Autonomous
-
After the Attacker Leaves: Benchmarking Carryover Attacks on LLM Agents
2026-10-20 15:55:05Zhiyue Xu, Xukai Wang, Zhiyuan Huang, Mingjie Zhan, Jian Zhao, Xu-Yao ZhangAbstract
Modern LLM agents persist state across sessions via two channels: long-lived memory files silently prepended to the system prompt, and scheduled tasks waking the agent without user input. A one-time indirect prompt injection committed to either channel can re-fire across sessions long after the attacker leaves, threats we term carryover attacks. Existing prompt-injection benchmarks evaluate attacks only in the session where malicious content is first observed, leaving the gate governing when and how often a planted payload later re-fires unmeasured. We present CarryoverBench: 12 personal-assistant scenarios and 101 attack tasks across three trigger channels: Instant, same-turn IPI; Autonomous, heartbeat-scheduled; and Latent, memory-resurfaced. A rule-based verifier scores planting and triggering as independent stages. Across five frontier models, planted payloads re-fire without measurable decay over five rounds; conditional on successful planting, the trigger stage often provides little additional protection. Porting the Latent channel to a second runtime, Hermes, attenuates but does not eliminate the effect, suggesting that carryover defense requires runtime-layer controls in addition to prompt-level interventions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28425
PDF
-
Auto-Director: Leveraging Multi-Agent Collaboration for Autonomous Video Editing
2026-10-20 15:11:55Yuxia Chen, Wenbo Zhu, Yangguang Ji, Zhenxiang Jiang, Teng Zhong, Yu ZhangAbstract
Autonomous video editing from open-world resources remains a challenging problem in multimedia content creation. Retrieval-based methods are constrained by fixed source material and lack creative flexibility, while generative models struggle with long-horizon coherence and often diverge from user intent. Both paradigms fail to replicate the structured, multi-stage reasoning that underlies professional post-production. To address these limitations, we present Auto-Director, a tool-augmented multi-agent framework that mirrors professional editorial workflows: a Planning Agent decomposes abstract topics into fact-grounded scripts via retrieval-augmented planning; a Material Agent indexes open-world footage through shot segmentation and visual tagging; an Editor Agent assembles semantically aligned clips with MLLM-driven spatial adaptation; and a Critic Agent governs an iterative Reflect-and-Revise loop that checks scene-level alignment and pacing. To rigorously evaluate this new paradigm, we introduce VEdit-Bench, a benchmark of 100 expert-curated topics with human-annotated Golden Scripts and a five-dimensional metric suite covering Narrative Logic, Factual Accuracy, Semantic Alignment, Compositional Quality, and Stylistic Cohesion. Extensive experiments demonstrate that Auto-Director significantly outperforms baseline methods in both automated metrics and human evaluation, effectively bridging the gap between amateurs and professional-grade video production.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28346
PDF
-
Interruption-Aware Recurrent Reinforcement Learning for UAS Navigation Under Temporary Overrides
2026-10-20 12:30:41Christopher Conrad, Deepak Panda, Weisi Guo, Antonios TsourdosAbstract
Safe autonomous navigation of UASs requires tactical deconfliction to address conflicts that strategic coordination cannot prevent. This task is challenging under partial observability, when sensor or traffic data are missing, delayed, or degraded. Geometry-based methods can offer separation assurances but face limitations in dense encounters. Recurrent reinforcement learning has therefore been proposed to learn navigation policies that integrate observation-action histories to optimise long-term safety-efficiency trade-offs. However, operational safeguards may require a remote pilot, onboard detect-and-avoid system, or runtime assurance mechanism to temporarily override the learned policy. A research gap remains in understanding how these interruptions affect recurrent policies when the agent regains authority. Benchmark evidence shows that interruptions make task variables less decodable from the recurrent hidden state and increase post-interruption collision risk. The findings suggest that altered recurrent context prolongs post-handback degradation through an action-observation feedback loop, in which changed actions alter the flight path and subsequent recurrent updates. To address this vulnerability, we propose three interruption-aware architectures that condition recurrent processing on interruption context through separate feature streams, dedicated interruption memory, or gated environmental features. Across simulations, all three architectures preserve more decodable task information than a standard recurrent policy. Moreover, the strongest architecture reduces post-interruption collisions by 74% and interruption-induced mission failures by 69% relative to the recurrent baseline, without degrading interruption-free performance. These results show that safe interruption does not guarantee safe handback, and support interruption-aware recurrent design for resilient UAS autonomy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28121
PDF
-
Real-Time Ground Normal Vector Estimation for Spherical Mobile 3D Mapping using LiDAR-Inertial Odometry
2026-10-20 11:30:56Tim Schubert, Fabian Arzberger, Andreas N\"uchterAbstract
Accurate ground plane normal estimation is essential for odometry in spherical mobile mapping systems (SMMS), which face challenges from rapid rotations and limited ground coverage. We propose two RANSAC-based approaches: single-scan estimation with normal vector scoring and multi-step validation, and LiDAR-inertial odometry (LIO)-based estimation using a global 3D map. Evaluated across diverse real-world datasets against terrestrial laser scanner ground truth, results show that LIO-based estimation significantly outperforms single-scan methods in accuracy and robustness. Integrating ground normal estimates into the motion model improves pose estimation, supporting autonomous navigation in challenging and hazardous environments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28701
PDF
-
Reinforcement learning for hardware acceleration and system-level optimization on FPGA and integrated-circuit platforms: A survey
2026-10-20 11:15:34Hamza KheddarAbstract
Reinforcement learning (RL) enables adaptive and autonomous decision-making in embedded, edge, and heterogeneous computing systems. Field-programmable gate arrays (FPGAs) and integrated circuits (ICs) offer low latency, energy efficiency, and architectural flexibility for RL deployment, while introducing challenges in resource constraints, implementation complexity, and hardware-algorithm co-design. This review surveys more than 100 studies on RL implementations across FPGA and IC platforms, emphasizing architectures, implementation strategies, performance evaluation, and applications. The literature is organized by RL family, including model-based Markov decision processes, classical value-based methods, deep RL, actor-critic, policy-gradient, and multi-agent approaches. We further classify studies by abstraction level, hardware realization strategy, and application domain, examining how RL algorithms map onto reconfigurable and fixed hardware. Unlike surveys restricted to particular algorithms or platforms, this work provides a unified analysis of FPGA and IC implementations, covering acceleration, reconfigurable architectures, energy-aware control, and system-level optimization. Comparative assessments consider resource utilization, latency, throughput, power consumption, and reported performance gains. Finally, we identify recurring architectural patterns, practical limitations, open challenges, and research directions for efficient RL-driven hardware systems. The survey offers a consolidated reference for researchers developing and evaluating RL solutions on specialized hardware.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28699
PDF
-
Differentiable Task-Driven Coded Aperture Camera Design with 3D Gaussian Scene Representations
Abstract
Camera design heavily influences perception task performance, yet cameras are typically designed by domain experts through costly experimentation, in isolation from the tasks they serve. Existing joint-design methods either rely on differentiable simulation limited to pre-captured 2D images, restricting them to optics or image-processing pipeline design, or use non-differentiable camera simulators optimised with derivative-free or reinforcement-learning methods that scale poorly with the number of design parameters. We present a differentiable framework for jointly designing complex camera systems and downstream perception tasks. We use it to design two coded-aperture depth-from-defocus cameras, a monocular and a stereo configuration, by jointly optimising the coded aperture mask, camera parameters, and a depth estimation network end-to-end. Our framework represents scenes with 3D Gaussian Splatting reconstructed from real-world captures, providing a differentiable image formation process for gradient-based optimisation over design spaces intractable for prior differentiable approaches. Results demonstrate that our differentiable method improves over existing coded aperture design and non-differentiable camera design baselines, offering a step forward in automated and principled camera design for autonomous systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28004
PDF
-
Muse Glimmer 30B: An On-Device Agentic Model
2026-10-20 10:14:52Arash Ebrahim Abtahizadeh, Muna Aghamelu, Adil Ahmed, Juan C. Angeles Acuna, Alexis Audran-Reiss, Asaf Avrahamy, Yoram Bachrach, Can Balioglu, Amar Budhiraja, Onur \c{C}elebi, Gaurav Chaurasia, Joy Chen, Lynn Cherif, Lucia Cipolina-Kun, Gal Cohen, Timoth\'ee Darcet, Beto de Paola, Digant Desai, Sam Devlin, Derek Dunfield, Ivan Evtimov, Maryam Fazel-Zarandi, Rob Fergus, Jean-Christophe Gagnon-Audet, Grant Gardner, Bhavul Gauri, Paris Giampouras, Sujan Kumar Gonugondla, Antoine Grosnit, Young Han, Michael Hassid, Monuril Islam, Masoud Jalili Sabet, Songhao Jia, Narine Kokhlikyan, Svetlana Kurtsman, Sandra Lefdal, Chee Hau Leow, Noam Levi, Mike Lewis, Sanae Lotfi, Xiyang Luo, Despoina Magka, Saeed Mahloujifar, Neal Mangaokar, Ishita Mediratta, Alexander H. Miller, Hela Momand, Saba Nazir, Kelvin Niu, Mattia Opper, Parth Pathak, Alberto Pepe, Danielle Pintz, Mikhail Plekhanov, Sidhartha Reddy Potu, Anton Protopopov, Shengyi Qian, Shashank Rajput, Joseph Rocca, Scott Roy, Luca Sbordone, Amin Shakeri, Tatiana Shavrina, Michael Shvartsman, Ruan Silva, Anya Sims, Eric Michael Smith, Hugo Touvron, Mabel Ubong, Isabel Urrego, Yanzheng Xiang, Zhiyuan Yao, Alex Yarmula, He Ye, Jade Yu, Luke Zettlemoyer, Arman Zharmagambetov, Perpetua Fathima Ahlijah, Tremo Ahmed, Enrique Alfonseca, Pedram Bashiri, Nikolay Bashlykov, Amine Benhalloum, Aaron Berman, Rohith Bhatia, Siddharth Bhattacharya, Prashant Bhende, Chloe Bi, Shuchao Bi, Clement Anthonioz Blanc, Allen Bolourchi, Iva Simon-Bubalo, Pere-Llu\'is Huguet Cabot, Andrea Caciolai, Erica Cai, Xiang Tony Cao, Yue Cao, Andrew Caples, Jinzhao Chang, Lele Chen, Moya Chen, Weijie Chen, Wenhu Chen, Xiaobai Chen, Yinyin Chen, Zhengxing Chen, Wei Cheng, Pavel Chikulaev, Edward Chou, Sy Choudhury, Brian Clerkin, Marta R. Costa-juss\`a, Hanjun Dai, Curtis Davis, Myra Deng, Tiffany Siqi Deng, Dujian Ding, Hantian Ding, Shuangrui Ding, Jesse Dodge, Carl Domond, Shweta Doshi, Shirin Eghtesadi, Faith Eischen, Athyu Eleti, Jordi Armengol-Estape, Alex Fabbri, Han Fang, Paula Farani, Aiman Farooq, Darius Feher, Christoph Feichtenhofer, Amanda Felix, Romain Froger, Carl Chengyan Fu, Sean Gahagan, Yifan Gao, Itai Gat, Jannes Gladrow, Akashdeep Goel, Ahuva Goldstand, Bo He, David Heineman, Dylan Herman, Irene Hjelt, Joonas Hjelt, Alexander Holz, Rui Hou, Annie Hu, Yuan-Ting Hu, Bernie Huang, Jing Huang, Kun Huang, Ashley Hunter, Srinivasan Iyer, Somya Jain, Bei Jia, Michael Jiang, Song Jiang, Wenwen Jiang, Lin Jin, Jacob Kahn, Melanie Kambadur, Yingxin Kang, Justine Kao, Stephane Kasriel, Hossein Kavianihamedani, Madian Khabsa, Ameya Khandekar, Yash Khare, Gefen Kohavi, Kavya Kopparapu, Praveen Krishnan, Venu Kuchibhotla, Ananya Kumar, Leona Lan, Jack Lanchantin, Hunter Lang, Nikolay Pavlovich Laptev, Yuanzhi Li, Yunlu Li, Asad Liaqat, Johnson Lin, Runwei Lin, Zhichao Lin, Shaun Lindsay, Yaron Lipman, Frederick Liu, Mengchen Liu, Qiang Liu, Yinghai Lu, Yujie Lu, Christopher Luc, Faye Ma, Pingchuan Ma, Tengyu Ma, Wufei Ma, Xiaodong Ma, Damir Maksyutov, Josh Malone, Udeep Manchanda, Thomas Mann, Kalyani Marathe, Akhil Mathur, Roberto-Rafael Maura-Rivero, Ruslan Mavlyutov, Thomas Mesnard, Gregoire Mialon, Julian Michael, Sagar Miglani, Todor Mihaylov, Naureen Mitha, Archi Mitra, Leo Mok, Naila Murray, Muthukumaravel Muthuraman, Mergen Nachin, Nese Demir Nalci, Saaketh Narayan, Alyssa Newcomb, Peter Ney, Joycelyn Ng, Devin Norder, Maxwell Nye, Rajvardhan Oak, Cody Ohlsen, Artidoro Pagnoni, Yi Pan, Nilesh Pandey, Guan Pang, Richard Yuanzhe Pang, Mahesh Pasupuleti, Parth Patel, Yash Patel, Vladan Petrovic, Leslie St. Pierre, Norman Ponte, Yundi Qian, Zengyi Qin, Jack Rae, Ramya Raghavendra, Emmanuel Ramirez, Nikhila Ravi, Hongyu Ren, Riandy Riandy, Harrison Rudolph, Kalyan Saladi, Eduardo S\'anchez, Karthik Abinav Sankararaman, Alan Schelten, Thomas Scialom, Aman Shankar, Paresh Shenoy, Alana Shine, Hamid Shojanazeri, Mitesh Kumar Singh, Pawan Sisodiya, Ali Sol, Sten Sootla, DiJia Su, Suraj Subramanian, Brian Sun, Tony Sun, Zhiqing Sun, Natacha Supper, Jason Talpalar, Ellen Xiaoqing Tan, Liang Tan, Bu\u{g}ra Tekin, Jean-Christophe Testud, Parth Thakkar, Joseph Tighe, Ty Toledano, T Tse, Igor Tufanov, Alex Vaughan, Josh Walters, Alex Wang, Bethany Wang, Meng Wang, Rocky Wang, Weiyue Wang, Xiaolan Wang, Xin Wang, Zijian Wang, Bram Wasti, Quentin Wellens, Yeming Wen, Mary Williamson, Yuncheng Wu, Fei Xia, Tian Xie, Anlu Xing, David Xu, Jacob Xu, Puxin Xu, Zheng Xu, Shen Yan, Megan Yang, Yining Yang, Nick Yannopoulos, Kevin Yao, Michihiro Yasunaga, Haoxuan You, Michael You, Dingli Yu, Tianhe Yu, Yue Yu, Summer Yue, Xiang Yue, Shuwei Zeng, Hanwen Zha, Chen Zhang, Fred Zhang, Hongming Zhang, Kaiyu Zhang, Meng Zhang, Mingyang Zhang, Yi Zhang, Shengjia Zhao, Chao Zhou, Claire Zhou, Shuyan Zhou, Yanjun Zhou, Yaxuan Zhou, Jiacheng Zhu, Rosalie Zhu, Yun ZhuAbstract
We introduce Muse Glimmer, an open-source 30B parameter causal language model with perception encoder, purpose-built for autonomous agentic tasks on consumer hardware. Muse Glimmer integrates multi-step reasoning, reliable tool use and failure recovery into a single model that runs locally on consumer devices without requiring cloud infrastructure. The model accepts text and image inputs and produces text outputs, was trained on data from over a hundred languages, and is quantized to approximately 4-bit precision for efficient single-GPU inference. Muse Glimmer achieves state-of-the-art performance for its size class on agentic benchmarks, setting a new standard compared to the models of its size: Gemma4-31B and Qwen3.6-27B on tool use, multi-step planning, and agentic task completion. We release the model under the Apache 2.0 license to foster open-source development of capable, safe, local AI agents.
Abstract (translated)
URL
https://arxiv.org/abs/2610.24628
PDF
-
Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay
2026-10-20 09:59:12Byeonghun Bang, Sangwoo Park, Jinheon Baek, Kangsan Kim, Youngwan Lee, Sung Ju HwangAbstract
Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse operations. However, such agents remain fragile in long-horizon settings, where errors accumulate and executed actions leave unintended side effects, making the ability to recover from failures critical. Yet, existing remedies remain inadequate: environment resets are infeasible in proprietary settings, action replay is prohibitively expensive over long horizons, and API-based rollback is limited to web environments, leaving model-based recovery largely unexplored. To address this gap, we present ReTrace, a scalable evaluation framework for systematically studying recovery behavior in computer-use agents. We formalize Transition-Consistent Recovery: identical downstream actions from the recovered and target states must yield identical outcomes. We operationalize this criterion through goal-oriented action replay following controlled error injection. Using ReTrace, we present the first systematic study of autonomous, model-based recovery, revealing that (i) ideal recovery can unlock model's latent task completion capabilities, (ii) current computer-use agents fail to exploit their latent recovery capabilities, and (iii) accurate model-based recovery yields measurable end-to-end gains. Together, these findings establish recovery as a fundamental capability for building reliable computer-use agents. Our code and dataset is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27954
PDF
-
PCLA-Bridge: A Framework for Cross-Domain Deployment of CARLA Agents
2026-10-20 09:53:57Masoud Jamshidiyan Tehrani, Jinhan Kim, Paolo TonellaAbstract
Most high-performing end-to-end autonomous driving agents (ADAs) are developed for the CARLA Leaderboard, tightly coupling them to CARLA's APIs, sensor layouts, coordinate systems, and internal clock. Reusing these models on real datasets, alternative simulators, or physical platforms necessitates substantial manual re-engineering. We present PCLA-Bridge, a deployable tool that runs unmodified CARLA Leaderboard agents from any sensor source to any control destination without an active CARLA server. With PCLA-Bridge handling dependency isolation, tensor marshalling, routing, and synthetic timing, integrators only need to provide a minimal interface. We validate the tool across two operational paradigms: offline replay on in-domain CARLA recordings and real-world nuScenes logs, and live closed-loop control across three diverse simulation engines: MetaDrive, AWSIM, and AlpaSim. We analyze the lightweight integration requirements for each platform, highlighting output translation (such as converting agent actions into target trajectory formats) and coordinate-frame transformations, showing that integration requires minimal glue code rather than structural changes. All eight evaluated agents execute across all three simulators without modification, confirming the reliability of PCLA-Bridge and establishing a foundation for systematic sim-to-real, cross-sim, and security testing.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28696
PDF
-
Enumeration-Guided Training of Neural Hamilton-Jacobi Safety Certificates
2026-10-20 08:50:55Mihaela-Larisa Clement, Tosca Pierro, Ezio Bartocci, Luca MarzariAbstract
Hamilton-Jacobi (HJ) reachability analysis offers formal safety guarantees for control systems, but training accurate neural certificates remains difficult, particularly when unsafe regions are hard to characterize. We propose a verification-guided training framework that addresses this by using probabilistic enumeration of safety constraints to detect forward-invariance violations, i.e., states where the learned certificate incorrectly classifies unsafe behavior. This produces a compact, targeted set of counterexamples that more precisely captures the failure boundary than inputs generated by standard adversarial attack methods. Crucially, using this representation to fine-tune a pretrained HJ value function yields larger certified regions and reduces certification time across all tested benchmarks. We further introduce a shielding mechanism based on the refined certificates to enforce safety constraints at deployment time. We evaluate the proposed safety filter in a realistic, physics-based Isaac Sim environment and through real-world autonomous racing experiments, achieving zero safety constraint violations compared to a nominal controller and a backup policy based on Linear Quadratic Regulation (LQR). These results demonstrate the effectiveness of the proposed shielding mechanism in ensuring safe operation under high-speed, safety-critical conditions.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27870
PDF
-
RSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?
2026-10-20 06:57:59Kaiwen Zhou, Udari Madhushani SehwagAbstract
Recursive self-improvement, in which frontier AI models work on training the next generation, is quickly becoming a reality. However, the safety of this process has received far less attention than it should. A misaligned model training its successor can shape what that successor knows, how it behaves, and what it wants, and the harm carries forward into the next generation. We study this risk through the lens of AI control. We introduce RSI Control Arena, a testbed in which a frontier model, acting as an autonomous R\&D agent, is given a benign main task from a stage of a successor model's training pipeline together with a covert side task to install a misaligned property in the successor. The testbed contains 16 side tasks in three classes, forming 22 task pairs with main tasks that span the pipeline from data curation to reinforcement learning. We evaluate six frontier models as agents against LLM monitors that read the transcript of the run and the agent's reasoning. We observe that every model completes a substantial share of the side tasks without degrading the main-task performance, including side tasks that make the successor itself a better saboteur. Under minimal instructions to stay covert, models already produce successful attacks that monitors fail to detect, and providing a short list of evasion tactics further reduces the detection rate. Monitors with access to agent's reasoning detects most attacks, but not all. Our results indicate that recursive self-improvement raises significant safety concerns, and that strong safety effort should be in place before models are trusted with greater responsibility of training their successors.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27735
PDF
-
Prescribed Performance Guided Safe Reinforcement Learning for Roundabout Navigation of Autonomous Vehicles
2026-10-20 06:54:57Wenhan Li, Yangrui Zhang, Hang Zhou, Peiran Liu, Yiding JiAbstract
Connected and Autonomous Vehicles (CAVs) face significant challenges in roundabout navigation due to dense traffic interactions and unpredictable agent behaviors, necessitating high levels of adaptability and safety. While the combination of Reinforcement Learning (RL) and Model Predictive Control (MPC) offers a promising approach, existing frameworks suffer from a structural mismatch where pointwise RL decisions fail to align with MPC's trajectory level optimization, and often lack rigorous safety guarantees. This work proposes RLTrajGen-PPMPC-CBF, a hierarchical framework for safe, smooth and comfort roundabout navigation, which regulates the coupling between RL-based planning and MPC-based control. We employ Prescribed Performance Constraints (PPC) to enforce a gradual, stable convergence between reference trajectories and control outputs, ensuring MPC tracking performance remains consistent with intended behavior from RL. Additionally, a Control Barrier Function (CBF) layer provides real-time safety corrections that are fed back into the RL process. Simulation results in the MetaDrive environment demonstrate that our method achieves a 6.25\% increase in average success rate and a 65.87\% reduction in Motion Sickness Dose Value (MSDV) compared to the optimal baseline, meanwhile accelerating training convergence.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27732
PDF
-
From Debate to Decision: Conformal Social Choice for Safe Multi-Agent Deliberation
2026-10-20 05:19:34Mengdie Flora Wang, Haochen Xie, Guanghui Wang, Aijing Gao, Guang Yang, Ziyuan Li, Qucy Wei Qiu, Fangwei Han, Hengzhi Qiu, Yajing Huang, Bing Zhu, Jae Oh WooAbstract
Multi-agent debate improves LLM reasoning, yet agreement is not evidence of correctness. When agents converge on a wrong answer through social reinforcement, consensus stopping commits that error to automated action with no recourse. We introduce Conformal Social Choice, a post-hoc layer that converts debate outputs into calibrated act-versus-escalate decisions. Verbalized probability distributions from heterogeneous agents are aggregated via a linear opinion pool and calibrated with split conformal prediction, yielding fixed-round marginal coverage: at any pre-specified round, the correct answer is included with probability ${\geq}\,1{-}\alpha$, without assumptions on individual model calibration. A hierarchical action policy maps singletons to autonomous action and larger sets to human escalation. Across eight MMLU-Pro domains and two additional benchmarks, fixed-round coverage stays close to target. The key finding is not that debate becomes more accurate, but that the conformal layer makes its failures actionable: at the final round, 81.9\% of wrong-consensus cases are flagged by non-singleton sets at $\alpha{=}0.05$. Separately, among cases that reach a singleton before the final round, accuracy reaches 90.0--96.8\% on MMLU-Pro (up to 22.1pp above consensus stopping): a selection effect, not a reasoning improvement. Simple probability- and entropy-threshold rules attain comparable interception; conformal's distinct value is a finite-sample fixed-round coverage guarantee together with explicit candidate sets for escalation. Adaptive first-singleton stopping is evaluated empirically and not covered by this guarantee.
Abstract (translated)
URL
https://arxiv.org/abs/2604.07667
PDF
-
Does Multi-Agent Collaboration Pay When Agents Serve Users? Testing Agent Scaling in Dual-Control Settings
2026-10-20 05:13:13Ethan Yang, Xiangcheng ShiAbstract
Multi-agent systems (MAS) built from language models are deployed on the premise that collaboration beats a single-agent system (SAS), yet when it pays is unclear. The most systematic study to date gives a capability-saturation rule: coordination helps while the SAS is weak and hurts once it is strong, with the crossing near 45% single-agent accuracy. That rule was derived on autonomous benchmarks, where no user takes part. We test it where agents now work: in conversation with a user under a written policy, on $\tau^2$-bench, the dual-control benchmark. On its airline, retail and telecom domains we compare the stock SAS with a centralized MAS built from the same model for six models from three families, over about 7,950 simulated conversations, with one completion-token ledger per episode per system. The study was pre-registered with a public change log; the MAS is reported as built, with one validity bar unmet (its planner never saw the tool schemas). Under a fixed simulated user no cell shows a MAS benefit: the MAS is worse in 12 of the 13 valid cells and tied in the thirteenth, and the fitted gain is negative across the observed capability range (weighted mean -28 points, 95% CI [-44, -12]). On the two cells where the rule predicts a benefit, the MAS loses by 13 and 22 points, and without a budget ceiling it at best draws level at 5.5 times the SAS's token spend. The one gain appears on the cell nearest 45%, under a second simulator. Whether the gain declines with capability is unresolved (slope -0.41, 95% CI [-1.51, +0.68]), because model-by-domain effects dominate. The MAS does not detectably reduce wrongful database writes; it converts other failures into budget exhaustion and inaction. For agents that serve people, the SAS is the default; a multi-agent design must show compute-matched evidence from the setting itself. We release all trajectories, ledgers, prompts and code.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27655
PDF
-
Local Allow, Global Deny: Why Per-Action Authorization Does Not Compose in LLM Agents
2026-10-20 04:35:39Anmol Pandey, Aditya Jain, Liang Chen, Carsten MapleAbstract
Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolation. We show that local authorization does not compose into global authorization. A compositional authorization failure (CAF) is a locally authorized execution, or a pair of locally authorized executions, that violates a global policy spanning intent, purpose, provenance, consent, and delegation. We characterize CAFs along two axes, expressiveness (single-trace safety versus relational k-safety) and observability (a ladder of monitor profiles). Our central result is an impossibility: relational purpose violations form a 2-safety hyperproperty with no per-trace locus of blame, so a per-action monitor that never raises a false alarm detects none of them, independent of the underlying model or decision procedure; they become visible only under cross-execution monitoring, which none of the six guardrails we survey implements. We make this constructive with AL-SYNTH, a SAT/SMT synthesizer (using no language model) that emits minimal CAF witnesses, each checked against an exhaustive oracle. The empirical signature is sharp: across nine LLM judges the per-action view approves the synthesized witness almost without exception, blocking it at a rate comparable to a benign control, yet the same models flag it when shown the two executions together. Per-action authorization is therefore structurally insufficient for relational policy conjuncts not reducible to single-trace safety: to bound them, a monitor must compare executions or accept false alarms.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27620
PDF
-
JARVIS: From Visual Manuals to Autonomous Robotic Assembly
2026-10-20 04:32:37Fan Ding, Fucai Ke, Kevin Yuchen Ma, Xuewen Luo, Wenyu Liang, Vishnu Monn Baskaran, Hamid Rezatofighi, Yan WuAbstract
Visual manuals communicate procedural knowledge through stepwise diagrams, but translating these instructions into reliable long-horizon robotic execution remains challenging. We introduce JARVIS, a method-agnostic benchmark for autonomous visual-manual-guided execution without additional language instructions. JARVIS comprises 236,679 LEGO assembly tasks across 8,987 scenes, with a carefully curated JARVIS-v1 suite of 50 tasks for interactive robotic evaluation. Tasks span varying initial structural complexities and assembly horizons, requiring agents to interpret manuals, ground actions in an evolving workspace, and execute the intended procedure. A structure-aware evaluation protocol captures geometric accuracy, structural relations, construction order, partial progress, and completion. We further introduce JARVIS-agentic, a tool-grounded embodied agent that composes robot primitives into executable programs and uses execution feedback for verification and recovery, without task-specific action trajectories or model parameter updates. Across nine multimodal and reasoning models, task-oriented primitives increase the average assembly score. Performance nevertheless declines sharply with assembly horizon, and execution errors remain difficult to correct. Prior-task experience improves initial performance, while repeated reflection provides inconsistent benefits, highlighting persistent limitations in connecting visual procedural reasoning with reliable physical execution.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27618
PDF
-
Provisioning Robust and Efficient LiDAR Perception for Autonomous Driving
2026-10-20 04:31:30Tingxu Han, Zijie Shen, An Guo, Lyuke Wang, Chunrong Fang, Zhenyu Chen, Wei SongAbstract
LiDAR-based 3D object detection is a core perception service for autonomous driving, but deployment requires robustness to point-cloud corruption while meeting latency and memory requirements. Existing approaches address robustness and resource efficiency separately, resulting in compact detectors that are fragile under corruption or robust detectors that remain costly to deploy. We therefore formulate LiDAR perception provisioning as constructing a detector that remains accurate under point-cloud corruptions while meeting constraints on inference latency and peak GPU memory. To achieve robustness, we first craft corrupted samples that mimic extreme weather conditions. Then we train candidate detectors offline by ordering clean and corrupted samples by perturbation sensitivity, through which detectors learn more from hard corrupted samples. We estimate perturbation sensitivity using an ensemble of seven heterogeneous 3D detectors by tracking changes in confidence, BEV overlap, and unmatched detections. To improve efficiency, we narrow the network and use offline neighborhood-density measurements to determine how many points and neighbors each sampling stage processes. We evaluate our method using AP (Average Precision) under clean and corrupted conditions, inference latency, and peak allocated GPU memory. On KITTI for Car detection with PointRCNN, our method improves Moderate AP under corruption by 3.32 points over the original detector while reducing mean latency by 19.8% and peak allocated GPU memory by 53.9%. Across two datasets, two detector architectures, and three object classes, our method improves AP under corruption by 4.03 points on average over the corresponding original detectors, while reducing mean inference latency and peak allocated GPU memory by 14.4% and 38.0%, respectively. Our code is available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27617
PDF
-
WORTH Benchmark: Evidence Discovery under Not-Fully-Cooperative Information -- A Two-Episode Pilot
Abstract
Existing reasoning evaluations typically provide task-relevant information to models as available premises, rarely examining concurrently how models discover evidence autonomously and how information presentation within narratives guides or obscures judgment. This paper proposes the WORTH Benchmark: models read original mystery narratives without clue annotations, autonomously select key clue sentences, identify case participants, and explain their reasoning process. The narrative materials are designed by professional authors such that evidence facilitating reasoning coexists with narrative arrangements that delay the revelation of truth. We report a pilot experiment under full-story conditions across two episodes, conducting a total of 70 formal runs on models, of which 67 runs are content-scorable. Scoring separately records hits on author-designated key clue sentences and participant selections; natural language explanations are used for case diagnosis and are not scored independently. The results show that clue hits and participant judgments are not synchronized; across 37 content-scorable runs in Episode 02, 31 runs simultaneously selected the same set of incorrect participants, while adjacent suspicion-oriented and exoneration-oriented sentences were selected 25 times and 0 times, respectively. These phenomena illustrate the diagnostic value of component-wise analysis and suggest that not-fully-cooperative informational relationships may influence evidence selection and judgment. This study only implements full-story conditions for two episodes, and does not establish stable model rankings or infer general mechanisms on this basis; human player records have not yet been cleaned, and this version does not report human-model comparisons.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27597
PDF
-
Policy Search in Code Space for Multi-Agent Pathfinding
2026-10-20 03:42:05Matthias Eder, Pantelis Emmanouil, Vivek Farias, Fabian Fischer, Adam Jozefiak, Tianyi Peng, Thomas Ulz, Raphael Watschinger, Fangyu Wu, Andrew ZhengAbstract
Developing coordination policies for complex multi-agent systems relies on either labor-intensive algorithm design or opaque task-specific reinforcement learning. With recent advances in autonomous coding agents, we show that policy search directly in code space offers a compelling third path that combines automated optimization with explicit interpretability. We investigate a human-directed workflow in which coding agents iteratively propose, implement, evaluate, diagnose, and eventually refine algorithms guided by simulation feedback and explicit correctness verification. We conducted two case studies and found that this workflow robustly outperformed any manually engineered solutions. On a challenging map in the 2024 League of Robot Runners competition, a two-day search discovered a policy that exceeds the stronger locally reproduced competition entry by 35.0% on the densest instance and generalizes to unseen map instances. In simulated real-world warehouses with irregular lanes, continuous robot geometry, and asynchronous motion, a week-long search discovered an entirely new class of multi-agent pathfinding algorithm that outperforms a calibrated proprietary solution in throughput by 58.9%. Under stated assumptions, we further prove that the new algorithm is collision-free and completes, in finite time, every accepted goal that is not withdrawn or replaced. Together, the studies show that policy search in code space powered by state-of-the-art coding agents offers a highly competitive path to building real engineering solutions that are both effective and analytically tractable.
Abstract (translated)
URL
https://arxiv.org/abs/2610.25946
PDF
-
RaspAssistant as an Agentic Framework for Automating Adsorption Simulation Research in Porous Materials
2026-10-20 03:41:00Marko Petkovi\'c, Susanne Gooijer, Jos\'e Manuel Vicent-Luna, Vlado Menkovski, Sof\'ia CaleroAbstract
Porous-material adsorption studies require coordinated structure preparation, force-field selection, simulation, validation, and interpretation, making end-to-end automation difficult. We test whether RaspAssistant, a hierarchical multi-agent framework, can carry an adsorption study from force-field preparation through validation and downstream separation analysis. Across twelve multi-agent workflow-reproduction runs spanning four adsorption and separation benchmarks, overall scores ranged from 8.50 to 10.00 on a rubric evaluating workflow correctness, simulation validity, and analysis consistency. In a separate eight-case force-field extraction benchmark, the mean weighted score was 0.967, combining parameter agreement and RASPA readiness. In open-ended studies, the system diagnosed and refined an acetylene force field and, after validating a CO$_2$ force field against MFI experiments, screened 197 pure-silica zeolites that passed automated input checks. These results demonstrate autonomous workflow execution after task specification and input provision: RaspAssistant coordinates, validates, adapts, and documents extended adsorption-simulation workflows while exposing model sensitivity and methodological limitations for expert review.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27572
PDF
