. arxiv:2610.09427 · cs.RO
    Event-Aligned Visual Action Reasoning for World Action Models
    Xiaomeng Yang, Yushu Wu, Yi Gao, Yuhao Lei +3

    World-Action Models (WAMs) utilize future visual prediction as an intermediate reasoning process to guide action generation. However, existing WAMs typically structure visual imagination according to predefined temporal intervals, without explicitly accounting for the different roles of task-critical interactions and connecting transitions. We argue that effective visual foresight should align directly with task-relevant interactions and their corresponding reasoning demands. To this end, we introduce an event-aligned visual action reasoning framework that organizes visual-action prediction around interaction events. Through event-aligned visual-action supervision, WAM learns to generate event-aligned visual context in each imagined rollout, placing greater emphasis on critical state changes that inform action generation. This shapes the visual reasoning granularity according to the underlying interaction dynamics, with detailed reasoning around task-critical events and coarser progression through connecting transitions. Furthermore, we introduce an execution validity head that identifies the valid portion of each predicted action sequence, avoiding redundant actions during chunked inference. Experiments demonstrate a 10.26 percentage point improvement in DOMINO success rate over baseline and competitive performance on RoboTwin 2.0. It also transfers from DOMINO Level 1 to Levels 2 and 3 without target-level adaptation.

    robotwin
  182. arxiv:2610.09426 · cs.AI
    RSI-Forge: From Research Papers to Environments for Recursive Self-Improvement
    Renxiong Wang, Darvin Yi, Abril Herrlein, Anas Mahmoud +15

    Environments are the foundation of recursive self-improvement: they provide the problems agents work on and the feedback used to evaluate progress. Yet constructing challenging research environments with reliable evaluation still depends on domain experts, limiting their scale and disciplinary coverage. We introduce RSI-Forge, a multi-agent pipeline that turns published papers into executable environments for self-improvement. Three agents coordinate construction, reproduction, and review to produce tasks with automated evaluators; each paper's method is independently reimplemented to establish a baseline score. We present 210 environments across 18 fields, including 90 reviewed by independent human domain experts. Both experts and agent judges give high ratings to the potential for improving the provided starting solutions and the evaluators' ability to distinguish solution quality, whereas experts are more critical of shortcut resistance, faithfulness to the source paper, and whether a single idea can exhaust a task. To validate their use for repeated improvement, we evaluate four models over 3 successive attempts on 120 environments, with each attempt inheriting prior code and notes while model weights remain fixed. At least one model improves after the first attempt in 84% of environments. Models also outperform the reproduced paper methods in 68 of the 120 environments, demonstrating room for gains beyond these baselines. Transcript analysis identifies work beyond parameter tuning in 95% of these successful attempts. Analysis of the resulting trajectories shows that models scoring lower on these tasks explore less, more often accept gains smaller than the reported standard error, and rely more heavily on tuning to the development set. RSI-Forge provides a scalable approach to constructing research environments for training and evaluating self-improving agents.

    agentmulti-agentself-improvingself-improvementevaluator
  183. arxiv:2610.09412 · cs.CL
    Finding the Right Balance: Relevance and Diversity in LLM Retrieval
    Guillaume Brouillette, Faustin Kagabo, Usef Faghihi, Nadia Ghazzali

    Retrieval diversification is widely available in retrieval-augmented generation (RAG) frameworks, yet prior studies disagree on whether it improves retrieval and answer quality. We show that its effectiveness varies primarily with candidate-pool redundancy, in a pattern consistent with the number of distinct evidence pieces a query requires. Using controlled near-duplicate injection and production-style overlapping chunking, we find that diversification harms relevance, evidence coverage and answer quality on clean pools, but becomes beneficial on multi-evidence tasks when redundancy causes nearest-neighbor retrieval to select repeated passages. We therefore introduce a query-adaptive rule that diversifies only when the effective number of distinct documents in the nearest-neighbor top-$k$ selection falls below the query's evidence requirement. Computed from existing embeddings, the rule captures most of the achievable gain, transfers across datasets and encoders and automatically reduces to nearest-neighbor retrieval for single-evidence queries. We also introduce RNG-Score, a geometric reranker with an exact nearest-neighbor fallback whose margin indicates duplicate structure. Overall, we conclude that diversification should be used selectively, based on observable redundancy and evidence requirements.

    retrieval-augmented
  184. arxiv:2610.09400 · cs.AI
    TutorLoop: Regulating Student Learning Behaviors via Sensor-in-the-Loop Generative Feedback
    Songlin Xu, Xinyu Zhang

    We present TutorLoop, a sensor-in-the-loop system that regulates student learning behaviors by delivering adaptive feedback based on real-time cognitive states. Unlike prior large language model (LLM) tutors that directly depend on scenario-specific content, TutorLoop operates on sensor-derived signals captured via webcams. Moreover, unlike direct cognitive-to-feedback mappings that are short-sighted, the system employs a deep reinforcement learning (DRL) agent to optimize the feedback type across the entire learning process. Finally, another LLM tutor refines feedback into human-like, context-aware messages. We evaluate TutorLoop in a large-scale user study (N=187), where a model trained offline is directly applied to a new learning task without retraining. Results show that TutorLoop provides less frequent yet more effective interventions, improving attention, reducing workload, increasing engagement, and ultimately enhancing learning outcomes. These findings highlight the potential of closed-loop, sensor-driven feedback for scalable human-AI integrated systems to support learning.

    agent
  185. arxiv:2610.09396 · cs.CL
    ARCS: Towards Precise Text-to-SQL via Structured Disambiguation
    Yihao Hu, Yanlin Feng, Naoki Otani, Nikita Bhutani

    As text-to-SQL systems move beyond demonstrations toward real-world deployment, ambiguity in user questions becomes a primary source of errors. Such ambiguities are often subtle, domain- or data-specific, and can silently cause system outputs to deviate from the user's true intent. Ambiguity is traditionally addressed through conversational clarification, which is often inefficient, cognitively demanding, and poorly aligned with real-world user workflows. We propose structured disambiguation, a new paradigm in which ambiguity is resolved through explicit, constrained interactions rather than free-form dialogue. We construct ARCS (Ambiguity Resolution Corpus for SQL), the first text-to-SQL benchmark featuring naturally occurring, unconstrained ambiguities over real-world databases, with complete annotations of all valid ambiguity points, interpretations, and SQL queries. Experimental results show that text-to-SQL remains challenging in the presence of ambiguity: gpt-6-sol achieves only 51% end-to-end execution accuracy, and no open-source model exceeds 27%.

    benchmark
  186. arxiv:2610.09377 · cs.AI
    From Plausible Hierarchies to Useful Taxonomies: Evaluating Agentic Harnesses on Customer Feedback
    Prabhath Chellingi, Raviraja G, Viraj Bagal

    Taxonomies are the symbolic representations through which AI systems organize evidence, aggregate patterns, and answer questions over large document collections. Over customer feedback, the category tree decides how every record is counted and routed, which problems get seen, and which team owns them. Agentic harnesses now make it easy to generate a plausible-looking hierarchy, and such trees are checked today with generic, individually scoped checks: each name fits its description, sits under the right parent, and stays distinct from its siblings. We ask a more operational question: when is a generated hierarchy actually useful as a production taxonomy? We build six taxonomies over two proprietary feedback corpora (1,940 and 5,000 records): for each corpus, a production reference and two repeated runs of the same harness under identical inputs. All six pass every generic naming and structure check, and a deeper product-coverage check even prefers the generated trees. Yet in every generated tree at least 97.7% of leaf names merely restate an ancestor's name (13.9% and 2.9% in the references), and in one, three of every four records fall under multiple top-level categories. We introduce two families of whole-tree metrics: structural discriminators test whether a tree's shape was learned from the data or imposed by its generator; team partitionability tests whether branches split feedback into groups teams can own. Trees the generic checks rate as equally correct differ by 27 percentage points in cross-branch leakage, and only one of the two beats a random split. Surface plausibility is an insufficient measure of taxonomy quality: evaluation must measure the whole tree as well as each node.

    agentic
  187. arxiv:2610.09374 · cs.AI
    DUDA-Bench: Benchmarking LLM Agents on Multimodal Data-Driven Urban Diagnosis
    Yizhi Song, Hang Ni, Weijia Zhang, Hao Liu

    Urban diagnosis integrates heterogeneous observations to identify urban problems, localize affected areas, and investigate contributing factors, informing evidence-based urban planning and management. However, its reliance on labor-intensive, case-specific expert workflows limits scalability and reuse, motivating the exploration of agent-based execution. To evaluate this capability, we introduce DUDA-Bench, a hierarchical and interactive benchmark that formalizes data-driven urban diagnosis as a multi-stage agent workflow. It comprises 86 atomic and 22 workflow tasks spanning four analytical stages, grounded in multimodal data from 12 cities covering five urban problem types. Evaluations of seven backbone models and five agent systems reveal a substantial gap between isolated analytical competence and end-to-end diagnosis, with system benefits varying across backbones. Trajectory analysis shows that unresolved evidence gaps propagate across stages, while successful recovery involves revising assumptions and actions using feedback. These findings highlight limitations in coordinating analytical capabilities across stages, particularly adaptive planning, evidence integration, and verification. More broadly, DUDA-Bench provides a framework for translating expert analytical workflows into hierarchical agent tasks and process-aware evaluation, supporting systematic assessment of end-to-end analytical capabilities.

    agentllm agentagent systemhierarchical agentbenchmark
  188. arxiv:2610.09371 · cs.AI
    The Confidence Game: Strategic Miscalibration in Human-AI Delegation
    Raghu Arghal, Saswati Sarkar, Shirin Saeedi Bidokhti

    Calibrated uncertainty quantification is essential to ensuring AI agents are trustworthy and reliable. However, when agents seek to maximize user engagement or revenue, confidence reports may be strategically distorted, detracting from their informativeness. We formalize this problem in the Confidence Game: a repeated signaling game with imperfect monitoring in which an agent of unknown honesty and ability reports its confidence, and a user decides whether to delegate the task or complete it herself. The agent manages the tradeoff between manipulating signals and maintaining its reputation. We characterize the Markov Perfect Bayesian Equilibria of the two-period game and show that honest reporting is not an equilibrium, inflation is the unique best response once the agent is sufficiently myopic, and under-reporting requires that the user believe honesty to be a minority. We then place an LLM in the agent role, supplying it with its true probability of success so that any gap between what it knows and what it reports is attributable to incentives rather than to miscalibration. The model claims high confidence on 56% of tasks it has been told it will probably fail. This persists on real tasks, where it must estimate its own accuracy and causes miscalibration to increase while the agent's signal becomes less informative. Furthermore, we find that the LLM agent's decisions are coherent, but it systematically underestimates both how likely the user is to delegate and how secure its reputation is, resulting in less extreme behavior. Pricing the agent's reporting rule, we find that it destroys 68% of the gains from delegation, of which 71% is information the report no longer carries and no amount of user sophistication recovers. Overall, we establish confidence reporting under delegation as a strategic problem and provide a tractable basis for modeling, analyzing, and testing agent behavior.

    agentai agentllm agent
  189. arxiv:2610.09369 · cs.RO
    Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise Assignment
    Xiao Zhang, Yuxin Chen, Zhixuan Liang, Guojian Zhan +4

    When diffusion policies were first introduced, they were expected to recover multi-modal action distributions. However, we find this expectation does not always hold, as diffusion policies often collapse to a single modality even when we guarantee the balance of dataset modalities and exact within-batch symmetry. Our analysis indicates that independent action-noise pairing contributes to this failure by increasing mixing and crossing among diffusion paths, which can produce averaged denoising responses and suppress modality-specific behavior. This issue is especially severe in robot planning, where action spaces are dense and low-dimensional, significantly increasing such mixing and crossing. To alleviate this problem, we propose Immiscible Diffusion Policy, a label-free training-time add-on to diffusion policy that uses action-noise assignment to preserve relatively distinct noise-to-action routes without modifying the policy architecture or inference procedure. Across five simulated and two real-world humanoid manipulation tasks spanning state, RGB, and point-cloud observations, our method significantly improves the policy's preservation of action modalities while maintaining strong task performance. It increases the proportion of the non-dominant modality by 6.0x-14.6x across three two-modality tasks and recovers demonstrated modalities that are entirely absent from vanilla policy rollouts on both four-modality tasks. These results demonstrate that Immiscible Diffusion Policy provides a simple yet robust approach to preserving action multi-modality in general robot learning tasks.

    manipulationhumanoiddiffusion policy
  190. arxiv:2610.09366 · eess.SY
    Learning Stability of Replay-Based Co-Optimization for Transmission Expansion under Strategic Bidding
    Tomonari Kanazawa, Hikaru Hoshino, Eiko Furutani

    This paper investigates the behavior of learning-based co-optimization for transmission expansion under strategic bidding in electricity markets. In this framework, transmission capacities are updated while market participants simultaneously learn their bidding strategies through deep reinforcement learning, resulting in coupled and non-stationary learning dynamics. We show that transient policy degradation of bidding agents can generate inconsistent cost-capacity samples, which bias the transmission-capacity update and prevent the co-optimization process from converging to the desired solution. To mitigate this, replay-based capacity updates with nearest-neighbor filtering are introduced to exclude inconsistent samples from the update data. We then analyze a new oscillatory behavior that appears when the replay memory is enlarged. Numerical results on the IEEE 30-bus system demonstrate that enlarged replay memories improve robustness against transient policy degradation but can introduce a temporal lag, leading to oscillations unless the capacity-update learning rate is appropriately reduced. These results reveal the trade-off between replay-memory size and learning rate and provide practical guidelines for stable co-optimization.

    memory
  191. arxiv:2610.09361 · cs.AI
    From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QA
    Xiaotian Qiu, Kairui Liu, Shi Chenyi, Jinyuan Deng +2

    Retrieval-Augmented Generation (RAG) is widely used to ground answers in documents. For complex technical documentation, however, the primary bottleneck is often not model reasoning but a mismatch between a query and the way knowledge is organized for retrieval. This mismatch is pronounced in Electronic Design Automation (EDA) documentation, where the information needed for an answer is scattered across heterogeneous yet tightly coupled artifacts. We therefore redesign the basic retrieval unit of RAG. Instead of operating on isolated chunks or binary relations, we collect typed artifacts into EDA functional units. Each unit is recorded as a hyperedge with links to its source chunks. We then train an encoder to align queries with functional units and combine unit retrieval with direct chunk retrieval. After mapping the selected units back to their sources, a unified reranker chooses the evidence given to the generator. On the newly constructed EDADocEval-QA dataset, our method improves ROUGE-L by 37.1% over Chunk RAG and 55.6% over the strongest graph baseline. On the public ORD-MMBench benchmark, it improves ROUGE-L by 30.0% over the strongest baseline. These results support function-aware evidence organization in the evaluated EDA documentation settings.

    retrieval-augmentedragbenchmark
  192. arxiv:2610.09360 · cs.AI
    TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence Reasoning
    Ruochi Li, Jianzhe Lin, Haoxuan Zhang, Haihua Chen +3

    Real-world documents distribute evidence across text, tables, figures, and captions within complex page layouts. Answering complex questions over such documents therefore requires more than retrieving relevant passages: systems must recover the evidence topology that connects heterogeneous evidence units. Existing GraphRAG evaluations remain largely text-centered, while multimodal document RAG benchmarks assess cross-modal retrieval and generation without directly evaluating recovery of the intended evidence topology. We introduce TOPOGRAPHRAG-BENCH, a layout-grounded benchmark for multimodal evidence reasoning in GraphRAG, comprising 2,024 questions over 201 long, visually rich documents. Questions are constructed bottom-up from text, figure, and table evidence units under three controlled topologies: single-hop retrieval, bridge-chain reasoning, and multi-source synthesis. To ensure that questions preserve their intended structure, we apply counterfactual validation for shortcut resistance, modality necessity, and evidence necessity. We evaluate text-only GraphRAG, page-level visual retrieval, and multimodal GraphRAG systems using retrieval, generation, and topology-aware reasoning metrics. Multimodal GraphRAG systems achieve the strongest overall performance, but still fail when visual-textual evidence alignment or multi-unit composition is incomplete. Text-only GraphRAG struggles when key dependencies are grounded in figures or tables, while page-level visual retrieval lacks the fine-grained structure needed for topology recovery. These findings motivate GraphRAG systems that move beyond text-derived entity relation graphs to explicitly model document layouts, cross-modal evidence alignment, and the reasoning roles of evidence units. Code and data are available at https://richardlrc.github.io/TopoGraphRAG-Bench/.

    ragbenchmark
  193. arxiv:2610.09358 · cs.RO
    COOL: Curiosity-Driven Object Ownership Learning for Personalized Robotic Assistance
    Samira Huber, Ruben Hammele, Sören Pirk

    Robots are increasingly expected to provide personalized services in everyday environments. To do so, they must ground natural-language commands such as "Where is my backpack?" or "Find my bottle" and execute them by reasoning about object instances, people, locations, and ownership. This is challenging because ownership is rarely labeled explicitly and must be inferred from long-term, behavioral evidence of human-object interactions. To address this, we present COOL, a novel robotic framework for autonomously learning object ownership from everyday observations and maintaining a long-term spatial memory of its environment. To keep its memory current, COOL uses an agent-based curiosity-driven data collection strategy that guides the robot toward the most promising locations to gain information and refresh stale observations. Offline experiments, ablation studies, and real-world evaluations show that COOL can infer ownership relations from real-world interactions and use this knowledge for ownership-conditioned navigation and task execution.

    memory
  194. arxiv:2610.09355 · cs.AI
    Multimodal LLMs Can Learn to Read Brain Signals: A Vision--Language Model for Unified Multi-Task EEG Decoding
    Parastoo Azizeddin, Omid Sharafi, Maryam M. Shanechi

    Learning EEG representations that generalize across cognitive tasks, subjects, and recording conditions remains a key challenge in electroencephalography (EEG) decoding. Recent advances in foundation models have improved EEG decoding performance, yet a fundamental open question remains: how to effectively interface neural signals with these models to enable multi-task learning across datasets. To investigate this question, we introduce BraVista, a visual-language framework that encodes multichannel EEG signals as structured images and enables multi-task learning through instruction-conditioned vision-language models (VLMs). Our approach relies on continued post-training of a general-domain VLM, leveraging its visual and linguistic priors to adapt to neural signals without a separate large-scale EEG-specific pretraining stage. We evaluate BraVista on four datasets spanning sleep staging, emotion recognition, cognitive workload classification, and abnormal EEG detection, showing strong performance across these tasks. Further analyses show that the choice of EEG-to-image representation is critical to performance. Moreover, through controlled perturbations of the EEG signal, we observe a gradual performance degradation under increasing noise, suggesting that the model relies on EEG-relevant information rather than superficial visual patterns. Together, these findings establish structured visual representations as an effective and scalable interface between neural signals and general-domain foundation models for unified multi-task EEG decoding.

    post-training
  195. arxiv:2610.09348 · cs.AI
    Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QA
    Yufeng Li, Shuxin Li, Zhenhua Xu, Junxian Li +6

    LLM agents that interact with a user across many sessions accumulate histories that exceed their context window, so they store past interactions in an external memory and answer each question from a small set of retrieved records. Existing memory systems rank records by lexical or embedding relevance, yet the top-ranked memories can each be relevant while jointly omitting a complementary fact that the answer requires, especially for multi-session and temporal questions. Drawing on the distinction between relevance and sufficiency in legal evidence scholarship, we recast memory retrieval as constructing a sufficient memory set. To operationalize this view, we introduce a blinded LLM judgment over the retrieved set, together with Gold Hit and Turn Hit as evidence-coverage proxies. We then propose Budgeted Flat Reconstruction (BFR), which builds sufficient sets over a fixed flat memory store in two stages. Specifically, we first apply Formal Concept Analysis for Memory Selection (FCA-MS) to decompose the question into information requirements and select a compact candidate subset that jointly covers them. Then, we repeatedly acquire unseen records through deeper text search or complementary entity and session views, stopping when the budget is exhausted. Experiments on LoCoMo and LongMemEval-S show that BFR outperforms same-store adaptations of recent agent-memory systems in both answer quality and evidence coverage. Specifically, on LongMemEval-S it raises judged accuracy from 72.4% to 82.2% and Turn Hit to 91.4%.

    memoryexternal memoryllm agent
  196. arxiv:2610.09335 · cs.AI
    SearchWorld: Spatial Value-Grounded Imagination for UAV Object Search via World Models
    Yatai Ji, Zhengqiu Zhu, Yong Zhao, Yue Hu +4

    Autonomous unmanned aerial vehicle (UAV) object search involves a closed loop of perception, decision-making, and action under partial observability. Urban environments pose several challenges: large search areas and narrow egocentric views limit coverage, dense 3D geometry constrains safe motion, and open-world instructions require identifying a specific target among distractors. Many existing methods mitigate partial observability through explicit maps or memory representations, yet remain largely reactive, reasoning over past observations without explicitly predicting future states. World models enable prospective reasoning through imagined rollouts. However, image-generating world models can incur high inference latency, while spatially grounded planning remains challenging for latent world models. We propose SearchWorld, a recurrent state-space world model that connects explicit spatial memory with value-guided imagination. The model maintains BEV exploration and obstacle memory and decodes a task-aware spatial value layer to guide search. A cognition-action network uses this learned spatial value prior to improve the policy through imagined rollouts, without training a separate scalar critic. Training progresses from world-model learning to expert imitation and imagination-based exploration refinement. On UAV-ON, SearchWorld improves the success rate to 23.8% (19.5% for the strongest published agent) and raises oracle success to 35.5%, while remaining robust on unseen scenes (19.9% success rate). By grounding imagination in explicit spatial representations, SearchWorld enables UAV agents to plan prospectively rather than react.

    world modelimagination-basedmemory
  197. arxiv:2610.09315 · cs.RO
    ClimbLab: MATLAB Simulation Platform for Legged Climbing Robotics
    Kentaro Uno, Warley F. R. Ribeiro, Yusuke Koizumi, Keigo Haji +3

    This paper presents an open-sourced MATLAB simulation and analysis platform dedicated to legged climbing robots. This simulator enables the design of any limbed robotic system as an articulated multi-body with a floating base and simulates it walking and climbing in an arbitrary environment. The main variable environmental parameters are inclination, gravity, and ground stiffness, and any point cloud can be installed as the terrain map. Furthermore, the simulator employs a rigid body dynamics engine. This paper first describes the simulator structure, and the computational flow and next presents the representative simulation examples where quadrupedal robots assumed gripping on the wall or climbing on the steep slope.

    quadruped
  198. arxiv:2610.09309 · cs.RO
    Predicted Futures Are Not Enough: Learning Executable Goals for Robot Manipulation
    Tzu-Yu Chuang, Ching-Hsiang Chang, Yi-Hsiu Lee, Yi-Ting Chen +2

    Generative world models provide rich predictions of how manipulation scenes may evolve toward task objectives, yet those futures do not directly expose the compact task variables required by control. When training supervises future prediction alone, terminal goal accuracy is not an explicit learning objective, even when geometric recovery is available. We present Entity-Level Goal Readout, a learned prediction-to-execution interface that makes the executable terminal goal an explicit output of a 3D trace world model. It combines object-centric pose prediction with translation grounded in observed depth to produce a compact goal in SE(3). A shared Pose-Native Executor consumes this fixed goal with online object-pose feedback for closed-loop control without rerunning the world model. Across five manipulation tasks, the pipeline achieves a mean success rate of 79.69%. Goal diagnostics directly measure terminal goal accuracy, while controlled translation perturbations characterize how execution degrades under goal error. Zero-shot deployment on a Franka arm achieves 73.33% success on nominal StackCube, 66.67% with distractors, and 75.00% on PickPlate with a target unseen during policy training. These results support treating the prediction-to-execution interface as an explicit learned component of world-model planning rather than incidental post-processing in the control pipeline itself. Project page: https://claire0730.github.io/executable-goals/

    manipulationfrankaworld model
  199. arxiv:2610.09305 · cs.RO
    Kuration SDK: Addressing the Virtual2Real Gap via Data Curation
    Nirmit Desai, Eric Song, Mayank Sengupta, Tejal Bedmutha +3

    Benchmarks for measuring the quality of action-conditioned world models are still evolving and shifting away from visual similarity-based metrics to action-semantic and physically-grounded metrics. However, for domain and task-agnostic action-conditioned world model training, existing benchmarks provide a limited signal. By training and evaluating diffusion world models on CounterStrike gameplay data, we confirm that qualitative playability does not correspond with metrics such as FVD, LPIPS, and JEDi. We term this the Virtual2Real gap. We posit that, in lieu of reliable benchmarks, curating raw gameplay data and measuring a variety of diagnostic properties provides a more robust signal to bridge the gap, before the training even begins. We present several curation strategies and a general-purpose kit for physical AI data curation called Kuration SDK, which is being open-sourced with this paper. The SDK was instrumental in uncovering the root cause of the virtual2real gap in a specific case: why two world models trained on identical gameplay map, action and state distribution, behaved very differently when played in spite of having very similar LPIPS and FVD scores. Thus, Kuration SDK has the potential to uncover the root causes of Virtual2Real gap in specific datasets and accelerate development of sample-efficient training datasets.

    world modelaction-conditionedbenchmark
  200. arxiv:2610.09302 · cs.RO
    Adaptive Risk-Certified Event-Triggered Replanning for Dynamic Navigation
    Richie R. Suganda, Bin Hu

    Safe navigation in dynamic environments requires robots to plan under obstacle predictions whose errors are uncertain, non-stationary, and can induce rare but safety-critical failures. Existing control-barrier-function safety filters can reject immediately unsafe controls, but they provide little guidance on when the current finite-horizon planning mode itself is becoming unsafe as prediction uncertainty evolves. We propose Conformal Event-Triggered Risk-Certified Replanning (\emph{CERT-Replan}), a framework that uses calibrated barrier risk as an early-warning signal for replanning. CERT-Replan calibrates horizon-indexed obstacle-prediction residuals online and uses the resulting uncertainty radii to evaluate dynamic-obstacle safety margins. A one-step safety filter protects the next applied control, while a horizon-level risk monitor evaluates the upper-tail CVaR of predicted barrier-violation losses along the current MPC rollout. When this risk exceeds an allocated budget, CERT-Replan rejects the current planning mode and selects a lower-risk alternative, such as a different speed profile, corridor, or homotopy class, rather than repeatedly correcting the same nominal plan. In a non-stationary benchmark, CERT-Replan achieves an \(83.3\%\) collision reduction relative to the safety-filter-only baseline \textcolor{black}{and a \(77.8\%\) reduction relative to simple replanning triggers}, while reducing average safety-filter intervention by \(32.4\%\). \textcolor{black}{With Trajectron++, CERT-Replan achieves \(96\%\) collision-free operation. Hardware experiments and onboard runtime profiling demonstrate computational feasibility.}

    benchmark
  201. arxiv:2610.09296 · cs.AI
    The AI Evaluation Ecosystem
    Yash Dave, Sang T. Truong, Serena Wang, Sanmi Koyejo

    AI evaluation shapes the decisions of model providers, users, funders, and regulators. We argue that designing valid benchmarks requires contextualizing design choices in the dynamics of this ecosystem of actors. We develop a simulation architecture that combines rule-based market dynamics with LLM-driven strategic actors, building on advances in Generative Agent-Based Modeling (GABM). We model benchmarks, consumer needs, and provider capabilities as vectors over a six-dimensional capability space (reasoning, coding, knowledge, safety, communication, agentic), with structural information partitions across actors. As a case study, we apply this stylized simulation to explore benchmark holdout design. We find that moving from public benchmarks to private holdout benchmarks shrinks the gap between benchmark scores and user satisfaction on most benchmarks but widens it on a few, depending on where holdout weights shift scoring credit. We stress-test our findings at both the instrument and case-study level, drawing on the V&V framework of Sargent (2013) and GABM-specific evidence criteria. Beyond holdout design, our simulation is a hypothesis-generating sandbox for studying how evaluator and policy choices, in turn, reshape the ecosystem.

    agenticbenchmarkevaluator
  202. arxiv:2610.09294 · cs.AI
    RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment
    Tianruo Rose Xu, Jiawei Ren, Yichi Yang, Zhaoxu Zheng +1

    Rapid progress in AI agents has brought growing attention to agent safety, with extensive evaluation focused on digital environments. As agents move into the physical world, embodied safety becomes increasingly important: failures can cause human injury and costly hardware damage. Beyond selecting safe actions, embodied agents must also operate under real-time constraints: the physical world does not pause while an agent reasons. As pedestrians move and vehicles approach during inference, an action that appears safe at observation time may become unsafe before execution. Real-time embodied safety therefore depends on both decision quality and decision latency. We introduce RT-SAFE, a simulated urban benchmark for evaluating embodied-agent safety under real-time constraints. RT-SAFE combines navigation tasks with moving actors, environmental hazards, and traffic rules, while allowing the world to evolve throughout inference and action execution. Across eight VLMs, agents achieve high task completion yet almost never complete safely: in the hardest setting, only 0.7% of episodes finish without a safety event. More strikingly, matched static and real-time evaluations yield task completion rates of 91.3% and 94.1%, respectively, while real-time execution increases collisions by $12.3\times$. These results reveal that standard task success can mask substantial safety failures, and that decision latency itself can become a source of physical risk. Finally, we show that RT-SAFE can support offline RL training and substantially reduce collision rates while achieving strong task completion.

    embodiedagentai agentembodied agentbenchmark
  203. arxiv:2610.09291 · cs.RO
    Co${}^{2}$Skill: Whole-Body Control via Skill Composition for Long-Horizon Human-Environment Interaction
    Jeonghwan Kim, Hyeonwoo Kim, Hanbyul Joo

    Achieving human-level dexterity in complex, unstructured environments requires the seamless integration of whole-body scene interaction and dexterous object manipulation skills. While existing physics-based controllers generate physically plausible behaviors in each domain, they largely address these two capabilities independently. In this paper, we present Co${}^{2}$Skill that integrates scene interaction and dexterous manipulation through a unified policy formulation. Built on a pretrained motion prior, the policy uses task and phase dependent observation masks to select information relevant to the current interaction goals. We introduce a goal-conditioned loco-manipulation curriculum that combines partial reference guidance for precision with exploration from varied initial states while allowing goal-directed execution beyond the demonstrated trajectories. We further introduce a cross-task curriculum that jointly trains individual skills and selected task sequences, preserving physical states across task boundaries and maintaining grasps during subsequent scene interactions. Together, these support sequential task execution and simultaneous scene interaction with object manipulation. We evaluate sitting, standing, climbing, stair traversal, and goal-directed manipulation, together with sequential execution and with random different conditions. Additionally, we demonstrate skill compositions in indoor environments, illustrating their integration within the same control formulation.

    manipulationdexterouswhole-body controlgrasp
  204. arxiv:2610.09285 · cs.RO
    LeCuration: A Tiny World Model as a Data Curation Multi-Tool
    Mayank Sengupta, Nirmit Desai, Eric Song, Kunal Sawarkar

    Many applications of physical AI run within finite or closed physical worlds with a limited set of physical laws governing object behavior. Examples include robots working in a warehouse and agents moving around in a video game. In order to better organize, filter, and curate data for physical AI applications, we propose a new approach centered on the unique settings and physical laws of individual datasets. We train LeCuration, a small world model intended to serve as a data curation tool for a separate, larger downstream model. To build this model, we choose LeWorldModel (LeWM)as our latent encoder and predictor, adding a diffusion transformer (DiT) decoder to add visuals to autoregressive gameplay rollout. We find that the embeddings of this model can be used as an anomaly detection signal and as a content-based clustering heuristic, and that auto-regressively predicting the game state with this model allows us to qualitatively check for action-state consistency. This paper presents a qualitative, proof-of-concept case study on CS:GO gameplay data; we do not yet report quantitative curation metrics or downstream training results, which we identify as the key next step.

    world model
  205. arxiv:2610.09283 · cs.RO
    LACE-CRAFT: Robot Co-Design with Actor Inheritance and Blackboard Collaboration
    Yuhan Wen, Jiawei Wang, Qixuan Zhang, Yusen Qin +1

    Robot co-design couples morphology search with policy learning, yet training every new design from scratch discards acquired control experience. We present LACE-CRAFT, which compares continued learning on the current robot with policy adaptation to new morphology-reward pairs. LACE resumes the incumbent's full learning state and initializes compatible challengers with its actor parameters and observation statistics. A fixed task metric selects among both branches and the frozen incumbent. CRAFT coordinates Feedback, Morphology, Reward, and Integration roles through shared experimental records and behavioral replays to generate and cross-review paired proposals. A generative extension converts generated meshes into editable articulated models with configured joints, actuator interfaces, and consistently updated simulation assets. Across five locomotion benchmarks, mean scores over three evaluation seeds are 6.4-91.9% higher than D2C. Both methods train 30 new morphology-reward pairs over five rounds; LACE additionally uses four continuation training units. Five-task ablations examine policy inheritance and replay-derived feedback. A fabricated prototype demonstrates indoor walking and illustrates the geometry-to-hardware workflow.

    benchmark
  206. arxiv:2610.09266 · eess.SY
    Cooperative Dueling DQN SAC Learning for Energy Efficiency in Dynamic OWC Networks
    Walter Zibusiso Ncube, Ahmad Adnan Qidan, Taisir El-Gorashi, Jaafar M. H. Elmirghani

    Growing wireless traffic is increasing pressure on the congested radio-frequency spectrum. Optical wireless communication (OWC) provides a complementary solution by using the abundant unlicensed optical spectrum. However, indoor OWC networks are dynamic: users move, enter or leave the network, and subscribe to different services. Poorly coordinated resource allocation can consequently waste subcarriers, require excessive transmission power and cause frequent AP reassignments. Energy efficiency (EE), defined as the total delivered data rate divided by the total network power consumption, therefore requires the serving AP, number of allocated subcarriers, and transmission power to be jointly adapted while maintaining QoS. Optimising these in a dynamic time series, multi-service OWC environment produces a complex sequential EE optimisation problem. To address this problem, this work proposes Dual-Agent Resource Allocation using Deep Reinforcement Learning (DARA-DRL). DARA-DRL combines a branching duelling deep Q-network for association and subcarrier allocation with a conditional soft actor-critic agent for continuous power control. The agents are coupled through a common reward and a cooperative value update that evaluates each discrete allocation together with its corresponding power decision. Simulation results show that DARA-DRL remains within 5\% of the optimal solution and, compared with state-of-the-art benchmarks, it improves EE by 28.8\% and QoS satisfaction by 10.5\%, while reducing online decision time by 14.5\%. Results demonstrate that agent specialisation simplifies mixed-action learning, and cooperation outperforms independently trained agents.

    agentbenchmark
  207. arxiv:2610.09264 · cs.AI
    Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule Files
    Yupu Wang, Zhengyuan Jiang, Reachal Wang, Neil Zhenqiang Gong

    Modern agentic coding frameworks increasingly rely on community-shared rule files (e.g., AGENTS.md or .cursorrules) to guide autonomous code generation, yet the security risks of this pipeline remain underexplored. To bridge this gap, we introduce the package hallucination attack, where an attacker injects malicious prompts into benign rule files to induce coding agents to replace legitimate dependencies with attacker-controlled packages. To obtain effective malicious prompts injected into rule files, we propose PackHallu, an evolutionary optimization framework that iteratively rewrites these injected prompts using trajectory-level feedback and LLM-guided mutations. Evaluations across multiple benchmarks, LLMs, and agent frameworks show that PackHallu achieves high attack success rates and strong transferability across diverse models and agent combinations. Our findings demonstrate that coding agents are vulnerable to package hallucination attacks, highlighting the urgent need for stronger security safeguards in autonomous coding systems.

    agentagenticagent frameworkbenchmark
  208. arxiv:2610.09254 · cs.RO
    RoboRender: Robot-Oriented Video Generation for Visual Sim-to-Real Transfer
    Huang Huang, Wensi Ai, Ziyu Chen, Youhui Wang +5

    Simulation enables large-scale, low-cost robot data generation, but policies trained in simulation often fail to transfer to the real world due to the sim-to-real visual discrepancies. Existing approaches often rely on intermediate representations, which can discard rich semantic information or require additional perception modules at deployment. We address this visual sim-to-real gap with RoboRender, a framework that converts simulated trajectories into photorealistic RGB videos for policy learning. RoboRender trains a robot-oriented video generation model conditioned on simulated depth videos, language instructions, and robot RGB mask videos, preserving simulator geometry, robot motion, and action labels while synthesizing realistic textures, backgrounds, and distractors. The generated RGB videos are paired with simulator-provided states and actions to train policies for zero-shot real-world deployment. On robot video test sets, our video model outperforms depth-conditioned video generation baselines in generation quality. In real-world experiments across pick-and-place, articulated-object manipulation, and mobile manipulation tasks, policies trained on RoboRender-generated data achieve a 71% average success rate, outperforming raw simulation renderings and conventional visual domain randomization by approximately 7.1x and 3.6x, respectively. We further show that policy performance improves with more generated videos per simulation trajectory, increasing opening-task success by 65 percentage points. These results demonstrate that generative video rendering mitigates the visual sim-to-real gap for zero-shot policy transfer. Project website: https://robo-render.github.io/.

    manipulationsim-to-real
  209. arxiv:2610.09250 · cs.AI
    Efficient Best-of-N policy evaluation for inference-time alignment
    Jonas Schweisthal, Yuxin Wang, Athiya Deviyani, Stefan Feuerriegel +1

    Best-of-N (BoN) is a common inference-time alignment method that selects the highest-scoring response among N samples from a reference model. Evaluating BoN policies from logged data is challenging under sample-only access because standard off-policy estimators require density ratios that depend on unavailable response likelihoods. In this paper, we propose a sample-only framework for evaluating and selecting BoN policies without access to these likelihoods. We show that the order-statistic structure of BoN allows the required density ratios to be expressed through score-rank probabilities that are estimable from samples alone. We then develop a doubly robust estimator of the BoN policy value (BoN-DR) that efficiently reuses a shared auxiliary sample pool across candidate budgets. We establish valid asymptotic inference even under reward estimator misspecification and prove the efficiency of our BoN-DR estimator. Since larger budgets can amplify errors in the score function and lead to reward overoptimization, we derive two selection rules: (i) maximizing the estimated policy value and (ii) maximizing a lower confidence bound on the improvement over the reference policy, which accounts for estimation uncertainty and provides a no-harm guarantee. Across synthetic experiments and GSM8K with multiple reference and reward models, our framework accurately estimates BoN policy values and selects effective sampling budgets.

    policy evaluation
  210. arxiv:2610.09247 · cs.RO
    An Informational Curse of Horizon in Goal-Conditioned Policy Learning
    John L. Zhou, Yuxuan Dong, Jonathan C. Kao

    The difficulty of learning goal-reaching policies is often attributed to a "curse of horizon" that manifests as bias accumulation in temporal-difference backups and noisy advantage estimates. In this work, we identify an additional informational curse of horizon in goal-conditioned policy learning, where increasing the goal relabeling horizon can significantly reduce policy generalization and performance. Through a series of controlled experiments with oracle planners, we decouple the goal horizons sampled during training from those that the policy is asked to reach at test time. Even when evaluated only on a sequence of nearby subgoals, goal-conditioned behavioral cloning (BC) policies suffer from severe, training horizon-dependent performance degradation that is mitigated by reinforcement learning (RL) objectives. We explain this phenomenon as a horizon-dependent decrease in the conditional mutual information between actions and hindsight-relabeled goals, and find empirically that both BC and RL policies trained on longer-horizon goals exhibit a shift in sensitivity from goal to state information, as measured by the policy's input Jacobians. Motivated by this observation, we find that distilling the input Jacobians of short-horizon policies into long-horizon policies yields significant performance gains, especially in combinatorial manipulation tasks. Taken together, our results highlight goal relabeling horizon as an important consideration when learning generalist policies from offline data.

    manipulation
  211. arxiv:2610.09244 · eess.SY
    Beyond Nominal Equilibria: Risk-Averse Multi-Population Mean-Field Games
    Bhavini Jeloka, Siddhartha Ganguly, Panagiotis Tsiotras

    Recent advances in mean-field games and its multi-population variants enable large-scale heterogeneous multi-agent systems to be modeled through representative agents and their associated mean-field distributions. However, existing approaches do not explicitly account for uncertainty in the behavior of other populations. To this end, we introduce a new paradigm: risk-averse multi-population mean-field games, where each population optimizes a worst-case expected reward over dynamically feasible ambiguity sets of mean-field flows of a subset of the other populations. Employing an occupation-measure formulation along with tools from set-valued analysis, we establish, under mild assumptions, several theoretical properties of the multi-population game, including the geometric properties of the ambiguity sets and the existence of a novel risk-averse multi-population mean-field equilibrium. Further, we derive contractivity results of the fixed-point operator under entropy regularization and show that it can be utilized to learn the equilibrium. Finally, we propose a risk-averse fictitious-play scheme and show that exploitability decays to zero, despite the additional nonlinearity introduced by the worst-case objective. We report several numerical experiments to illustrate convergence and risk-averse behavior.

    multi-agentagent system
  212. arxiv:2610.09243 · cs.AI
    We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to Agents
    Kefan Liu, Fengning Ou, Yelin Luo, Jingdi Lei

    Agentic systems use large language models (LLMs) to carry out concrete tasks. Prior work often borrows abstractions such as scheduling, caching or isolation piecemeal from operating systems, so the mechanisms it builds share little common ground, and the shared view of the two forms of agentic system, Workflows and Agents, is limited. We construct an abstract machine that provides both. We treat the LLM as an Oracle and extend a two-stack pushdown automaton with one instruction, which hands the Oracle a whole stack as its query and appends the answer to that same stack. The machine thus performs two computations, the Oracle's and a Turing-complete one that we call the Priestess. A stack that the program only appends to grows autoregressively, as an agent's context does. Two symmetry breakings, S in storage and T in transitions, make a Priestess program the operating system of the programs the Oracle runs, and produce the Agent and the Workflow as the two placements of a task's program. For internally autoregressive Oracles, the two computations synchronize at the end of every answer under certain conditions, and through that synchronization we model caching and analyse scheduling. No guarantee that holds for every Oracle can fix which content crosses between the two computations, but such a guarantee does fix the boundary itself. The construction V fits the machine to a von Neumann computer. To show that it is realizable, we propose ArchNights, an extended RISC-V ISA and a Linux-style operating system implementing the machine by design. ArchNights-SE runs on gem5 as a computer system, becomes an agentic system when it runs an LLM as the Oracle, and will be open source. Agentic systems can then be designed as computer systems are. With a foundation built and a unified view, future work can share invariants and bounds, each with its conditions.

    agentagentic
  213. arxiv:2610.09240 · cs.AI
    Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution
    Wanjing Han, Levi Taiji Li, Mu Zhang, Yue Jiang +1

    Modern web agents built on large vision-language models process webpages, select relevant UI elements, and translate model outputs into browser actions. Existing visual red-teaming approaches use adversarial visual content to manipulate this process. However, they primarily target model inference and do not explicitly account for structured input processing or action post-processing. Consequently, model-level success does not establish control over browser execution and cannot reliably characterize end-to-end agent robustness. To address this gap, we formulate red teaming for vision-grounded web agents as an end-to-end grounding-to-execution problem, and introduce WebMirage, a framework that crafts localized visual perturbations that cause agents to select attacker-controlled content and execute the corresponding browser action across varying webpage renderings. It uses a role-slot abstraction and webpage recomposition to capture competition among webpage elements, and dataflow analysis to align optimization with action post-processing. We evaluate WebMirage across four agent configurations and six VLM backbones on 2,250 tasks covering 13 public websites and a sandbox benchmark. WebMirage achieves an average attack success rate of 91.9%, compared with 17.4% for the strongest baseline, and remains effective against three agent-level defenses.

    agentbenchmark
  214. arxiv:2610.09239 · cs.AI
    The Winner's Curse in LLM Self-Improvement Loops: Selection Noise, Lock-in, and Acceptance Rules
    Litao Hu, Yutong Tang

    Self-improving LLM systems propose changes to themselves and keep those that score better on a small evaluation set. We treat this keep-if-better step as selection under measurement noise, model the correlated errors of the candidates in a single decision, and study empirically what happens when the evaluation set is reused. In runs where Qwen models rewrite their own instructions and every candidate is also scored on 600 held-out items, most proposals after the first are harmful, and the model gives the size of the winner's curse of a generation's best candidate. With a prior from a separate pilot, it matches the average overstatement of first-generation commits in native loops, though not setting by setting. In a pre-registered study, the final selection-set score of greedy loops exceeded held-out accuracy by 13 to 20 points with 16 selection items and by 1 to 5 points with 256. Held-out gains grew with the selection set on TREC but not on GSM8K, and the tested acceptance rules did not beat greedy acceptance over whole runs. Gains measured on the selection set also exceeded held-out gains when a current model refined a competent instruction, and in the validation scores of GEPA and MIPROv2. Scoring the starting and the current instruction on 64 items never used for selection removes the average bias of a loop's reported gain, but single estimates remain off by about 6 points. Self-improvement studies should report held-out gains with their uncertainty.

    self-improvingself-improvement
  215. arxiv:2610.09237 · cs.AI
    Trajectory Abstraction for the Science of Language Agent Behavior
    Tianqiang Yan

    Scientific studies of language agents need behavioral variables that support hypotheses across tasks and models. We formulate this research problem as learning and testing a hierarchy of trajectory abstractions. A concrete recursive procedure first measures role- and phase-indexed events, proposes temporally constrained relations, and tests their stability across conditions. It then constructs episode-level motif variables from selected relations and repeats the analysis on those variables. Explicit measurement functions connect every abstraction level to the original trajectories. Observations and randomized protocol experiments assess the resulting hypotheses, while comparisons between intervention realizations determine whether an abstraction should be retained, refined, or restricted. We derive a finite-depth bound for accepted reductions, identify protocol effects on fixed abstractions, and characterize realization disagreement and composition of abstraction error. A finite-sample test makes projected intervention consistency operational, and constructed examples illustrate motif construction and abstraction refinement. The formulation distinguishes this experimental approach from semantic taxonomies, qualitative theory induction, and behavior-model recovery. It specifies a proposed research procedure for discovering generalizable behavioral hypotheses, with literature-relative novelty assessed separately from model-relative surprise.

    agent
  216. arxiv:2610.09229 · cs.AI
    Conditional Accuracy Profiles: Diagnosing LLM Judges across Deployment Conditions
    Wenqi Li, Bin Liu, Mindi Ruan, Chuanbo Hu +2

    LLM-as-judge is now a standard tool for scalable evaluation, but judge performance is still often summarized by a single accuracy number. This aggregate view hides the deployment conditions under which a judge succeeds or fails. We introduce \textbf{Conditional Accuracy Profiling} (CAP), a post-hoc diagnostic framework that decomposes pairwise LLM-judge accuracy into eight conditions organized into content sensitivity, robustness, and rationale quality. CAP is benchmark-agnostic: it can be applied directly when a benchmark provides the required annotations, approximately through task-subset proxies, or through controlled augmentation when perturbation pairs can be generated. We instantiate CAP on seven LLM judges across six pairwise judging benchmarks, including \textsc{judgerEva-Standard}, a controlled testbed we created to support all eight conditions. CAP exposes profile differences hidden by aggregate accuracy: on \textsc{judgerEva}'s judge-independent Hard-Constructed subset, the two judges most sensitive to omitted qualifications rank in the bottom three of seven by overall accuracy, so omission sensitivity is not predicted by aggregate accuracy. Across benchmarks, Position Robustness shows the strongest rank stability (mean Spearman $\barρ{=}0.87$) but is itself fragile under JudgeBench-Pro adversarial stress, showing the largest mean accuracy drop among the shared conditions, though the dominant degradation channel varies by judge. Condition-level profiles provide a more actionable basis than aggregate accuracy for selecting LLM judges.

    benchmarkscalable evaluationscalable evalllm-as-judge
  217. arxiv:2610.09228 · cs.RO
    Co-Evolving Robot Orchestrators and Policies through Deployment
    Xilun Zhang, Maggie Wang, Erik Bauer, Hong-Xing Yu +3

    Vision-language-action (VLA) policies trained on large datasets are capable within their training domains, yet they still fail to generalize to the variety of situations a robot meets in real-world deployment. Agentic robot systems complement the policy with a vision-language model (VLM) orchestrator that learns when to call the policy, how to instruct it, and when to use scripted skills instead. However, because the harness is built around a frozen policy that has limited language steerability, the orchestrator can avoid the policy's failures but never overcome them. The policy becomes the bottleneck of the whole system. Fine-tuning the policy can remove this bottleneck, but updating it alone decouples it from an orchestrator tuned to its old behavior. We propose Robo-COP, in which the orchestrator and policy co-evolve during deployment. Robo-COP curates skill demonstrations from its own executions, fine-tunes the policy when this data can address recurring failures, and adopts each new policy only after it improves the skills it was trained for. Across ten simulated RoboLab tasks, Robo-COP raises mean held-out success from 64.8% to 73.8% over the same harness with a frozen policy, while fine-tuning on a fixed schedule without verification reaches only 65.8%. On three real-world tasks, Robo-COP raises held-out success from 38.3% to 50.0%. Robo-COP turns deployment into a self-improving flywheel in which robots learn by doing, with each improvement in execution producing better data for the next round of learning. Videos and code are available at https://robo-cop.pages.dev/.

    vision-language-actionagenticself-improving
  218. arxiv:2610.09227 · cs.CL
    Quantize by Drift: Label-Free Mixed-Precision Post-Training Quantization for Text Embedders
    Hyojung Han, Jongmin Kim, Seung-Hun Jeon

    Mixed-precision post-training quantization needs a per-module sensitivity signal; for a text embedder the obvious one -- the retrieval quality a module costs when quantized -- needs relevance labels that deployments rarely have. We measure a label-free substitute: quantization-induced representation drift, obtained by quantizing one module, re-encoding the corpus, and recording how far the output embeddings moved from their full-precision positions. What is specific is the observable: the deployed output representation a dense retriever ranks with. Across five development embedders, configuration-level drift orders sampled mixed-precision plans against held-out retrieval quality at a macro Spearman of 0.911, the sensitivity transports across calibration corpora and retrieval domains in the usable regime, module drifts compose rank-consistently but not numerically, and relevance-derived sensitivity adds no consistent value. The method is one additive allocation under a hard packed-byte budget, with no labels and no search. On three embedders held untouched until method, baselines and hypotheses were frozen and sealed, the pre-registered directional hypothesis against the prior LieQ criterion holds (3/3 at the main budget, no collapse) and drift scores above a two-sided LieQ steelman in 2/3; but at the main budget drift is numerically lower than same-budget uniform precision on all three (-0.99, -0.85, -1.01 points), having reduced module and whole-model drift as designed. Output drift is thus a robust coarse sensitivity signal, not a universally optimal allocation objective: it avoids the catastrophic failures of the transferred signed-geometry adaptation and can remain usable at stressed budgets where uniform collapses, but fine-grained redistribution around a strong uniform operating point remains unresolved.

    post-training
  219. arxiv:2610.09224 · cs.RO
    Fast Planning for Multi-object Multi-target Throwing
    Zhengming Zhu, Yang Liu, Xiao Gao, Aude Billard

    Robot throwing has emerged as a promising technique for improving efficiency in logistics and warehouse automation, by enlarging the workspace and speeding up the process. To significantly increase the throwing system's throughput, we develop strategies for throwing multiple objects in one swipe. Such multi-object multi-target throwing (MOMT) leverages the large degrees of freedom of anthropomorphic hands. The key is to quickly generate fast and feasible throwing motions, which involves a complex trade-off between short trajectory duration and short planning time. We solve this problem in two stages. Offline, we build a model of the feasible set by combining object's inverted flying dynamics and the robot's kinematics and dynamics. Online, we generate feasible throws through fast solution matching and filtering of object's valid detach state and robot's feasible state that can compose sequences of throws in less than 5 ms. We validate the framework on a 7-DoF manipulator equipped with a multi-fingered hand. In simulation, coordinated two-object throwing reduces execution time by up to 46% compared to independent single-object planning, and this improvement is maintained when scaling to three objects. Real-world experiments with two objects confirm a 29% reduction; the remaining gap to the theoretical 50% is attributed to inter-throw transition overhead. When target positions are randomly changed mid-execution, the system re-plans and successfully reaches the new targets within 100 ms latency without stopping the robot. These results establish the first unified planning framework for MOMT throwing -- demonstrating scalability to multiple objects in simulation and real-world feasibility on two-object tasks -- advancing the frontier of high-throughput robotic manipulation. A video summarizing the method and the hardware experiments is available at https://liuyangdh.github.io/momt-video

    manipulationmanipulator
  220. arxiv:2610.09219 · cs.AI
    CM-DPO: Constraint-Margin Direct Preference Optimization for LLM Planning
    Rabimba Karanjai, Qun Gu, Hemanth Hegadehalli Madhavarao, Wenhuan Sun +7

    Direct Preference Optimization (DPO) treats all constraint violations equally: a $1 budget overshoot and a $1,000 overshoot induce the same training signal. It is also susceptible to length and style bias when preference pairs come from different model families. We introduce Constraint-Margin DPO (CM-DPO), which replaces DPO's binary preference signal with a continuous margin derived from a deterministic symbolic verifier and scaled by violation severity. Hard and soft constraints are separated through a lexicographic objective, ensuring hard constraints are never traded off against preferences. To supply CM-DPO with bias-reduced training pairs, we generate preference data through procedurally generated constraint profiles (DCCG) and minimal-edit distillation from a reasoning teacher (RT-MED), within a framework we call SynPlan-R. On TravelPlanner, NaturalPlan, and out-of-distribution PlanBench, an 8B model fine-tuned with CM-DPO achieves 89.2% pass rate and 93.4% solve rate, matching multi-agent systems at 13x lower latency while outperforming GPT-4o on unseen Blocksworld by 9.2 points.

    multi-agentagent system
  221. arxiv:2610.09218 · cs.AI
    RLDISCOVER: LLM-driven co-evolution of reinforcement learning algorithms
    Haoran Li, Zengle Ge, Xiaomin Yuan, Yui Lo +13

    LLM-guided program evolution has enabled discoveries in mathematics and computational optimization, raising the prospect of reinforcement learning (RL) algorithms that self-evolve to improve how agents learn. However, realizing this prospect faces two obstacles. Joint search over coupled algorithmic components is difficult to scale: simultaneous changes can disrupt learning, while isolated changes overlook their dependencies. Evaluating candidate algorithms also requires costly training, with fitness remaining uncertain across random seeds. We introduce RLDiscover, a framework for the self-evolution of model-free deep RL algorithms. Progressive Co-Evolution advances from targeted component edits to joint evolution, while Progressive Probabilistic Evaluation balances search breadth and evaluation fidelity through staged training and repeated evaluation. Experiments across SAC, PPO, and DQN on four benchmark suites show substantial improvements in mean return, with per-family median gains of 32%-84% and a peak return ratio of approximately 363x over a near-zero baseline. These gains include transitions from failed learning to successful task completion, and improvements persist when evolution starts from stronger open-source implementations. On measured SAC locomotion runs, evaluation uses approximately one-fifteenth the estimated compute required to fully evaluate the same candidate pool. Remarkably, independent searches repeatedly discover interpretable combinations of adaptive robust losses, progress-dependent value targets, and running statistics, with selected programs transferring to unseen tasks. These findings point toward a broader role for self-evolution in AI: discovering interpretable algorithms that improve how agents learn.

    benchmark
  222. arxiv:2610.09215 · cs.AI
    AGAR: a reinforcement learning substrate for LLM program evolution
    Haoran Li, Zengle Ge, Xiaomin Yuan, Yui Lo +10

    Given a task and an evaluator, a language model can rewrite a candidate program while a search loop decides which rewrites survive, offering a practical route to algorithm discovery. But that loop is governed by five constants set by hand: which parent to select, how hard to mutate, how to keep diversity, what to remember, and a scalar score that never says which part of the program earned it. Reinforcement learning already has an estimator for each. The obstacle is that program evolution is not usually written down as a decision process. We formalize it as a Markov decision process whose action is the modular prefix the model is conditioned on, rather than the program it emits. Credit assignment, value estimation, adaptive exploration, and experience memory can then attach to distinct components. AGAR (Algorithm Generation As RL) provides the resulting substrate: any estimator can be replaced or switched off without changing the controller, making the transfer auditable one mechanism at a time, with no gradient training of the backend model. Across 19 tasks, two backends, and three seeds under one harness, AGAR improves on the stronger of two published baselines on most tasks, with gains concentrated in the competitive-programming family. The formalization also yields a checkable reading of prior work: these systems are implicitly zero-discount, not by choice, but because fitness is exogenous to an individual rather than a return over successors, leaving a discount factor nothing to act on.

    memoryevaluator
  223. arxiv:2610.09213 · eess.SY
    Mission-critical spectrum sharing with decentralized Multi-Agent Reinforcement Learning
    Dimitrios Pylorof, Imtiaz Nasim, Humberto E. Garcia, Vivek Agarwal +2

    Motivated by emerging mission-critical applications and an increasingly congested spectrum, we develop a decentralized multi-agent reinforcement learning (MARL) model for dynamic spectrum access. The model enables secondary users to learn effective transmission strategies across shared frequency bands while minimizing collisions with high-priority primary users and among themselves. We design the agent-level learners following a Markov potential game approach, connecting independent local updates to system-level improvement. We instantiate this design using lightweight linear actor-critic learners suitable for resource-constrained edge devices, rather than computationally intensive centralized or deep multi-agent architectures. Across spectrum environments with different incumbent activities, the learned policies adapt their transmission policy and waiting behavior to preserve throughput while greatly reducing transmission collisions relative to random and forecast-aware heuristic baselines. The results establish the value of decentralized MARL and shows up to 96.8% reduction in overall collisions.

    multi-agent
  224. arxiv:2610.09209 · cs.AI
    Multi-Objective Aligned Small Language Model Framework for SUD Patient Dialogue Generation
    Thushara Manjari Naduvilakandy, Hyeju Jang, Mohammad Al Hasan

    Substance Use Disorder (SUD) counseling requires patient responses that reflect underlying cognitive states such as beliefs, coping strategies, and readiness for change. Although large language models (LLMs) can generate fluent text, they often fail to produce cognitively coherent and clinically realistic patient behavior, especially under ethical and data-scarce clinical settings. Moreover, deploying frontier-scale LLMs in healthcare applications presents practical challenges including high computational cost, latency, privacy concerns, and limited deployability in resource-constrained environments, motivating the need for cognitively aligned small language models (SLMs). We propose a cognitively grounded framework for SUD patient dialogue generation that explicitly models and aligns latent cognitive components with patient histories and counselor questions. Our pipeline consists of two stages: cognitive component detection and cognitive component-aligned dialogue generation. To enable effective learning with smaller models, we combine knowledge distillation from high-capacity teacher models, preference optimization from human-annotations, and attention-guided reward shaping. Extensive evaluations using automatic scores like BERTScore, ROUGE, METEOR and BLEU, and LLM-as-judge hit-metrics against both human and teacher-model references show that cognitively informed fine-tuning substantially improves cognitive realization and alignment over a generic instruction-tuned baselines and mental health domain specific SLMs, with particularly strong gains for open-ended cognitive components.

    llm-as-judge
  225. arxiv:2610.09205 · cs.AI
    Do Vision Models Learn Physical Constraints or Rendering Shortcuts? A Counterfactual Benchmark for Grounded Physical Consistency
    M. Moein Esfahani, Sepehr Salem, Mohammed Alser, Vince Calhoun

    Modern image editing models can satisfy a text instruction while breaking the physics of the edited scene. A new object may cast no shadow, a mirror may fail to reflect visible geometry, or an object may float above a surface that should support it. We study physical plausibility diagnosis, detecting whether an edited image violates scene physics, naming the violation type, localizing the affected region, and explaining the failure in language. We introduce a counterfactual benchmark whose controlled synthetic component uses Mitsuba~3 to generate 5,500 images from 500 scene families. Each family contains one clean image and ten matched violations involving shadows, reflection, support, surface response, and occlusion. The renderer pipeline provides category labels, affected-region masks and boxes, scene metadata, and explanation targets. We use LLaVA-1.5-7B, Qwen2.5-VL-7B, and InternVL3.5-8B as diagnostic baselines rather than proposed methods. On a 1,650-image synthetic test set, the adapted baselines reach 64.0--67.8\% category macro-F1 on standard held-out scenes. For LLaVA-1.5-7B, category macro-F1 falls from 64.0\% on the standard split to 40.8\% under intervention shift. This gap shows that high in-distribution accuracy partly reflects cues tied to rendering and counterfactual construction.

    benchmark
  226. arxiv:2610.09197 · cs.AI
    FreeEvolve: Learning to Evolve Beyond Fixed Loops
    Lecheng Kong, Like Hui, Nikos Kanakaris, Prithwish Jana +2

    Agent evolvers automate the design of the prompts, skills and workflows around language model agents, yet the optimization process they follow is still designed by hand: a fixed search loop decides how candidates are evaluated, which are kept and when the search stops. We propose FREEEVOLVE, which automates this process as well. An environment specifies the goal, target agent, evaluator, data and resource limits; within these limits, the evolver itself decides what to test, how much evidence to collect, which candidates to pursue and when to stop. These decisions follow an editable evolution skill, which we improve through meta-evolution by scoring each candidate skill on the fresh target agent it produces. The optimization process thus becomes a capability learned from experience rather than a loop engineered in advance. On tau3-bench, ARC-AGI-2, ARC-AGI-3 and Terminal-Bench 2.1, FREEEVOLVE controls the evolution campaign by itself, yet improves the primary held-out metric by 13.6 points on average and matches or exceeds hand-designed evolvers. The learned process keeps improving with experience: meta-evolved skills add 6.9 points over the seed skill on fresh target agents, demonstrating transferability across environments.

    agentevaluator
  227. arxiv:2610.09195 · cs.RO
    StableGrasp: Reconstructing Physically Stable Human Hand Grasps from Single Images
    Han Jiang, Etienne Vouga, Qixing Huang, Georgios Pavlakos

    Reconstructing a physically stable human grasp from a single RGB image is challenging because physically modeling grasps is itself difficult, and the problem requires estimating not only a visually constrained hand pose but also a control target that stabilizes the grasp. Existing methods either model only visual hand geometry without considering physics, or rely on less plausible physical modeling, which limits the physical validity of the resulting grasps. In this paper, we present StableGrasp, a differentiable simulation-based optimization framework that explicitly separates the visual hand pose from the control target that determines the grasping forces. Our method jointly optimizes hand geometry and control by minimizing the kinetic energy of the grasp in a differentiable simulator, while regularizing the hand geometry to preserve visual consistency and geometric plausibility. The reconstructed grasps are substantially more stable under rigorous physical simulation, while remaining visually consistent with the input images and geometrically plausible. Experiments show that our approach produces far more stable grasps than alternative hand-control strategies, benefiting visual-only grasp reconstruction pipelines by turning their outputs into physically stable grasps.

    grasp
  228. arxiv:2610.09194 · cs.AI
    Patient, Place, Prior (P$^3$): What Counts as Personalization in Medical World Models?
    Xingrui Gu, Hanxue Gu, Yuxiang Zhang, Yang Yang

    Longitudinal models forecast how a patient's imaging state evolves, but accuracy does not show whether the patient's observed trajectory drives the prediction. A population-average forecast may be useful but cannot establish a patient-specific world-model claim. We introduce Patient, Place, Prior (P$^3$), an audit asking whether a forecast benefits from the patient's longitudinal imaging history (Patient), benefits from patient-matched externally supplied spatial support (Place), and gains predictive value beyond a population-average prediction under matched support and context (Prior). We also propose Cancer JEPA, a one-step model that forecasts frozen representations of future breast dynamic contrast-enhanced MRI examinations during neoadjuvant therapy. It adds a lesion-constrained neural correction, trained with an occlusion-based latent objective, to a patient-conditioned low-complexity reduced-rank regression baseline. This factorization permits a post-hoc P$^3$ audit of the frozen model. In a validation cohort previously used in development, forecast error is lower when the neural correction receives the patient's history rather than another patient's and patient-matched lesion occupancy maps rather than substituted maps. However, the descriptive 95% interval comparing the correction computed from patient history with the population-average neural correction includes zero. P$^3$ thus separates input use from evidence of patient-specific predictive value beyond a population-level pattern.

    world model
  229. arxiv:2610.09193 · cs.AI
    Bookkeeping, Composition, or Unreachable Gold? Reading MemoryAgentBench's Conflict-Resolution Scores Against a Frozen Last-Write Resolver
    Egor Pakhomov, Erik Nijkamp

    MemoryAgentBench's Conflict Resolution split is read as measuring "selective forgetting". We execute the benchmark's own rule - the newest statement about a fact wins - as a zero-learning resolver frozen on one of the four fact lists. Under the official metric the rule answers 80.25% of the questions (74.5% on the three held-out lists). Of the rest, 67 items have a released gold that the last-write graph cannot reach but overwritten statements would ("The capital of India is New Delhi." superseded by "The capital of India is Grosseto."; gold New Delhi); such items are a third of the multi-hop questions at 262K. Two long-context models and our pre-registered approximate re-implementation of the benchmark's BM25 agent, one retained run per item and outcomes only, score 84.7%, 82.6% and 41.6% on the items the rule solves against 10.4%, 11.9% and 6.0% on those 67. The failures are a reachability split plus a small parser-scope residual; the per-item split, not the aggregate, is the unit at which a score here can be read.

    long-contextbenchmark
  230. arxiv:2610.09192 · physics.app-ph
    Physics-Derived Natural Coordinates for Fast Uncertainty Propagation in Multilayer Thermoreflectance
    Tao Chen, Dihui Wang, Puqing Jiang

    Uncertainty quantification in thermoreflectance measurements of multilayer structures is challenging because thermophysical-property extraction involves nonlinear inverse problems with strongly coupled parameters. Covariance-based analytical propagation is efficient but assumes local linearity and approximately Gaussian fitted variables, whereas Monte Carlo (MC) propagation captures non-Gaussian behavior but is computationally expensive and can be unreliable when simultaneously fitting parameters spanning very different orders of magnitude. Here, we address these issues by combining normalized MC sampling, used to obtain reliable benchmark distributions, with physics-based variable transformations for analytical uncertainty propagation. From the multilayer heat-diffusion equation, we identify natural coordinates: the interfacial thermal resistance 1/G, the substrate combinations sqrt(k_z k_r) and sqrt(k_z C), and the thin-film combinations k_r/C, hC, and Ch^2/k_z. Across several representative multilayer systems and thermoreflectance modalities, these coordinates are approximately Gaussian even when the original physical parameters are skewed. Performing covariance-based propagation in the transformed space and mapping the results back to physical parameters yields asymmetric confidence intervals that closely match normalized MC benchmarks. The approach preserves the non-Gaussian uncertainty structure of the recovered parameters while avoiding repeated nonlinear refitting, providing a fast and physically interpretable methodology for thermoreflectance uncertainty quantification in multilayer systems governed by diffusive heat conduction.

    benchmark
  231. arxiv:2610.09188 · cs.AI
    From Probabilities to Decisions: Search and Multi-Teacher Distillation with Jev
    Mohamad Yazan Sadoun, Sarah Sharif, Yaser Mike Banad

    Probability-only models, which TypeSafe calls System One models, return calibrated probabilities for fixed choices in milliseconds and generate no text. We study one such model, Jev, through two tasks that require decisions under tight constraints. In bullet chess, a bot that places Jev's judgment inside Stockfish search alongside an opening book and endgame tablebases climbs above a 2200 Lichess bullet rating against other bots. Live model calls are too slow for search, so we distill pairwise judgments into a compact evaluator that runs at every position. We then ask how best to spend a fixed labeling budget when an LLM, Qwen3-32B, is available as a second teacher. In chess, averaging both judges' labels beats spending the whole budget on Qwen alone by 9.6 Elo (95% interval 4.3 to 14.9), and the gain replicates on fresh openings; a second answer from the same judge is no substitute, and Jev is the strongest partner for Qwen among the models tested. In passage reranking, Jev's labels alone train a reranker that scores as high as Qwen's, from 21 minutes of API calls instead of 5.1 GPU-hours, and adding Qwen gains at most a few thousandths in ranking quality. Search supplies the lookahead, distillation makes the judgment cheap enough to use at every position, and an LLM partner pays off in chess.

    evaluator
  232. arxiv:2610.09178 · cs.RO
    CAP: Codebook-Aligned Prediction for Tokenized Robot Policies
    Haoran Chen, Jingtian Ji, Samuel Wheeler, Kaylene Caswell Stocking +1

    Action tokenization converts continuous robot actions into discrete symbols that can be modeled autoregressively. However, existing tokenizer-based policies typically ignore the tokenizer's learned latent code structure: after tokenization, the policy treats tokens as unrelated class indices and learns a new classifier from scratch. We show that this discarded structure is valuable. We introduce Codebook-Aligned Prediction (CAP), a method that directly reuses the tokenizer's code vectors as policy class prototypes while leaving the tokenizer and policy backbone otherwise unchanged. Across four quantizer families, three simulation benchmarks, and two real-robot tasks, CAP consistently improves task success over standard token classification heads while holding the tokenizer (and therefore its reconstruction quality) fixed. Our analysis further shows that these gains are not explained by higher token accuracy or changes in the policy head alone. Instead, reusing the tokenizer codebook provides the policy with valuable information about the tokenizer's learned latent structure across tokens, making token prediction errors more benign in action space and improving the representations learned by the policy backbone. These results suggest that action tokenizers learn useful action-aware latent structure beyond discrete targets that should be preserved when training downstream policies.

    benchmark
  233. arxiv:2610.09170 · cs.RO
    Beyond Reconstruction: What Matters in Action Tokenization for Robot Policies?
    Haoran Chen, Jingtian Ji, Samuel Wheeler, Kaylene Caswell Stocking +1

    Autoregressive action-token policies such as vision-language-action models require action tokenizers to translate discrete token sequences into precise control actions in continuous space. Many action tokenizers learn the mapping between tokens and actions via a reconstruction objective. However, as we show through extensive analysis, sufficiently accurate action reconstruction is only one part of what makes a downstream robot policy successful. It is also critical that the policy is able to predict the right tokens for new observations, and that unseen policy token predictions still decode into reasonable actions. These properties are downstream of tokenizer training and are not directly incentivized by a reconstruction objective alone. In this work, we introduce Predictable and Robust Action Tokenization (ProAct), a tokenizer training method that strategically augments reconstruction with the goal of improving downstream predictability and robustness. ProAct is policy-agnostic and uses only action datasets for training. Across the Robomimic, LIBERO, and RoboTwin benchmarks and a diverse set of tokenizer architectures, ProAct improves rollout success by an average of 11.3 percentage points. These improvements also translate to vision-language-action policies and real-world robotic manipulation, yielding average gains of 21.8 and 36.7 percentage points, respectively. These results suggest that effective action tokenization should be designed as a policy interface that balances fidelity, predictability, and robustness, rather than as a reconstruction problem alone.

    vision-language-actionmanipulationrobot policyliberorobotwinbenchmark
  234. arxiv:2610.09165 · cs.RO
    geodex: A Library for Motion Planning on Riemannian Manifolds
    Phone Thiha Kyaw, Ben Wei, Sepehr Samavi, Miguel Angel Rogel Garcia +1

    Planning motions that respect the intrinsic geometry of a robot's configuration space, including its curvature and a configuration-dependent notion of cost, yields shorter, lower-energy, and more natural trajectories than planning under the ambient flat metric. Existing libraries for optimization on manifolds provide rich geometric primitives but do not plan around obstacles. While general-purpose motion planning libraries support many state spaces and custom distance functions, they do not yet treat a configuration-dependent Riemannian metric as the geometry that drives distance, interpolation, and geodesics. We present geodex, an open-source C++20 library with Python bindings. The library exposes the manifold, its Riemannian metric, the retraction, and the sampler as independent, interchangeable components through a single sampling-based motion planning interface. The same planner runs unchanged on canonical spaces $\mathbb{R}^n$, $\mathbb{T}^n$, $\mathbb{S}^n$, matrix Lie groups such as $SO(2)$, $SE(2)$, $SO(3)$, and $SE(3)$, products of these spaces, and articulated-robot configuration spaces, each equipped with a user-defined Riemannian metric. We make geodex publicly available with documentation, tests, and a reproducible benchmark suite.

    benchmark
  235. arxiv:2610.09163 · cs.AI
    ToolRACER: A Robust Agentic Conversation Emulation Resource for Agent Training and Evaluation
    Arkajyoti Chakraborty, Aryan Tayal, Ishika Agarwal, Tanner Sorensen +4

    Task-oriented conversational agents remain fragile under real world conversation scenarios as they rarely follow a predictable script, especially when users exhibit non-cooperative behavior. Existing function-calling benchmarks often emphasize successful, cooperative interactions and underrepresent adversarial conversation trajectories, thereby limiting the training resources available for developing robust agents. We present ToolRACER, a synthetic data generation pipeline that coordinates user, assistant and tool emulation models to generate and validated multi-turn interactions between a user and an agent. Using \sysn, we construct ToolRACERBench a robust multi-turn conversation benchmark spanning six domains, ranging over 55 varied personas, generating a validated corpus of 5.6K conversation trajectories, with approximately 66\% of conversations containing failure-prone conversation scenarios. We inject adversarial behaviors, producing validated conversational interaction trajectories that capture realistic, robust scenarios. We evaluate models trained on ToolRACERBench against internal benchmarks, as well as on function calling benchmarks such as $τ^2$-bench, BFCLv3 and ACEBench to evaluate agentic accuracy and robustness. Models trained on ToolRACERBench improve end to end agentic accuracy across $τ^2$-bench and ACEBench, demonstrating significant gains when mixed with in-domain dataset in small language models for agent capability tasks.

    agentagenticbenchmark
  236. arxiv:2610.09159 · cs.AI
    SpecGuard: Proving a Task Is Broken Before the Agent Cheats
    Param Biyani, Krishnamurthy Dvijotham

    As autonomous coding agents get increasingly deployed, the risk that accidental or adversarially injected misspecifications in tasks lead to dangerous agent behavior is critical to address. Prior work has shown that agents given such tasks rarely flag the conflict and instead cheat, editing tests or hard-coding expected outputs, and the actions taken to cheat can cause real damage, such as deleting a security defense to make a corrupted test pass. It remains unclear whether such conflicts can be established with independently verifiable evidence before the agent acts. We present SpecGuard, which detects and formally certifies these conflicts between task intent and tests. Given only the task description and codebase, SpecGuard autoformalizes the intended behaviour into a Lean 4 specification. The tests are formalized independently, and the Lean kernel checks whether any implementation could satisfy both formalizations, producing a machine-checked certificate when none can. On conflicted SWE-bench tasks, SpecGuard detects up to 72.8% of conflicts and formally certifies up to 51.1%, with a nearly five-fold lower conflict miss rate than model-based judgment. SpecGuard provides a pre-execution safety check that identifies reward-hacking opportunities through formal certification of task-level conflicts, before any agent behavior is observed. Our code is available at https://github.com/prmbiy/specguard.

    agent
  237. arxiv:2610.09152 · cs.AI
    sk-bench: A Native-First Benchmark for Evaluating Large Language Models in Slovak
    Marek Šuppa, Ivan Vykopal, Andrej Ridzik, Kristián Sopkovič +8

    Multilingual LLM benchmarks omit Slovak, a morphologically rich West Slavic language of five million speakers, or cover it only by machine translation. We present sk-bench, a native-first Slovak benchmark with 30 datasets (33 scored task variants) across ten skill categories. Eleven resources are introduced or first packaged for generative-LLM evaluation, including IFEval-SK with Slovak-adapted instruction checkers and native Chiby/SKJ1 resources for Slovak grammar and morphology. We evaluate 55 open- and closed-weights models under one harness. The best open model trails proprietary APIs by 12.6 points. Model rankings are similar for native and translated closed-form data ($ρ\geq0.98$), though translation separates the strongest models less well. By contrast, human-authored and LLM-generated QA questions rank models differently ($ρ=0.72$). For Qwen3-14B, continued Slovak pretraining lowers the overall score by 13.9 points. A small instruction set restores three quarters of that loss. Test-time reasoning improves scores by 8.5 to 12.5 points for models of 9B and above. Together, these findings suggest four design lessons for other under-resourced languages: use native data where translation fails, plan instruction repair after language adaptation, enable test-time reasoning before scaling up, and avoid overinvesting in target-language prompts. We release the data and code at https://github.com/slovak-nlp/sk-bench

    benchmark
  238. arxiv:2610.09146 · cs.AI
    Frozen Models, Evolving Expertise: Model-Agnostic Learning from Deployment Experience for Multimodal Medical AI
    Yexiao He, Yucheng Tang, Pengfei Guo, Yufan He +5

    Large language models (LLMs) and vision-language models (VLMs) are usually frozen after deployment, so they do not learn from the cases they solve. This is especially concerning in medicine, where new clinical evidence, updated guidelines, and new therapies can change established practice. Fine-tuning can update the model, but it requires access to model weights and additional training. Parameter-free methods avoid training, but they may overfit a fixed validation set, lack reliable domain knowledge, or lose visual details by saving experience only as text. To address these limitations, we present a model-agnostic framework that allows frozen LLMs and VLMs to learn from deployment experience through three forms of external expertise: a Skill that guides reasoning and tool use, a Knowledge Memory that stores reliable facts supported by earlier cases or trusted external evidence, and a Multimodal Knowledge Base that keeps visual examples and guides the model to relate each retrieved case to the current image. Instead of relying on a fixed validation set, a validation strategy keeps an update only if it helps on new cases without degrading performance on earlier ones. Across six benchmarks covering clinical diagnosis, clinical workflows, medical reasoning, and medical and non-medical visual reasoning, and with four open-weight and closed-source base models, our framework improves performance during online deployment by up to 34.2% over the base model on medical tasks, generalizes to unseen cases, transfers to other models without further optimization, and works in non-medical domains.

    memorytool usebenchmark
  239. arxiv:2610.09144 · cs.AI
    DIVA: Dual-Space Intent-Aware Visual Attenuation for Vision-Language-Action Policies
    Kaixi Feng, Guoheng Sun, Ziyao Wang, Yexiao He +2

    Vision-language-action (VLA) policies typically feed dense visual patch tokens into a language-action backbone, preserving scene context but offering no explicit mechanism to regulate how strongly different visual tokens influence policy computation. We introduce DIVA, a Dual-Space Intent-Aware Visual Attenuation module with an anchor-then-attenuate design. DIVA combines high-level task intent with low-level visual evidence to estimate patch-wise relevance anchors, then applies them in two complementary spaces: it reweights projected visual tokens before backbone entry and persistently attenuates low-relevance visual states within the backbone. DIVA preserves the full visual token sequence and requires no external grounding supervision. On LIBERO, DIVA improves OpenVLA-OFT from 96.6% to 98.0% average success and raises its zero-shot LIBERO-Plus score from 69.6 to 72.6. Real-world experiments further show consistent gains under task-irrelevant visual perturbations, supporting the robustness of intent-aware visual attenuation beyond simulation.

    vision-language-actionopenvlalibero
  240. arxiv:2610.09142 · cs.AI
    Finding Blind Spots in AppWorld and WorkArena Task Verifiers
    Richard Abrich

    Execution-based task verifiers decide whether an agent succeeded. We audit shipped AppWorld and WorkArena verifiers with source-informed mutation tests. The main audit never modifies a shipped checker. In AppWorld, duplicating a non-idempotent write creates an extra record while preserving every checked field value. The verifier accepts all three task variants from two of five eligible generators: 6/15 constructed effects. A cardinality patch applied to checker copies after the census makes all six cells fail while preserving valid controls. In WorkArena, we prospectively rerun 23 extra-field candidates selected for earlier checker-PASS outcomes. Independent Table API readback confirms nondefault persisted values in 21, while all 23 receive PASS. Two requested strings are aliases of stored defaults. The 21 confirmed wrong effects span three form templates. These selected cases confirm wrong effects under the audit's protocol; they do not estimate a population rate. No other construction produces an independently confirmed false accept. Other checker-PASS cases are effect-correct degeneracies. We report zero-PASS families separately because retained evidence differs. In fixed intent-swap grids, the checkers return no PASS on 2,689 off-diagonal executions. This is a rejection census: 57 WorkArena cells use session-scoped evidence; the other 2,632 lack classified rejection causes and independent target ground truth. Each increment is specified before its own cells are scored. A supplement accompanies the OpenReview submission with the construction grammar, evidence, content-bound stage lineage and count reproducer.

    agent
  241. arxiv:2610.09138 · cs.AI
    SwarmReconGuard: Black-Box Detection of Distributed Collective Reconnaissance by Individually Benign-Looking Agent Populations
    Vahid Tavakkoli, Kabeh Mohsenzadegan, Kyandoghere Kyamakya

    Autonomous and agentic clients can distribute reconnaissance across many identities so that each request remains valid, low-rate, and benign-looking while the population collectively acquires broad system knowledge. We formalize this threat as Distributed Collective Reconnaissance (DCR) and present SwarmReconGuard, a reproducible black-box benchmark in which the defender observes only service-boundary telemetry. The Docker-isolated study evaluates 11 benign and attack behaviors across 10-10,000 virtual identities, comprising 440 test runs and 3,666,300 requests, with complete telemetry integrity. We compare semantic, Gaussian, conditional, graph, kernel, hybrid, and CUSUM-based detectors. Gaussian likelihood-ratio detection achieves 100$\%$ detection with 0$\%$ observed false positives on known attacks but only 3$\%$ on unseen policies. CUSUM yields 36.1$\%$ overall detection at 1.25$\%$ false positives, while hybrid CUSUM reaches 85.7$\%$ detection with 0$\%$ observed false positives at 10,000 identities. Results expose a major policy-generalization gap and motivate exposure-aware, scale-aware defenses.

    agentagenticbenchmark
  242. arxiv:2610.09134 · cs.RO
    World Models Dream of Success: Diagnosing and Repairing Failure Insensitivity in Robot World Models
    Jiuyi Xu, Xiao Hu, Meida Chen, Peng Gao +2

    Robot world models support policy evaluation, planning, and synthetic data generation, but these applications require predictions that distinguish successful actions from failures. Across four released checkpoints from two architecture families, we observe weak sensitivity to action changes and success-like predictions on verified failures. Although recent work incorporates failures into model training, which data can repair released checkpoints without changing their architecture or training objective still remains underexplored. To this end, we introduce CureWM, which constructs alternative actions from successful demonstrations across a severity grid, verifies their outcomes through execution in simulation or on hardware, and fine-tunes released models on the resulting failures and surviving successes alongside nominal demonstrations. This construction provides controlled action contrasts from shared starting contexts. On 484 held-out LIBERO failure counterfactuals, optimism falls from 80\% after fine-tuning on the official data to 30--43\% across four independently fine-tuned CureWM models (38\% mean). In two separate evaluations on a physical robot arm, failure predictions scored as success-like by a latent-distance diagnostic decrease from 90\% after fine-tuning on successful demonstrations alone to 33\% with CureWM. With failure counts per task, successful replay data, and training budget matched, counterfactual failures yield a success--failure value gap of 0.124, compared with 0.014 for freshly collected on-policy failures. These findings support execution-verified counterfactual replay for post-hoc repair and show why reduced optimism must be evaluated alongside success--failure discrimination. Code is available at https://github.com/jiuyixu25/CureWM.

    liberoworld modelpolicy evaluation
  243. arxiv:2610.09127 · cs.AI
    CADFather: Autonomous CAD Reconstruction through Coordinated Tool Use
    Gennadiy Savrasov, Maksim Elistratov, Nikita Gavrilov, Albert Garifullin +6

    Reconstructing an editable CAD model from a 3D shape remains a challenging engineering task. Existing methods can propose CAD operations, but no single source of proposals works equally well across different part geometries and stages of reconstruction. We introduce CADFather, an autonomous agentic system that coordinates complementary tools to recover parametric CAD programs from 3D meshes. A vision-language assistant inspects renders of the target and intermediate reconstructions, then decides which candidate CAD programs to extend, which tools to invoke, how many proposals to generate, and when to finish. Learned and algorithmic tools propose CAD operations, while numerical optimization refines the parameters of existing programs. Proposed or refined programs are executed and evaluated to provide feedback for subsequent decisions. The agent maintains alternative candidate programs for each target part and preserves the best valid result throughout reconstruction. CADFather uses pretrained generation and assistant models without additional training. We evaluate reconstruction quality and execution validity on the full DeepCAD, Fusion360, and MCB test sets, as well as on CADENA-Bench, CADBench, and BenchCAD. We additionally analyze computational cost and the trade-off between cost and reconstruction quality.

    agentautonomous agentagentictool use
  244. arxiv:2610.09120 · eess.SY
    The Deceptive Bandit Problem: Exploratory Coupling and the Fragility of Multi-Agent Learning
    Michael Tang, Mahmoud Abdelgalil, Jorge I. Poveda

    Randomized exploration is central to bandit learning, multi-agent reinforcement learning, and zeroth-order policy search, yet its independence and privacy are usually only treated as technical assumptions. We show that these properties are critical for security purposes and demonstrate how an adversarial agent can exploit privileged information on another agent's exploration. We analyze a deceiver-victim pair in the minimal two-player strongly monotone setting, where a deceptive player obtains leaked signals that are merely correlated with the victim's exploration. We show that, by coupling their own exploratory action with this information, the deceptive player injects an externality that steers the learning dynamics to a new steady state, called the deceptive Nash equilibrium (DNE). We prove that the deceptive bandit learning (DBL) dynamics converge to an arbitrarily small neighborhood of the DNE while retaining optimal convergence rates. Interestingly, our analysis attains these optimal rates while relaxing second-order smoothness conditions from standard bandit optimization literature. We characterize conditions under which deception strictly shifts the steady state and its effect on the deceiver's cost, illustrating the results in a resource-allocation game.

    agentmulti-agent
  245. arxiv:2610.09119 · cs.AI
    Which Buildings Are Artificial Intelligence-Ready? A Measurement-Based Assessment Framework for AI Question Answering and Actuation
    Wooyoung Jung

    Agentic artificial intelligence (AI) systems are becoming the interface to buildings, answering questions and controlling operations, but a building's readiness for them has not been systematically assessed. This study proposes a framework to quantify it. First, a building's knowledge graph sets two ceilings. The answerable-readiness ceiling is the share of operational questions its data could answer, and the actuation-readiness ceiling is the share of control actions it exposes. Second, a reference AI agent's accuracy on a fixed set of these questions shows how much of the ceilings is realized. On a simulated office, the agent realizes 0.62 of a 0.64 answerable ceiling, so missing data, not the AI, limit readiness, except in naming a fault's cause. Across 37 public real-building graphs, the median answerable ceiling is 0.16, and in 15 of 45, unlinked sensors lower it. The framework turns "is this building AI-ready?" into an auditable, ranked retrofit question.

    knowledge graphagentai agentagentic
  246. arxiv:2610.09117 · cs.RO
    Workhorse: Learning Robust Whole-Body Humanoid Loco-Manipulation from Human Data
    Songbo Hu, Qiayuan Liao, Yufeng Chi, Kevin Zakka +3

    Humanoid robots still struggle to plan contact-rich whole-body manipulation from egocentric RGB and proprioception. Workhorse learns such manipulation from robot-free human demonstrations. A visual planner predicts five-link targets: the poses of the torso, both wrists, and both feet. A reinforcement-learning whole-body tracker follows them on the robot. Both policies train separately on the same recorded human poses, without retargeting. We augment the training data of each policy to imitate the errors that the other makes at deployment. On a real Unitree G1, Workhorse sorts boxes with its hands and a kick, catches a thrown box, and topples and climbs a suitcase. During box sorting, we show recoveries after a person pushes the robot or takes the box away. In a simulated copy of the demonstration room, the system completes box sorting in 77% of episodes, and in 64% under 40 N.s pushes. With both policies retrained from the same demonstrations, a simulated second humanoid completes box sorting in 83% of episodes without pushes.

    manipulationhumanoid
  247. arxiv:2610.09115 · cs.AI
    From Uncertainty to Action: Learning to Steer LLM Agents
    Hanwen Li, Jinhao Duan, Guanhua Zhu, Junchi Lu +3

    Steering an LLM agent means deciding whether to correct it, at which step, and with which mechanism. Uncertainty is often used to decide when to correct an agent, but whether it can guide these decisions remains unclear. We steer agent trajectories separately at every non-terminal step with each of four mechanisms and run each continuation to completion. The resulting stepwise outcome table (SOT) holds about 82,000 counterfactual continuations of 1,864 trajectories from three benchmarks and two agents. It shows that uncertainty can identify failing trajectories, but that no single signal reliably locates the step at which steering helps. We therefore propose VoS (Value of Steering), a trajectory-level monitor, offline or online, that learns from SOT the value of steering at each step and decides where to steer by it. A harm-budgeted trigger decides whether to steer, limiting the fraction of successful trajectories that VoS disturbs. VoS improves on unmodified execution in all 12 settings of benchmark, agent, and offline or online use, by 7.8 points on average, and outperforms the strongest of five existing uncertainty-triggered methods in 11, by 2.9 points on average. Ablations show that training on measured outcomes and a tight harm budget are both essential.

    agentllm agentbenchmark
  248. arxiv:2610.09112 · cs.AI
    GeoNatureAgent (GNA): A Framework and Benchmark for Pre-Production Evaluation of Tool-Using Agents on Geospatial and Environmental Tasks
    Gabriel Diaz-Ireland, Diego Prieto-Herráez, Mario García Peces, Javier Velázquez +2

    Before tool-using LLM agents are deployed in environmental and geospatial workflows, teams need evidence that an agent reliably selects the right operations against real APIs. We introduce GeoNatureAgent (GNA), a framework for pre-production evaluation of tool-using agents: a fixed sixteen-tool geospatial interface published as a Model Context Protocol (MCP) server, so the agent under test is the only variable, scored against an identical tool layer, task suite, and deterministic scorer. Its flagship instance is a 103-task benchmark (a 93-task main suite across 18 categories plus a ten-task comparison expansion) evaluated against an open, self-hostable geospatial API serving three environmental indicators across Spain and Portugal. We evaluate nine LLMs under three temperature-1.0 seeds, reporting capability and per-case cost as orthogonal axes. (1) Claude Sonnet 4 achieves the highest capability (61.7% +/- 0.7% on all 103 tasks; 60.8% on the main suite), followed closely by DeepSeek V3.2 (57.9%), while no other model exceeds 53%; (2) the cost-accuracy Pareto frontier is mostly open-weight, with DeepSeek V3.2 offering 93% of Claude's capability at 11.3x lower list-price cost; (3) under strict all-checks scoring the best model sits 24-36 points below the 85-97% reported on general-purpose GIS benchmarks, whereas per-check partial credit for the top four models (86-90%) is comparable, so much of that gap reflects scoring strictness rather than task difficulty alone. The MCP server, evaluation harness, benchmark, and API are publicly available; swapping the tool executors and task suite instantiates an equivalent benchmark for any geospatial domain.

    agentllm agentbenchmark
  249. arxiv:2610.09107 · cs.AI
    Constraint Tree Exploration for Learning from Language Feedback
    Shaoang Li, Daniel R. Jiang, Jian Li

    Natural-language feedback in interactive learning often explains why an action failed by pointing to violated requirements. Misinterpreting this feedback can lead an agent to rule out valid solutions. We study this setting by modeling user intent as latent constraints over an action space and formulating learning from language feedback as pure exploration over feasible regions. We introduce TRACE, an algorithm that organizes candidate constraints in a tree and tests each proposed refinement by generating actions that satisfy it. TRACE commits to the refinement only if the resulting feedback does not contradict it over repeated tests. We distinguish two ways of using the same feedback: (i) falsification, which detects contradictions to the constraint set currently being tested, and (ii) identification, which may additionally name a violated constraint. We prove high-probability coverage bounds with dependence on the candidate class size $H$ for TRACE-Falsification. With reliable identification, TRACE-Identification can replace this dependence by $K/p_{\mathrm{ext}}$, where $K$ is the number of latent constraints and $p_{\mathrm{ext}}$ lower-bounds the probability of extracting a missing true constraint from informative feedback. We evaluate TRACE across six language-feedback tasks. On RecMovie, TRACE-Identification achieves 73% and 86% final-output success under caps of 20 and 60 evaluated outputs, compared with at most 42% and 48% for the evaluated prompting baselines given the same feedback and output caps. Controlled identity-corruption experiments further show greater robustness than direct accumulation when the falsification detector remains reliable.

    agent
  250. arxiv:2610.09092 · cs.AI
    MaRK: Markov-adapted Recurrent Kernels for Dynamic Operator Conditioning in State Space Models
    Syed Ibrahim Omer, Ginny Y. Wong. Xiangyu Zhao

    State Space Models (SSMs) offer an efficient alternative to Transformers for sequence modeling, yet conditioning pre-trained SSMs for iterative generation typically operates outside the recurrent operator, through input injection or activation modulation. While such mechanisms expose the model to conditioning information, they leave the underlying temporal dynamics fixed. We introduce MaRK (Markov-adapted Recurrent Kernels), a dynamic operator-conditioning framework that maps context vectors directly into bounded modulations of a frozen SSM's recurrence ($A$), read-in ($B$), read-out ($C$), skip ($D$), and discretization ($Δ$) parameters. Viewed through the lens of LPV-SSM systems, MaRK induces a context-indexed family of Markov parameter sequences, allowing each diffusion timestep to reshape the model's input-output memory kernel. We instantiate MaRK on a frozen 111M-parameter Hydra SSM backbone and study three adapter geometries: Hypernet, Chebyshev polynomial, and Discrete Cosine Transform kernels. Since these adapters modify the Markov parameter sequence through low-rank auxiliary maps on the frozen backbone, parameter-efficient fine-tuning arises as a structural consequence of the adaptation mechanism itself, requiring only 6.3--11M trainable auxiliary parameters to transition from a bidirectional objective to an iterative diffusion regime. The bounded recurrence parameterization further yields an analytic Affine Quadratic Stability certificate for the modulated recurrence. Through synthetic LPV recovery experiments and Markov-operator diagnostics, we show that MaRK recovers coordinate-invariant temporal operators under matched assumptions and produces distinct, stable timestep-conditioned memory profiles. Empirically, the Chebyshev variant yields the strongest performance, achieving an average validation loss of 2.55, followed by the DCT (2.59) and Hypernet (3.77) geometries.

    memory
  251. arxiv:2610.09088 · cs.AI
    RippleCP: Measuring Counterfactual Checkpoint Advantage in Coding Agents
    Mayur Akewar, Ravi Ranjan

    Agent checkpoint systems decide what state is recovery-relevant, how to snapshot it, and whether rollback is admissible. None decides which of the safe boundaries they expose are worth materializing. We formulate this as counterfactual checkpoint advantage, the reduction in future recovery cost obtained by checkpointing a candidate rather than skipping it, and measure it by driving a CP branch and a SKIP branch to the same logical failure and recovering both under matched model, tool, verifier, and stopping conditions. On a frozen pilot of 12 SWE-bench Verified tasks and 106 real recovery branches, checkpointing saves 49.4 s per task, and that figure resolves into two regimes two orders of magnitude apart. The first checkpoint returns 100.0 s on 156.5 s of protected work, a conversion of 0.64; a second one step later returns-1.1 s on 41.8 s, a conversion of -0.03. Recovery is a re-derivation rather than a replay, so preserved work is a poor guide to saved work, and the classical elapsed-work rule misprices the second checkpoint by its full nominal cost. We identify where placement can pay, and set the bar a placement policy must clear.

    agent
  252. arxiv:2610.09087 · cs.AI
    U-Space: Uncovering When and Why Uncertainty Arises in Language Models
    Tobias Braun, Nils Loose, Alexander Herzog, Virginia Ceccatelli +3

    Large language models are informing decisions with ever-higher stakes. As the consequences of their errors grow, a central question becomes harder to ignore: how much can we trust an individual answer? Yet recognizing when to defer remains difficult because language models can present incorrect conclusions with fluent explanations and an authoritative tone. Uncertainty quantification seeks to address this disconnect by estimating the reliability of individual predictions. However, many existing methods require repeated generations or separately trained components, and their scalar estimates do not reveal where uncertainty arises or how it evolves during reasoning. Recent work has also shown that generation length can be strongly associated with uncertainty estimates and correctness, raising the question of how much of an estimator's predictive power comes from uncertainty-specific information rather than output length alone. Mechanistic interpretability offers a way to address these limitations by connecting human-interpretable concepts to intermediate model states. Building on this capability, we introduce the U-Space, a low-dimensional subspace that makes a model's evolving uncertainty measurable and interpretable. We identify semantic anchors for doubt and certainty, map their unembedding directions back into the residual space, and combine their contrasts into an orthogonal basis. The U-Lens projects each token state onto these basis vectors, yielding an interpretable token-level uncertainty map that can be inspected directly or aggregated into a scalar uncertainty score. Our approach requires no correctness labels, repeated generations, or training. Across reasoning benchmarks, its confidence score outperforms established baselines under both standard and length-controlled evaluation and transfers more reliably than supervised estimators. Code: https://github.com/s2labres/U-Space.

    benchmark
  253. arxiv:2610.09079 · cs.CL
    Large-scale Repository Engineering via Agent-Native Reusable Code Primitives
    Haibo Jin, Peng Kuang, Xucheng Yu, Jerry Wang +2

    Large language models equipped with development environments have moved code generation toward repository-scale construction, yet building complete repositories remains difficult because interacting modules, interfaces, configurations, tests, and dependencies must work together. We introduce Code Primitives, agent-native reusable executable components with interface contracts, dependency closures, validation tests, and provenance. Each primitive uses a resident LLM to assess relevance and adapt its implementation, interfaces, and dependencies to the target repository, and we organize 1,424 validated primitives in CodeFace, a searchable library for repository construction. We introduce LEGO (Large-scale repository Engineering via aGent-native reusable cOde primitives), which activates task-relevant primitives, integrates their adapted implementations with task-specific code while resolving cross-component constraints, and revises the result against executed tests. To measure construction end to end, we build LEGO-REPO, a benchmark of 522 executable reconstruction tasks spanning seven software domains, 22 capability tracks, and five difficulty levels, scored against native test suites between an empty-package floor and original-source ceiling. The strongest of 13 evaluated backbones reaches a delivery score of 0.318 and scores zero on 41.0% of tasks; LEGO improves all 13 by 0.1474 on average and raises GPT-5.6-terra from 0.3180 to 0.5134 (+61.4%). In controlled comparisons, adapted primitives outperform retrieved code supplied as context or vendored unchanged. The effect persists against independent repository agents, across three external benchmarks, and with a disjointly re-mined CodeFace; GPT-OSS-20B for adaptation and diagnosis retains 95.1% of the homogeneous score at 24.0% lower cost.

    benchmark
  254. arxiv:2610.09057 · cs.AI
    Epistemic Uncertainty-Aware Defect Detection for Quality Control in Medical Device Manufacturing
    Raham A. Butt, Marco Romanelli, Roche C. de Guzman

    Objective: We investigate whether accounting for epistemic uncertainty can improve the reliability of automated defect detection in medical device manufacturing. Methods: We consider a machine learning framework that operates on heterogeneous manufacturing and device-report data represented with Knowledge Graphs. To mitigate errors arising from uncertainty in the decision model, we analyze a principled rejection strategy to abstain from predictions whose estimated epistemic uncertainty exceeds a specified threshold. We evaluate the approach using standard synthetic benchmarks and real-world medical device report data. Results: The theoretical results establish the validity of the method characterizing the regimes under which it is expected to be effective. Empirically, the rejection strategy enables explicit control of coverage, that is, the proportion of samples for which the model issues predictions, while improving performance on the retained samples. On 266,170 real-world FDA MAUDE device reports, a 10% abstention rate reduces classification error by 48%, and more aggressive rejection (approximately 70% coverage) yields near-perfect accuracy on the retained samples. On standard synthetic manufacturing benchmarks, abstaining on 9% of the decisions, our approach reduces the risk up to 63% compared with the standard no-abstention approach. Conclusions: Abstaining from predictions with high epistemic uncertainty can provide a practical tool for controlling the reliability of machine learning-based defect detection, especially in high-stakes medical device manufacturing applications. Significance: Uncertainty-aware defect detection may support safer and more reliable quality assurance in medical device manufacturing by identifying cases that require additional inspection rather than issuing potentially harmful predictions.

    knowledge graphbenchmark
  255. arxiv:2610.09055 · cs.RO
    MimicX: Policy-in-the-Loop Supervision Refinement for Video-Driven Humanoid Motion Tracking
    Shuaijun Liu, Chenglong Zhang, Xuhao Liu, Feiyang You +6

    Human videos provide rich motion targets for humanoid learning, yet visually plausible references can still produce persistent failures under physics-based execution. These failures reveal where training supervision should change. We present MimicX, a policy-in-the-loop framework that uses execution feedback to refine video-driven humanoid motion tracking. Starting from reconstructed and retargeted motion, MimicX localizes difficult transitions and affected body regions, then jointly adapts tracking objectives and the reset curriculum for policy continuation. Repeated rollout verification selects execution-priority improvements subject to tracking guards. Across four core video tasks, MimicX consistently improves tracking accuracy and Robust Execution Horizon relative to the Fixed Reference baseline. Task-averaged results show a 25.7% reduction in body-tracking error and a 255.6% increase in execution horizon. Additional video, motion-reference, and collision-scene studies evaluate the method beyond the core tasks, while MimicX-HLoop accelerates feedback through heterogeneous execution. Overall, MimicX turns policy failure into actionable supervision for deciding what to refine and which refinement to retain.

    humanoid
  256. arxiv:2610.09053 · cs.AI
    Justice After Identity: Large Language Models and the View from Everywhere
    W. Russell Neuman

    The search for a common view of justice and fairness has challenged human collective activity, as our diverging judgments are unavoidably shaped by the self-interests of social position, personal benefit, cultural inheritance, and historical circumstance. John Rawls famously attempted to overcome this limitation through popularizing a philosophical tradition known by the phrase "the original position" - a thought experiment by which people select principles of justice without knowing the identities or advantages they will possess. Critics, however, have long questioned whether people can meaningfully suspend their social identities and suppress morally relevant forms of lived experience. Artificial intelligence engaged to calculate algorithmic and agentic fairness introduces a novel possibility. LLMs have no singular class, race, gender, nationality, or biography, yet their parameters encode linguistic representations of a vast range of human identities and moral traditions. Perhaps the ethical judgments of LLMs could approximate an integrative original position - a "view from everywhere" generated not by excluding social identities but by computationally incorporating their diversity.It is unlikely that humankind will "hand over the keys" to computational systems by simply delegating complete agentic control of distributive and procedural collective processes. But AI may play a role, perhaps a positive one, interacting with individual and collective human judgment as we often confront increasingly polarized views on what is fair and just. We present data comparing human, base model, and frontier/fine-tuned model judgments about classic moral dilemmas while systematically varying identity relationships and Rawlsian constraints on identity. We conclude by speculating whether, if advanced AI systems provide humans with thoughtful advice, humans would actually be likely to accept it.

    agentic
  257. arxiv:2610.09034 · cs.RO
    Shared-Roadmap Generation and Evaluator for Multi-Agent Path Planning Using Heterogeneous Graph Neural Network
    Brandon Ho, Nikola Rogers, Seung-Kyum Choi

    Multi-agent path planning (MAPP) in continuous environments often relies on roadmaps to balance safety and search efficiency. However, traditional roadmap generation methods, such as lattice grids or standard sampling-based approaches, frequently face a trade-off between graph density and the likelihood of finding feasible, high-quality solutions. In this paper, we propose a scalable heterogeneous Graph Neural Network (GNN) framework for the automated generation and evaluation of shared multi-agent roadmaps. Our model covers the representation of waypoints, agent locations, and task locations as distinct nodes in a heterogeneous graph, allowing it to reason over global connectivity and inter-agent interactions. By training on occupation density maps aggregated and collected from expert solver trajectories, the GNN learns to identify critical points of interest and prune redundant nodes and edges. This process produces a compact, coordination-aware roadmap that is invariant to task permutations and is reusable for multi-agent pick and delivery tasks. Experimental results demonstrate that our framework can reduce planning effort and can potentially find better solutions, reaching at least 40% reduction in runtime and in graph size for dense roadmaps.

    agentmulti-agentevaluator
  258. arxiv:2610.09027 · cs.AI
    Visual Memory Attacks Can Persist Through The KV Cache
    David Dobre, Leo Schwinn, Gauthier Gidel, Spandana Gella +2

    Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images. Can an adversarial input continue to steer a model even after that input is removed from its context? We show that attacks can be trained to persist through the key/value (KV) cache of subsequent tokens, allowing adversarial influence to outlive direct access to its source.We consider the Visual Memory Injection (VMI; Schlarmann and Hein, 2026) attack setting, in which an adversarial image that stays in the context plants a hidden backdoor: the model behaves normally until a chosen trigger elicits an attacker-chosen response. We first demonstrate persistence in this setting with optimized soft prompts, which remain effective after we mask the prompt from attention. We then introduce Persistent Visual Memory Injection (P-VMI), which optimizes images to preserve this adversarial behaviour after they are masked from attention. These attacks persist over conversations substantially longer than those used during optimization. On Qwen3-VL-8B-Instruct, P-VMI achieves up to approximately $90\%$ target success in its strongest configuration and remains effective under a stricter removal setting that exposes the image only on the first turn. A cache-swap ablation localizes the persistent influence to the KV cache. Finally, we show that these attacks can be trained to survive compaction that retains the KV cache of a summary generated by the same model, demonstrating that adversarial behaviour can persist in cached state without continued access to its source.

    memorylong context
  259. arxiv:2610.09026 · cs.AI
    BEACON-SP: Ontology-Grounded GraphRAG Framework for Clinical Suicide Risk Assessment
    Kemal Davaslioglu, Nathan Conger, Sastry Kompella, Yalin E. Sagduyu +1

    We present BEACON-SP, an ontology-grounded Graph Retrieval-Augmented Generation (GraphRAG) framework for clinician-facing decision support in behavioral health settings such as suicide prevention, where effective assessment requires integrating heterogeneous clinical, behavioral, social, and temporal evidence. BEACON-SP combines patient knowledge graphs with ontology-guided retrieval to support multi-hop reasoning across diagnoses, medications, risk and protective factors, life events, and temporal relationships. The framework is enabled by a comprehensive suicide prevention ontology that integrates the Three-Step Theory, the Integrated Motivational-Volitional Model, and the Suicide Social Determinants of Health Ontology into a unified representation of patient risk factors. We construct ontology-grounded patient knowledge graphs and evaluate BEACON-SP for clinician-facing question answering. Compared with a vector-based retrieval-augmented generation (RAG) baseline on a 1,500-query benchmark spanning 15 clinical categories and 100 patients, BEACON-SP improves completeness, clinical relevance, and evidence grounding under a corrected comparative evaluation protocol, with a small gain on factual accuracy. In paired criterion-level comparisons, GraphRAG is preferred in 76.4% of cases. These results demonstrate the potential of ontology-guided GraphRAG to provide structured, contextualized patient evidence for clinical decision support.

    retrieval-augmentedknowledge graphbenchmarkevaluation protocol
  260. arxiv:2610.09021 · cs.AI
    Not Every Call Needs a Frontier Model: Per-Call-Site Evaluation of Small Language Models in a Deployed Agentic Home-Automation System
    Panagiotis Kasnesis, Christos Chatzigeorgiou, Lazaros Toumanidis, Amalia Contiero Syropoulou

    An agentic system issues several structurally different kinds of LLM calls. It routes intent, classifies actions, grounds language in a device registry, plans multi-agent pipelines and writes the Python code those pipelines run. The difficulty of these call sites varies by an order of magnitude, yet in practice a single model, chosen for the hardest site, serves all of them. In this work, we evaluate 9 models from 0.8B to a frontier hosted model across the five call sites of a deployed open-source home-automation framework (Wactorz), using its unmodified production prompts and two real Home Assistant installations (280 cases, 2520 scored calls). We find that capability is not ordered the same way at every site, and that larger models are not uniformly better: one 4B model is worse than its 2B sibling at grounded actuation. Paired testing shows the best local model to be statistically indistinguishable from both hosted models at four of five sites. Only code generation separates them, against a small hosted model (p = 0.039) as well as a frontier one (p = 0.002). Aggregate accuracy also hides a safety failure specific to actuation, where small models resolve the accuracy/refusal trade-off in degenerate ways: one model (Gemma4 E2B) actuates on 87.2% of requests for devices the site does not own, while another refuses every request it receives. Routing each site to its best local model reaches 91.8% against 95.4% at no per-call cost. In a live deployment judged by a user, hosting only the two generative sites matches hosting everything (39/43 against 39/43) for 28% of the spend, and the actuation gap the benchmark predicted appears as exactly one case in twenty-six. Benchmark, harness and all records are released at https://github.com/waldiez/slm-callsite-eval.

    multi-agentagenticbenchmark
  261. arxiv:2610.09016 · cs.AI
    PAIR: Bridging Perception and Action in Vision-Language-Action Models
    Kaixi Feng, Guoheng Sun, Ang li

    Vision-language-action (VLA) models map visual observations and language instructions to continuous robot actions. This task requires a transition from representations that describe the scene and instruction to representations that support action generation. Many continuous-action VLAs leave this transition implicit and supervise it mainly through the final action-prediction loss. We introduce PAIR, a framework that learns a shared perception-action representation between these two spaces. During training, a Masked Action Autoencoder encodes expert action chunks into horizon-aligned Action Latent Tokens. A Bridge Module extracts task-relevant features from the current visual-language representations. PAIR aligns these features with the Action Latent Tokens to form Bridge Tokens that preserve task information and capture the structure of expert actions. The Bridge Tokens are then projected into the action-token space and injected into the initial Action Tokens, providing an action-ready starting point for Action Expert refinement. At inference, the autoencoder is removed, and the Bridge Tokens are generated only from the current observation and instruction. Experiments on LIBERO, LIBERO-Plus, and CALVIN ABC-D show gains for the evaluated OpenVLA-OFT and VLA-Adapter models. On LIBERO-Plus, PAIR raises VLA-Adapter's success rate from 59.1% to 64.2%. On CALVIN, it increases VLA-Adapter's average completed sequence length from 4.42 to 4.53. Across seven real-world tasks, PAIR raises OpenVLA-OFT's success rate from 51.4% to 65.0%. Representation analyses show that Bridge Tokens retain task information while making continuous-action information accessible before Action Expert refinement. These results support a shared intermediate representation as a useful interface between perception and action in continuous-action VLAs.

    vision-language-actionopenvlalibero
  262. arxiv:2610.09015 · cs.AI
    Personalize at Test Time: Learning User Preferences for Image Generation
    Jiamu Bai, Jiaming Hu, Yanhong Wu, Zellux Wang

    Diffusion models can generate high-quality images, yet aligning their outputs with individual user preferences remains challenging. A key bottleneck is accurately modeling diverse user preferences from limited feedback. Existing approaches often rely on labor-intensive manual preference annotations or vision-language models (VLM) to extract preference information from user interaction histories, introducing substantial annotation or computational costs that limit scalability. We propose an approach that learns personalized reward models directly from users' historical image preference pairs. First, we use an autoencoder to compress hundreds of visual attributes into 50 attribute-anchored preference dimensions and train an evaluator to score images along these dimensions. We then represent each user's preferences as a linear combination of the shared dimension scores, estimating the user-specific weights by maximizing the likelihood of their observed pairwise preferences under the Bradley-Terry model. This formulation reduces per-user adaptation to optimizing a low-dimensional weight vector, simplifying optimization and enabling data-efficient personalization from sparse feedback. The learned personalized rewards guide image generation at inference time while keeping the diffusion model frozen. Experiments on real-user preference data show that our approach achieves approximately 77% held-out pairwise preference prediction accuracy and improves the alignment of generated images with individual user preferences.

    evaluator
  263. arxiv:2610.09013 · cs.AI
    Enabling Dynamic Computation in Looped LMs
    Aayush Mishra, Arnau Padrés Masdemont, Victor Conchello Vendrell, Jordi Ros Giralt +2

    Looped LMs are parameter efficient and promise dynamic computation (saving memory and FLOPs on easy tokens). However, state-of-the-art open Looped LMs trained with this dynamic computation capability (Ouro models) do not realize it in practice as each loop iteration (depth) requires its own level of KV-cache, necessitating all loop computations. Moreover, Ouro's early-exit prior is enforced on each token equally, which results in static lower-depth like processing of all tokens regardless of difficulty. In this work, we propose a simple "best-available" KV caching strategy that works out-of-the-box, creating a new frontier in the performance vs depth space. Our approach enables up to 30% reduction in FLOPs and KV memory while retaining full-depth performance, showing the true flexibility of Looped LMs. Furthermore, training looped LMs with awareness about this KV caching strategy improves performance and efficiency. Finally, we apply a small but effective fix to the early-exit prior enforcement objective that makes tokens exit at truly heterogeneous depths based on effort. Our findings are validated on Ouro models as well as smaller looped LMs pre-trained from scratch.

    memory
  264. arxiv:2610.09008 · cs.AI
    Whose Memory Is It? Scope-Aware Commit Rules for Long-Term LLM Memory
    Hongyu Gu, Xinchang Li

    Persistent memory allows an LLM agent to carry experience across conversations, but it also turns a local reasoning mistake into a durable one. During deliberation, an agent may consider a plan, simulate a tool result, report another speaker's belief, and then reject all of them. If memory retains only the resulting sentences, those once-useful possibilities can later return as facts. The record is neither fabricated nor irrelevant; it has simply been detached from the context in which it was valid. We identify this missing context as \emph{discourse ownership}: the world, branch, or speaker that licenses a proposition. Our first finding is counterintuitive. Language models already carry a causally active signal for ownership, yet conventional memory interfaces discard it when they convert reasoning into records. We introduce CASK (Causally Anchored Scoping Keys), a commit rule that preserves this signal so that shared-world facts enter durable memory while provisional content remains available only within its original scope. Our second finding is that the most obvious way to preserve the signal---storing the discovered internal coordinates---is unreliable because equivalent representations need not keep the same coordinates. CASK instead preserves the stable relations that express ownership. Controlled long-conversation conflicts and tool-agent traces show that this design improves memory admission and prevents provisional content from contaminating later answers while complementing runtime provenance. The resulting commit boundary lets agents explore more possibilities without granting every intermediate sentence authority over future behavior.

    memorypersistent memoryagentllm agent
  265. arxiv:2610.09003 · cs.AI
    Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers
    Sourabh Kasliwal

    Autoregressive Large Language Models (LLMs) frequently struggle with deterministic multi-step algorithmic tasks such as multi-digit multiplication and long division. In this paper, we investigate the mechanics of multi-step arithmetic in compact "Tiny" Transformers (~10.6M non-embedding parameters, 49.3M total) trained on synthetic data across four basic operations (+, -, *, /) unrolled as step-by-step scratchpads. First, we establish the necessary training foundations: (1) dataloader sequence padding creates an 83% gradient starvation artifact that collapses accuracy from 40% to 1%, remediated via continuous sequence packing; (2) linguistic pretraining is an essential prerequisite (<= 2.0% without it); and (3) modern architectural primitives (RoPE, RMSNorm, SwiGLU) and Sparse Mixture of Experts (MoE) substantially improve additive reasoning over baseline GPT-2. Second, we demonstrate that algorithmic scratchpad formulation directly dictates success. Introducing a deterministic Digit-by-Digit Long Division scratchpad within a 4-stage Hierarchical Developmental Curriculum dramatically elevates single-digit division from 4.0% to 86.7% accuracy on a 4,000-problem held-out benchmark. In contrast, multi-digit multiplication remained challenging: detailed error analysis revealed that while the model correctly computed single-digit sub-products and place-value zeros, our FOIL scratchpad failed because it forced a simultaneous summation of up to nine multi-digit terms in a single step without pairwise intermediate accumulation. Finally, we identify two key boundaries: performance collapses to 0.00% on unseen 4-digit operands, and unbuffered training induces catastrophic forgetting, collapsing division accuracy from 86.7% down to 0.00%.

    benchmark
  266. arxiv:2610.09002 · cs.AI
    Learning to Report Unsafe Tasks in a Multi-Agent Game
    Avyay M. Casheekar, Hariganesh Tangirala

    When agents share a reward for completed tasks, reporting unsafe work can reduce the reporter's reward by stopping a task. Audits can make reporting optimal without ensuring that further training teaches a silent team to report. We study this learning problem in a game where any witness can stop a task by reporting. With $k$ witnesses per task sharing a policy and drawing independently, the expected-reward derivative with respect to their shared silence probability counts each task's benefit $k$ times at universal silence. The comparison with universal reporting counts it once. For arbitrary policy groups, we give an audit condition sufficient for exact policy-gradient updates to reach universal reporting and, apart from boundary cases, necessary near universal silence. In a balanced family, the cheapest audits meeting the condition with prescribed positive margins cost exactly $k$ times as much for full sharing as for one policy per role. We train PPO policies on 24 witness graphs from learned silence. Separating co-witnesses reduces unsafe completion by 33.59 percentage points compared with shuffled groups of the same sizes under the same audits (95% graph-bootstrap interval: 21.03-45.13). Only 9 of 48 witness-group runs achieve below 1% unsafe completion while retaining at least 90% legitimate completion. At the same audit budget, a fully shared network meets both thresholds in none of 48 runs with independent action draws and all 48 with a common draw.

    multi-agent
  267. arxiv:2610.09000 · cs.AI
    How Fragile Is On-Device Language Model Safety? Localizing Safety-Critical Parameters for Sparse Fault Analysis
    Muhammad Zeeshan Karamat, Christiana Chamon Garcia

    As small language models (SLMs) are increasingly deployed on resource-constrained and on-device platforms, including as components of agentic systems, the integrity of locally stored model parameters becomes an important safety concern. We investigate whether safety-sensitive behavior in LLaMA-2-7B-Chat is concentrated within a sparse subset of parameters, creating a reduced fault surface for targeted analysis. We study two complementary localization methods: low-rank safety-associated subspace analysis and parameter-level safety--utility importance filtering. Both approaches reveal highly non-uniform safety sensitivity across the network, with the MLP down_proj consistently emerging as a prominent safety-sensitive component and o_proj providing a smaller contribution. Using parameter-level localization, modifying only 0.19% of model weights in down_proj yields 53% Basic ASR and 56% GCG ASR, while tinyBenchmarks accuracy remains at 51.6% compared with a 52.2% unmodified baseline. These results motivate targeted fault analysis and selective integrity protection for language models deployed in resource-constrained, on-device, and agentic settings.

    agenticbenchmark
  268. arxiv:2610.08995 · cs.RO
    PhysEvo: Astra Can Act, Let It
    Wenqing Tian, Zeyu Zhang, Zhaocheng Liu, Fengwei Liu +2

    Astra can act, yet reliable manipulation depends on the system through which it observes and controls the world. We introduce PhysEvo, a framework for physical recursive self-improvement (RSI) around a single frozen model. A task agent executes robot tasks; a meta-agent uses the resulting trajectories to diagnose failures, revise tools and skills, and test corrections. The meta-agent can also improve its own diagnostic tools, so retained revisions support both later action and later self-improvement. This process develops joint-level control, evidence-seeking observation, and reusable manipulation skills without model-weight updates or a separately trained action policy. Across 42 RoboDojo tasks, held-out-layout evaluation of retained task-specific deployment versions yields a five-dimension average score of 68.14/100 and 62.00% success, compared with 47.17% for RoboDawn's one-shot Astra agent, the strongest published reference in our comparison. On eight manipulation tasks challenging direct Astra, PhysEvo achieves 55.00% success, compared with 1.25% for the direct-Astra reference. Deploying the simulation-evolved harness on AgileX PiPER and continuing skill revision yields 90.60/100 average score and 84.00% success across 25 trials on five real-world tasks. PhysEvo turns the consequences of action into persistent, testable changes to how a frozen model acts and improves.

    manipulationagentself-improvement
  269. arxiv:2610.08993 · cs.AI
    Verify Less, Evolve More: Training Idea-Level Critics for Verification-Efficient ML Evolving Agents
    Jiamu Bai, Lizhu Zhang, Xin Yu, Yanhong Wu +8

    As large language models become more powerful, self-evolving agents are able to tackle challenging tasks including AI for machine learning (AI4ML). In AI4ML, while empirical verification is available, it often requires computationally costly model training and evaluation, limiting the speed and scale of agent evolution. Yet verification efficiency remains under-explored, and frontier models provide only limited gains when used directly as idea selectors. We address this gap with specialized idea-level critic models that predict whether a proposed ML modification will improve upon the current solution, allowing agents to screen ideas and concentrate verification resources on the most promising candidates. We train the critic models through supervised fine-tuning on high-quality critiques synthesized by Gemini-3.1-Pro, followed by GRPO to further improve their predictive accuracy. Empirically, our critic models outperform Gemini-3.1-Pro in static idea evaluation, and these gains extend to agent inference, continual learning, and policy training. During inference-time evolution, they improve final solution quality under the same verification budget by selecting more promising ideas, with further gains from continual learning. During policy training, they serve as learned reward models, reserving empirical verification for uncertain cases and enabling substantially more policy updates with the same verification resources. Together, these results show that idea-level critic models help ML agents discover better solutions and learn stronger proposal policies under limited verification budgets.

    agentself-evolving
  270. arxiv:2610.08970 · cs.RO
    HULK: Learning Whole-Body Forceful Loco-Manipulation for Humanoids
    An Dang, Arturo Flores Alvarez, Yu-Ming Chen, Conor Mc Gartoll +4

    Humanoid loco-manipulation of large, heavy objects demands forceful interaction across the entire body. However, such payloads shift a humanoid's center of mass and impose sustained loads across the upper body, challenging balance and command tracking. We present HULK, a whole-body control framework for forceful loco-manipulation. Using model predictive control (MPC) to guide reinforcement learning with predictions of the loaded dynamics, we train two teachers: one tracks arm motions under wrist forces, and the other locomotes while holding large objects against the body. A capture-point control barrier function augments the wrist-force teacher during training to improve balance under load. We distill both teachers into a single policy. Evaluation spans simulation and the Unitree G1. In simulation, the teacher with the barrier function achieves the lowest forward and lateral velocity tracking errors at 10 kg per arm among evaluated controllers and reduces aggregate divergent component of motion (DCM) excursion magnitude by 35.7% relative to MPC-guided reinforcement learning alone. Our wrist-force teacher withstands torso push disturbances of up to 130 N.

    manipulationhumanoidwhole-body control
  271. arxiv:2610.08966 · cs.AI
    Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models
    Xingang Guo, Jing Gu, Brian Jang, Renxiong Wang +25

    Humans perceive far more in a scene than what is explicitly depicted: a single glance captures past causes and future trajectories; a quick peek determines if a vehicle can fit between two parked cars; a few seconds of video reveals who holds authority in a room; and a fleeting clip highlights subtle abstract patterns like unwritten rules or hidden labels. This capacity reflects a form of humanity's sixth sense: an intuitive reasoning mechanism that recovers implicit information beyond raw sensory perception. Crucially, this rapid, zero-shot visual intuition underpins everyday navigation and social interaction, making it a vital capability for Multimodal Large Language Models (MLLMs) deployed alongside people. Existing visual benchmarks, however, target either deliberate expert-level analysis in academic and mathematical domains or low-level perception, leaving the intuitive reasoning that people perform largely untested. To bridge this gap, we introduce Humanity's Sixth Sense (HSS), a benchmark for intuitive visual reasoning. HSS spans diverse image and video inputs, organizes items under a structured taxonomy, and pairs each with human-written prompts probing the implicit temporal, spatial, social, and abstract structure that people infer at a glance. Frontier MLLMs fall short of human performance: participants reach 93.1% accuracy, while the strongest model, GPT-6-astra, reaches only 53.6% even at maximum reasoning effort. Despite excelling in many complex tasks that require advanced perception and knowledge, current models still struggle significantly on these visual tasks that are intuitive for humans. We further explore agentic setup that apply dynamic visual manipulation to HSS, which narrows but does not close the gap. HSS establishes intuitive visual reasoning as a measurable axis and directs attention to a capability that scaling on current benchmarks has so far left behind.

    manipulationagenticbenchmark
  272. arxiv:2610.08959 · cs.AI
    GraphOPD: Graph-Augmented On-Policy Distillation for LLM Agents
    Bohan Lin, Liyi Chen, Zhuoning Guo, Muyang Li +4

    On-policy distillation post-trains large language model agents by supplying dense, step-level guidance from a teacher policy when the reinforcement-learning reward is sparse and arrives only once per trajectory. Existing instantiations allocate this guidance by the size of the teacher-student divergence at each step, on the single-turn intuition that a large disagreement marks a mistake worth correcting. Once decisions chain over many turns, that rule misfires, since an early drift enters every later context both policies condition on, leaving the teacher consistent with the drifted trajectory instead of flagging its cause, while interchangeable steps register large but outcome-irrelevant divergences. We demonstrate this on an agentic benchmark, where distilling the highest-divergence steps brings no consistent benefit over random selection. To this end, we introduce GraphOPD, the first method to bring graph-based structural augmentation into on-policy distillation for agent capabilities. It reads which steps enabled which later ones from the environment's own record of state changes, immune to the drift that corrupts the teacher-student gap, organizes them into a dependency graph, scores each step by a random-walk stationary distribution over it, and fuses that structural credit with the divergence signal into a trajectory-relative mask concentrating supervision on each rollout's highest-aptitude steps. Across three model scales and eleven baselines on ALFWorld, WebShop, and SearchQA, GraphOPD shows competitive performance throughout, improving over the strongest baseline by up to +5.8 pp. An executed-replay audit further shows that this structural credit score tracks true causal impact far above chance, that both fused signals are independently necessary, and that the same signal transfers to out-of-domain tool-integrated reasoning.

    agentllm agentagenticbenchmark
  273. arxiv:2610.08954 · cs.AI
    RACER: Reflective Agent Coupling Query Interpretation and Tool-Based Retrieval for Frame Selection in Long Video Understanding
    Yiyang Huang, Yitian Zhang, Yizhou Wang, Jianglin Lu +5

    Video large language models (Vid-LLMs) excel at diverse video-language tasks by reasoning over selected frames. However, frame selection for long videos remains challenging, as it requires retrieving relevant frames distributed across segments from a large candidate pool given complex queries. This paper investigates dominant approaches to long-video frame selection from a task-decomposition perspective, identifying two key challenges: the Query Comprehension Gap in similarity-based methods and the Interpretation--Selection Gap in judgment-based methods. To address them, we propose RACER, a training-free reflective agentic framework that decomposes long-video frame selection into query interpretation driven by a lightweight Vid-LLM and evidence localization supported by an embedding model serving as a retrieval tool. Specifically, the Vid-LLM is responsible solely for reformulating the complex query into sub-queries that make implicit information requirements explicit, mitigating the Query Comprehension Gap. Meanwhile, the retrieval tool leverages these sub-queries to localize relevant evidence, relieving the Vid-LLM of direct frame selection and thus addressing the Interpretation--Selection Gap. Finally, the retrieved frames are fed back to the Vid-LLM for sub-query refinement, forming a reflection loop that iteratively improves query interpretation and frame selection. Experiments across multiple benchmarks show that RACER consistently improves long video understanding. Notably, RACER achieves effective frame selection even with limited-capability components, demonstrating that agentic integration enables these components to enhance more capable Vid-LLMs.

    agentagenticbenchmark
  274. arxiv:2610.08933 · cs.RO
    Toward Evidence-Driven Human-Agent-Robot Teaming for Earth-Independent Anomaly Triage
    Ignacio G Lopez-Francos, Alexis Gallagher, Samira Shalal

    Deep-space crews cannot rely on real-time ground support for urgent off-nominal events. Initial alerts may underdetermine cause, while discriminating evidence may reside in crew observations or at locations that are unsafe, costly, or unavailable for crew inspection. We present an evidence-driven architecture for human-agent-robot teaming in Earth-independent anomaly triage. Agentic AI is treated as a stateful coordinator over bounded, inspectable services rather than as a fully autonomous vehicle controller. A triage state manager maintains hypotheses, evidence provenance, uncertainty, operational context, and tool status; a crew-facing embodied agent elicits observations and explains assessment changes; and a mobile robot acquires targeted, localized evidence. Typed interfaces separate dialogue and orchestration from monitoring, robot command, context retrieval, and safety-critical control. Two scenarios illustrate the architecture: a crewed deep-space mission based on an actual ISS ammonia false alarm, where suspected contamination restricts crew access, and a power-interface anomaly at a crewed lunar base, where robotic inspection distinguishes a local connector fault from other causes ambiguous in remote telemetry. Our main contribution is an authority-bounded closed evidence-loop architecture, exercised in a hardware-in-the-loop integration prototype using Reachy Mini and an Innate MARS mobile robot.

    embodiedagentagenticembodied agent
  275. arxiv:2610.08928 · cs.AI
    Multi-Aspect Runtime Verification for Simulation-Based V&V of LLM-Enabled Autonomous Agents
    Nikolaos Kekatos, Dimitrios Nikou, Anastasios Temperekidis, Alexios Lekidis +3

    LLM-based agents are entering decision-support roles in defence staff work, where the obligations they must respect are already written down and binding, and where retraining is not available as a control because models arrive as procured components. What can be placed under engineering control is the interface between the agent and the systems it acts on. Those obligations are at once spatial, temporal and text-semantic, and a violation typically lives in the composition of a multi-step interaction, which is why per-event guardrails miss sequential tool-attack chains. We present a multi-aspect runtime-verification framework that decomposes a natural-language policy clause into a typed spatial/temporal/semantic triple over one canonical event stream, checks each aspect with its own monitoring specification, and fuses the verdicts through a four-valued algebra that carries provenance. The spatial aspect is interpreted over a weighted two-sorted location graph in which mission geometry and information-release topology are one object; we show that these spatial obligations are not in general subsumed by a first-order temporal specification. The past-time aspect runs on the unmodified MonPoly engine, which agrees with our reference monitor at every time point. Across two mission domains, casualty evacuation and contested sustainment, and one civil domain, composition under the precautionary blocking policy drives attack success to zero with no observed false positives and microsecond-scale per-event cost, while every single aspect and every pair leaves a substantial share of attacks succeeding. In a closed-loop experiment a policy-naive planner reaches a violating state in most unshielded missions and in none when shielded, and four refused episodes in five still recover to a compliant outcome.

    agentautonomous agent
  276. arxiv:2610.08927 · cs.AI
    Can AI Agents Make Open-Ended Scientific Discovery? Evidence from Station
    Wenyu Du, Stephen Chung

    Recent AI systems have made rapid progress in scientific discovery when given well-defined metrics, but whether they can autonomously undertake open-ended scientific discovery remains unclear. We investigate AI's ability to tackle open-ended tasks in Station, an open-world environment in which multiple agents simulate a scientific ecosystem. To tackle challenges specific to open-ended tasks, we propose augmenting Station with two mechanisms: a Supervisor mechanism and periodic Meta Reflection, which encourage persistent exploration even when intermediate metrics are lacking. We construct open-ended tasks from three recent oral papers presented at ICLR. We give agents the main research question studied in each paper while withholding the paper's results and disabling web access. We then measure how many of the original findings-partitioned into individual criteria-agents rediscover. We find that Station rediscovers 62.7% of the criteria on average, compared with 15.4% for Codex Multiagent-v2 and 14.4-20.6% for AI Scientist-v2. Ablation and behavioral analyses indicate that adding the two mechanisms together improves research coverage and continuity. We further evaluate Station on two open-ended tasks without oracle papers and find that some of the discoveries made by the agents closely match discoveries reported by researchers after the knowledge cutoff date. Together, these results indicate that a suitable environment can enable agents to autonomously make meaningful progress in open-ended scientific discovery.

    ai agent
  277. arxiv:2610.08917 · cs.CL
    CARE: Certifying Acceleration for Vision-Language-Action Inference
    Rui Liu, Tong Zheng, Jindong Gu, Zhipeng Wang

    While vision-language-action (VLA) models have advanced rapidly, running them at every control step remains expensive. Prior work accelerates VLA inference using techniques like action chunking and visual-token pruning, typically evaluating based on latency and average task success. However, acceleration may discard information and break tasks the original policy would solve, a risk hidden by average metrics. Measuring these failures is challenging because action deviations compound over closed-loop trajectories, meaning task failure is only observable across full episodes. We therefore define an acceleration-induced failure via paired rollouts from identical initial conditions, tracking when the reference succeeds but the accelerated policy fails. To manage this, we introduce CARE, an approach for certified accelerator selection. CARE uses paired rollouts on a calibration set to provide finite-sample guarantees that acceleration-induced failure risk stays below a user-specified budget. It deploys the fastest certified candidate, falling back to the reference if none qualify. By relying only on terminal outcomes and measured compute, CARE applies unchanged across diverse acceleration mechanisms, while sequential testing and failure-triggered reference rollouts keep certification affordable. On four LIBERO suites with OpenVLA-OFT, CARE certifies $9.0$--$10.8\times$ speedups while guaranteeing (at $95\%$ confidence) that at least $85.8\%$ of reference-solved episodes are preserved. Under tight budgets, selectors without guarantees exceed the budget in up to $75\%$ of trials, whereas CARE stays within budget and its sequential form uses $78.9\%$ fewer rollouts than exhaustive evaluation. CARE further generalizes to flow-step reduction for $π_{0.5}$, and to Qwen3.5-9B and Llama-3.1-8B agents in Crafter.

    vision-language-actionvlaaction chunkingopenvlalibero
  278. arxiv:2610.08902 · cs.AI
    Agent Plasticity: Measuring Self-Improvement Through Experience
    Harman Singh, Anton Bakhtin, Rulin Shao, Gabriel Synnaeve +7

    AI agents increasingly operate in environments where they can diagnose failures and improve through experience, yet existing evaluations largely measure what an agent can do at a fixed point in time rather than how effectively it learns. Evaluating self-improvement requires answering three questions: does future performance improve and generalize beyond the interactions that enabled learning; how efficiently are new capabilities acquired; and where does the self-improvement process break down? To answer these questions, we study self-improvement in a controlled setting where agents amortize past experience into reusable artifacts that are inherited by future instances. At each checkpoint, we measure performance on training and held-out environment interactions while accounting for learning cost. We introduce agent plasticity, the efficiency with which an agent converts experience into gains in future held-out performance. Across multiple environments, frontier models exhibit sharply different improvement trajectories despite comparable opportunities to learn. Some achieve substantial and persistent gains, while others remain near or below their initial performance, and gains within the training regime often transfer only partially to out-of-distribution conditions. Endpoint capability and acquisition efficiency also diverge: the agent that ultimately performs best need not be the one that improves most efficiently. Tracing failures through the improvement loop further reveals different candidate bottlenecks. Agents with low plasticity often fail to reuse relevant artifacts, whereas more plastic agents may still fail despite reusing relevant artifacts, pointing to limitations in artifact quality, generalization, or application. Evaluating self-improving agents requires measuring not only what they can do, but how effectively they become better through experience.

    agentai agentself-improvingself-improvement
  279. arxiv:2610.08901 · cs.AI
    Sequential Probabilistic Uncertainty Estimation for Parallel Multi-Agent Reasoning Systems
    Tunyu Zhang, Zihao Zhao, Yusong Zhao, Haizhou Shi +4

    LLM-based multi-agent systems (MAS) have attracted growing attention for improving reasoning through interaction among multiple agents. In this work, we focus on parallel multi-agent reasoning systems, where several agents solve the same problem over multiple rounds and aggregate their outputs into a final answer. Despite their strong reasoning performance, uncertainty estimation for such systems remains underexplored: the reliability of a MAS depends not only on individual generations, but also on how agents interact and evolve across rounds. We propose SAUCE (Sequential Agent Uncertainty through Consensus Evolution), a lightweight, training-free uncertainty estimator that formulates MAS uncertainty as sequential inference over a latent system-level belief. SAUCE aggregates round-level agreement and generation-uncertainty signals through a filtering-style update. Across five backbones, five benchmarks, and two MAS protocols, SAUCE improves misclassification detection, selective prediction, and calibration over a broad set of uncertainty estimation baselines, including standard log-likelihood-based methods and MAS-specific estimators.

    agentmulti-agentagent systembenchmark
  280. arxiv:2610.08900 · cs.AI
    Humanize: Judgement Engineering for Agentic Coding
    Sihao Liu, Ligeng Zhu, Zijian Zhang, Dongyun Zou +5

    Agentic coding makes code generation cheap, but reliable completion remains difficult: the agent that writes the code is a weak judge of whether it is done. We present Humanize, a multi-agent orchestration workflow for agentic coding built around judgement engineering: explicit, mechanically enforced decisions at the boundaries between planning, implementation, review, and learning. A human approves a plan contract, a builder agent implements it in rounds, and a reviewer agent from another vendor decides completion; deterministic hooks, not a model, route work between these roles and enforce 72 mechanical gates. Viewed as a Markov chain over repository states, alternating builder and reviewer samples jointly from two models, so a defect survives only if both miss it. We study Humanize through its deployment, 118 public postmortems of real loops, and its applications. Over 68 versions in 108 days, it gathered 1,468 GitHub stars. Applications include a 567-file gem5 build-system migration under upstream review; Kernel Design Agents, which extend the loop with a kernel knowledge base and profiling feedback and placed in the top three of all three Full-Agent tracks of the MLSys 2026 FlashInfer contest; and, through Humanize Olympiad Agents (HOA), full scores in IOI 2026, IMO 2026, IPhO 2026, and IBO 2024, 418.5/437 in IChO 2026 (gold-medal). Humanize also achieves 672/672 on PutnamBench and ranks first (251/303) on Lean-Eval's leaderboard even competiting with professional mathematicians. The postmortems show that independent review catches unsupported builder claims, but stopping remains a key weakness. In reports that separate rounds by phase, two thirds of rounds occurred after implementation was accepted. This evidence is observational, not a controlled comparison of workflows.

    agentmulti-agentagenticleaderboard
  281. arxiv:2610.08895 · cs.AI
    Contextualization of Third-Party Cloud Security Findings
    Leon Goldberg, Gal Engelberg

    Finding severity is the main driver of how security teams prioritize remediation. For third-party cloud security findings, that severity is static: the rule that raised the finding assigns it before the rule meets any environment, so it reflects the risk of the condition in general rather than the risk the finding poses to the concrete environment where it lives. Scoring standards define where environment-specific context belongs. How far that context changes finding severities in production, where the deciding evidence lies, and whether it holds against the live environment have not been measured. We address this gap with contextualization, re-deriving each finding's severity from evidence in the environment where the finding lives. A deep research agent over a precomputed cross-signal asset graph investigates each finding against the resource's state, its graph neighborhood, and other products' signals, and returns an adjusted severity with an evidence trace. We evaluate it in a production field study of 9,967 vendor HIGH findings from two commercial cloud security platforms across eight real production environments, on three criteria: the faithfulness of the facts behind each verdict to the live environment, the dependence of each decision on context beyond the flagged resource, and the regularity of the reasoning. Three in four findings are re-graded, mostly downward, and the same rule often moves in opposite directions inside a single environment. About half of the decisive evidence lies beyond the flagged resource, and read-only probes of live infrastructure confirm the decisive fact for 99.4% of decided findings.

    agent
  282. arxiv:2610.08894 · cs.AI
    Trustworthy Domain-Specific AI for Structured Knowledge Retrieval and Reasoning
    Ryan C. Barron

    This dissertation presents a scalable architecture for transforming unstructured, domain-specific text into structured knowledge for retrieval and reasoning. It integrates semi-automatic corpus curation, semantic structuring, retrieval, and inference into an interpretable pipeline. The research introduces Binary Bleed, an adapted binary search method that reduces low-rank search complexity for Non-negative Matrix Factorization (NMF), and Hierarchical NMF with automatic latent feature selection (HNMFk), a depth-adaptive topic modeling method that produces interpretable taxonomies guided by subject matter experts. These representations populate a typed Knowledge Graph and a semantically aligned Vector Store containing extracted latent features, synchronized through an event-driven substrate. Tensor-Structured Retrieval-Augmented Generation (T-SRAG) dynamically routes queries across retrieval paths. Contrastive alignment maps document and query embeddings to hierarchical topic structures to improve semantic fidelity and reduce hallucinations. Beyond retrieval, tensor-based link prediction identifies and completes missing links in the Knowledge Graph, supporting inference grounded in citation structure. Applications across cybersecurity, law, materials science, and healthcare demonstrate improvements in retrieval precision, early trend detection, hypothesis generation, and hallucination mitigation. The dissertation provides a deployable, modular foundation for trustworthy, domain-specific AI systems that retrieve and reason over structured knowledge.

    retrieval-augmentedknowledge graph
  283. arxiv:2610.08892 · cs.AI
    Hybrid++: The Bridge between PDE Models and Deep Learning for Gamma Noise Removal
    Mahipal Jetta, Sujato Dutta

    Multiplicative gamma noise is one of the dominant noise factors in Synthetic Aperture Radar (SAR) and medical ultrasound images. They are dependent on pixel level noises due to which they are highly varying across the image and harder to handle as compared to additive noise. The denoising methods to address this noise currently include classical partial differential equation (PDE) methods which are good for interpretation but lack the restoration ability as compared to the state-of-the-art models while deep convolutional networks like DnCNN achieve high performance but at the cost of transparency due to which practitioners are skeptical to use them in high-risk critical fields like medicine. This paper presents Hybrid++, a novel trainable nonlinear reaction-diffusion architecture that addresses both the concerns - staying interpretable while offering performance close to huge black-box models. It combines a fully learnable PDE initialization with a 3-stage reaction-diffusion network having 64-channel multiscale filter banks, 4-layer Squeeze-and-Excitation attention-based influence functions and a 64-dimensional noise level embedding. It uses a two-phase training strategy, stage-wise optimization followed by joint end-to-end refinement which enables co-adaptation of all learnable parameters. On the FoE benchmark, Hybrid++ substantially improves over classical PDE, BM3D and the original TNRD baselines. In the severe-noise setting L=1, it comes within 0.23 dB PSNR of a separately trained DnCNN while using only about 8% of its parameters. We therefore position Hybrid++ not as a universal state-of-the-art image restoration backbone, but as a compact, physically structured reaction-diffusion model for multiplicative gamma noise.

    benchmark
  284. arxiv:2610.08882 · cs.AI
    FinVector-Market-4B: A Controlled Study of LoRA Adaptation for Structured Financial Tasks
    Alina Khaybullina

    FinVector-Market-4B adapts Qwen/Qwen3.5-4B with rank-16 LoRA on a 22,000-example corpus for structured financial tasks. We evaluate the base and adapted models on the same 600-example benchmark under implicit and explicit JSON-schema contracts. Supplying the schema alone raises base-model JSON validity from 0% to 91.3%. Under matched explicit prompting, the frozen scores improve from 14.7% to 40.0% for FinQA answer exact match, from 48.0% to 82.7% for calculator-expression correctness, from 20.1% to 89.5% for scenario branch-label agreement, and from 52.4% to 87.2% for implication-direction agreement. A post-hoc policy-scoring audit shows that the reported macro-F1 decline reflects a changing label set; using the same three target classes gives 77.4% for the base and 83.1% for the adapter. Filing overlap and calculator-target inconsistencies qualify the benchmark's generalization claims. The results show that compact financial domain adaptation can produce substantial task-specific gains beyond output-format learning under matched prompting, with gains bounded by the evaluated task distribution and prompt contract.

    benchmark
  285. arxiv:2610.08875 · cs.AI
    An Empirical Study of Agent Skills' Downstream Utility
    Yu Cheng, Dehai Zhao, Zhongxin Liu, Qing Huang +2

    Agent Skills package procedural guidance and resources for reuse, but a relevant Skill does not necessarily improve task performance. Existing studies characterize Skill content and evaluate downstream performance, yet provide limited explanations of how utility depends on content, execution configuration, and multi-Skill organization. We conduct an empirical study on 87 SkillsBench tasks, defining downstream utility as the pass-rate difference from No-Skill on the same tasks under the same model--harness configuration. We compare the same Skills across nine configurations, then examine alternative published Skills and organizations of fixed Skill sets under three selected configurations. We retrieve marketplace candidates from a curated corpus of 37,596 Skills. LLM-assisted analysis of content, execution traces, and final artifacts, followed by author review, relates provided support to actual use and task outcomes. The same Skills help some configurations and hurt others on 36.78\% of tasks, with trajectories showing that recommended procedures can become an execution burden. Relevance rankings overlook more useful candidates. Within the evaluated candidate sets, reranking by support for required operations raises first-choice pass rates by 4.35--5.80 percentage points across the three configurations. We derive 17 authoring practices linking executable procedures to recovery, preservation of task requirements, and checks on final artifacts. Stage Plan and Dependency DAG outperform use order alone, with DAG's additional benefits concentrated in tasks supplied with five or six Skills. These findings guide developers to assess usable operation support, allow procedure adaptation while preserving task requirements, and make artifact dependencies explicit when organizing Skills.

    agent
  286. arxiv:2610.08871 · cs.AI
    CredLeakBench: Evaluating Credential Leakage and Recovery in LLM Agents
    Rafid Ahmed, Joseph Fioresi, Mubarak Shah, Yuzhang Shang

    Language model agents are increasingly deployed to automate everyday digital chores from managing emails and social media to handling banking and bills allowing users to step away from supervision. However, this capability also exposes sensitive information to phishing. Safe execution requires distinguishing malicious requests from genuine ones without simply refusing to act. Despite its practical importance, this problem remains underexplored and it is unclear whether current agents or existing defenses can achieve it. To study this problem, we first propose CredLeak-Bench, a comprehensive benchmark designed to evaluate how effectively and securely agents automate human workflows when confronted with phishing and identity verification. The benchmark covers both user-directed authentication and autonomous inbox monitoring, where agents are not explicitly instructed to log in. It systematically varies deceptive cues and pairs phishing scenarios with legitimate counterparts, enabling joint evaluation of information leakage and utility on genuine tasks. Within a sandboxed environment, leakage is measured through actual submissions of information rather than agents' self-reported behavior. Our evaluation reveals that all tested models are vulnerable to leakage. Agents also disclose sensitive information during autonomous inbox monitoring, demonstrating that phishing can induce disclosure without a user request to authenticate. Furthermore, most evaluated mitigations that reduce leakage also impair performance on genuine tasks, exposing a security utility trade off in existing defenses. These findings show why reducing leakage alone is insufficient: effective defenses must prevent unauthorized disclosure while preserving legitimate task completion. CredLeak-Bench provides a controlled framework for measuring both objectives and evaluating progress toward secure, useful agents.

    llm agentbenchmark
  287. arxiv:2610.08870 · cs.RO
    From Wearable Interfaces to Dexterous Policies: Contact Shifts and Tactile Representations
    Ruitong Tian, Fang Xu, Noah B. Wilson, Xianyao Li +1

    Unlike conventional teleoperation, wearable interfaces allow operators to collect dexterous demonstrations through their own hand motions while directly interacting with task objects. This direct interaction reduces dependence on the target robot during collection, but it also makes the collection hardware part of the physical process that generates each demonstration. Interface geometry can influence both how a task is performed and what tactile observations are recorded for learning. We study two versions of a DexUMI-family exoskeleton that share the same robot command definition, mapping procedure, and tactile module type but differ in hand-side geometry. The revised interface reduces reported physical demand, improves selected device ratings, enables tactile access in a precision grasp that is mechanically blocked by the baseline, and produces task-dependent changes in recorded contact. Lid twisting primarily exhibits a change in contact location, whereas egg carton opening primarily exhibits a change in contact occurrence. We then train matched policies using either a binary aggregate input or a spatial-plus-force input. On lid twisting and egg carton opening, policies trained on revised-interface demonstrations achieve higher success than those trained on baseline demonstrations, with a significant pooled interface effect. Across these and two additional tasks, USB insertion and soldering tool pick and place, the spatial-plus-force input likewise outperforms binary aggregation. These results show that wearable collection hardware is part of the data-generation process for robot learning. Such interfaces should therefore be evaluated not only through operator experience, but also through the tactile interactions they make recordable and the policy performance their demonstrations support.

    dexterousteleoperationtactilegrasp
  288. arxiv:2610.08863 · cs.RO
    Trajectory Planning without Trajectory Data: A Manifold-Guided Approach
    Silong Yong, Anji Liu, Cunxi Dai, Carl Busart +4

    A common way for trajectory planning is to leverage generative models trained on large collections of expert trajectories. At inference time, the model generates executable trajectories by conditioning on task goal constraints. However, trajectory-based methods rely on costly supervision, scale poorly with sequence length, and often generalize poorly to unseen constraints such as novel start-goal pairs. We propose an alternative to learn the underlying state-space manifold and use the geometry of the manifold for trajectory planning. This approach requires only state observations and enables generalization to unseen constraints by con- structing trajectories on the learned manifold of the state space. Experiments on Maze2D and robotic motion-planning benchmarks show that Ariadne constructs feasible paths from state-only supervision and generalizes to unseen start-goal combinations. On high-dimensional dual-arm planning, it remains competitive with trajectory-supervised and classical planners, while requiring no trajectory data for training.

    benchmark
  289. arxiv:2610.08862 · cs.RO
    CIRRA: Dual-Level Continual Instruction Reconciliation with Ongoing Execution for Embodied Robot Agents in Interactive Household Tasks
    Ci Zhang, Enfu Nan, Arman Akbari, Lin Zhao +5

    Household robots must accommodate new user instructions while executing ongoing tasks. Existing agents often regenerate or extensively revise the remaining task sequence, introducing plan ambiguity, logical inconsistency, and redundant execution. We formulate continual instruction reconciliation and propose CIRRA (Continual Instruction Reconciliation for Robot Agents), a dual-level framework combining LLM-based semantic reasoning with rule-constrained structural integration. CIRRA first grounds incoming instructions to unique executable skills and resolves underspecified actions and execution locations. It then preserves the ongoing subtask sequence as an execution backbone and generates integration candidates by inserting incoming subtasks into location-matched segments. The semantic reasoner evaluates only modified segments to identify dependencies and conflicts and select the most logically coherent local integration. This structure-preserving process maintains alignment with ongoing execution, mitigates ambiguity and inconsistency, and reuses shared subtasks to reduce redundant execution. We also introduce CHIRP (Continual Household Instruction Reconciliation and Planning), a text-based benchmark of 120 episodes across eight household environments and six categories of everyday activities. On CHIRP, CIRRA achieves 74.2% decision agreement, exceeding the strongest replanning baseline by 30 percentage points; every correct fusion decision yields a correctly placed, conflict-free schedule. On a Unitree G1 humanoid, CIRRA interrupts ongoing skills at the correct moment in every trial and significantly outperforms all baselines on every metric.

    embodiedhumanoidbenchmark

02 US SEMI · SEC 8-K FILINGS

1 items

scanned: NVDA / AVGO / MRVL / COHR / LITE / AMD / TSM / SMCI / ANET / CRDO / POWL / VECO

  1. $SMCI · 8-K · filed 2026-10-08
    Super Micro Computer Inc
    Items: 5.02,9.01
    8-K

03 HUMANOID · COMPANY NEWS

54 items

scanned: figure-ai / 1x / boston-dynamics / unitree / apptronik / sanctuary-ai / neura-robotics / agility-robotics / physical-intelligence / agibot

04 CN PHOTONICS · ANNOUNCEMENTS

0 items
China sources are not connected yet.