AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsHow GUI Agents Fail: GraceBench for Execution Stability Diagnosis
arXiv:2610.19900v1 Announce Type: new Abstract: As GUI agents are increasingly deployed for mobile task automation, their reliability depends not only on final task outcomes, but also on whether they reach these outcomes…
- arXiv cs.AIagentsNeurosymbolic Learning of Interpretable World Models
arXiv:2610.19955v1 Announce Type: new Abstract: World models aim to learn compact representations of an environment from observations, enabling agents to predict future states and plan their behaviour. However, most exis…
- arXiv cs.AIagentsWhat Coding Agents Leave Unsaid: Measuring Task-State Gaps Between Execution and Reports
arXiv:2610.20003v2 Announce Type: replace Abstract: Human supervisors rely on coding agents' reports to assess progress, verify repairs, and decide when to intervene. But a supervisor cannot investigate a failure they we…
- arXiv cs.AIagentsMemorizing Who, Knowing How: Benchmarking Personal and Procedural Memory for Persistent Assistants
arXiv:2610.20022v2 Announce Type: replace Abstract: Memory systems for persistent personal agents must move beyond isolated memories, maintaining both personal memory about whom they serve and procedural memory about how…
- arXiv cs.AIagentsEvalBuilder: Can LLMs Build Efficient Benchmarks?
arXiv:2610.20099v1 Announce Type: new Abstract: Large language model (LLM) agents are increasingly used for long-horizon research and engineering, yet evaluating these capabilities remains expensive, time-consuming, and…
- arXiv cs.AIagentsMaximising Transparency in Context Compaction Improves Retention of Facts and Commitments for Lightweight Coding Agents
arXiv:2610.20116v1 Announce Type: new Abstract: Long coding agent sessions outgrow the model's context window, so agents compact: older history is replaced by something shorter, usually a model-written summary. A summary…
- arXiv cs.AIagentsHEM-Med: A Hierarchical Agentic Memory Framework for Safe Multi-Center Medication Recommendation
arXiv:2610.20191v2 Announce Type: replace Abstract: Medication recommendation (MR) is critical for clinical decision support. While existing MR methods are mostly designed for single-center learning, where only one indep…
- arXiv cs.AIagentsDrivers of LLM Consensus Formation Under Competing Incentives: A Simulation Study
arXiv:2610.20200v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in multi-agent environments that produce unanimous agreement, both in intended interactions that need coordination an…
- arXiv cs.AIagentsCASI: Credit Assignment via Set Intervention for Agentic Retrieval
arXiv:2610.20293v1 Announce Type: new Abstract: Large language models increasingly generate multiple retrieval actions jointly, while downstream systems often provide only one reward for the resulting set. Broadcasting t…
- arXiv cs.AIagentsReflect After Failure: Brain-Inspired Self-Evolving Agents for Embodied Spatial Intelligence
arXiv:2610.20312v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have made substantial progress in spatial reasoning, and self-evolving agents further extend these capabilities to embodied environments by le…
- arXiv cs.AIagentsTreeFlex: Agents Navigating Their Own Search Trees
arXiv:2610.20334v1 Announce Type: new Abstract: A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path information consumes…
- arXiv cs.AIagentsFrom Relevance to Validity: Zero-Shot Tool Selection via Functional and Contextual Validation
arXiv:2610.20388v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly face tasks from unseen domains and execution contexts, making zero-shot tool selection essential for identifying tools that c…
- arXiv cs.AIagentsSwarmRSI: Recursive Self-Improvement through Evolving Scientific Agent Swarm
arXiv:2610.20431v2 Announce Type: replace Abstract: Recursive self-improvement (RSI) in scientific research aims to improve agents' research capabilities through their own experimental experience. Scientific agent swarms…
- arXiv cs.AIagentsThe Wealth of Agents: Scaling Agentic AI Across Developers
arXiv:2610.20518v1 Announce Type: new Abstract: Today's agentic systems are typically designed, built, and deployed by single developers with full control over all participating agents. While this simplifies development,…
- arXiv cs.AIagentsActiveEvidence: Decision-Focused Evidence Graphs with Verifiable Acquisition Gaps
arXiv:2610.20532v2 Announce Type: replace Abstract: A multimodal agent must decide whether visual evidence is worth acquiring, which candidate or resolution to query, and when further interaction can no longer change its…
- arXiv cs.AIagentsPhySGA: A Physics-Space Grounded Agentic Framework for Generalizable and Interactive 3D Composition
arXiv:2610.20560v1 Announce Type: new Abstract: 3D object composition is pivotal to digital content creation and robot simulation, while also serving as a critical testbed for physical intelligence in foundation models.…
- arXiv cs.AIagentsScaling Discovery Requires Forgetting
arXiv:2610.20563v1 Announce Type: new Abstract: Automated research with LLM agents has shown promising results in various domains. Through iterative refinement and scored verifiers, LLM agents are capable of discovering…
- arXiv cs.AIagentsCo-Evolving Acting and Forecasting for Language Agents
arXiv:2610.20597v2 Announce Type: replace Abstract: Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar…
- arXiv cs.AIagentsTheoPhysEval: Assessing AI agents at autonomous theoretical physics problem solving
arXiv:2610.16733v1 Announce Type: cross Abstract: We present a suite of 50 unpublished research-level theoretical physics problems with verifiable answers. Without AI assistance, a typical problem in our collection could…
- arXiv cs.AIagentsDo Perturbation Predictors Learn Gene Interactions? Diagnosing Extrapolation in Agentic Screening
arXiv:2610.18880v1 Announce Type: cross Abstract: High-throughput perturbation screens increasingly use machine-learning models to predict the effects of gene combinations that were never measured. A difficult case arise…
- arXiv cs.AIagentsFollowing the Flow the Law Requires: Training Voice Agents to Transfer to Unseen Regulated Procedures in Debt Collection
arXiv:2610.18881v1 Announce Type: cross Abstract: Voice agents built on large language models (LLMs) now handle customer calls, but in regulated applications completing the task is not enough: the agent must follow a con…
- arXiv cs.AIagentsCyberArena: Benchmarking AI Agents in Live Symmetric Attack-and-Defense Combat
arXiv:2610.19005v2 Announce Type: replace-cross Abstract: AI agents are demonstrating increasingly strong offensive and defensive cybersecurity capabilities in the real world. Current benchmarks mostly evaluate agents in…
- arXiv cs.AIagentsTowards a Data-Centric Understanding of Spatial Reasoning in Multimodal Large Language Models
arXiv:2610.19108v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limitations in spatial reas…
- arXiv cs.AIagentsLearning in Orbit: Onboard Training and Closed-Loop Attitude Control with a Thermal Segmentation Model on a Spacecraft
arXiv:2610.19122v1 Announce Type: cross Abstract: Deep space missions increasingly require spacecraft capable of autonomously operating in environments with communication delays and bandwidth limitations. A key enabler o…
- arXiv cs.AIagentsNarrowing the Collaboration Gap, Probably
arXiv:2610.19215v1 Announce Type: cross Abstract: Large language models are increasingly deployed as teams of agents that hold different private information about a shared task. How should such agents concisely communica…
- arXiv cs.AIagentsBeyond Maliciousness: Static and Runtime Attack-Surface Profiling of Agent Skills
arXiv:2610.19264v1 Announce Type: cross Abstract: Agent skills are Markdown documents that a tool-using agent reads as instructions and then acts on with the privileges of the session that loaded them. Installing one gra…
- arXiv cs.AIagentsWhy Do Agent Teams Fail Across Boundaries? A Failure Taxonomy for Agent-to-Agent Systems with Private States
arXiv:2610.19342v2 Announce Type: replace-cross Abstract: Agents are increasingly interacting with other agents that act for different principals (people or organizations on whose behalf they work), such as a buyer's per…
- arXiv cs.AIagentsBeyond Corrected Actions: Training LLM Agents on Textual Critiques
arXiv:2610.19367v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for multi-turn agentic tasks that require interactions with users and environments over extended sequences of actions.…
- arXiv cs.AIagentsPolicy-Verified Self-Training: Learning Agent Compliance from Verifiable Policy Rewards
arXiv:2610.19372v1 Announce Type: cross Abstract: Runtime policy verifiers can prevent agents from executing disallowed actions, but their decisions are typically used only for enforcement and discarded afterward. We ask…
- arXiv cs.AIagentsFrom Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents
arXiv:2610.19420v1 Announce Type: cross Abstract: Simulated environments enable scalable training data generation for embodied agents, but more data does not necessarily provide what a particular agent needs to learn. Ex…
- arXiv cs.AIagentsRetrieve What Helps, Only When It Helps: Agentic Reinforcement Learning for Selective Retrieval-Augmented Machine Translation
arXiv:2610.19528v1 Announce Type: cross Abstract: Retrieving external knowledge can improve large language model (LLM) translation by providing supplementary information such as idiom interpretations and terminology. How…
- arXiv cs.AIagentsXferAgent: Cross-Agent Experience Transfer for Self-Improving LLM Agents
arXiv:2610.19581v1 Announce Type: cross Abstract: Large language model (LLM) agents can reuse experience from prior task executions to improve performance on subsequent tasks. Although existing methods enable cross-agent…
- arXiv cs.AIagentsJevCoder: When Does Decision Delegation Pay Off in Code Repair?
arXiv:2610.19596v1 Announce Type: cross Abstract: A coding agent repeatedly makes decisions as it repairs code. These decisions shape repair trajectories and affect the token cost of successive model requests. We ask whi…
- arXiv cs.AIagentsDivergent Paths: Learning an Outcome-Predictive Representation of LLM Agent Trajectories
arXiv:2610.19614v1 Announce Type: cross Abstract: In this work, we reframe agentic trajectories as paths through a shared embedding space of actions and environmental observations. We show that successful and failed roll…
- arXiv cs.AIagentsMeasuring and Reducing Unusable Replies of LLM Agents
arXiv:2610.19659v1 Announce Type: cross Abstract: People delegate multi-step work to LLM agents and read only the reply that the agent hands back. Current evaluation scores task completion and the faithfulness of reports…
- arXiv cs.AIagentsInterlock: From Local Correctness to Task Completion in Long-Horizon Agents
arXiv:2610.19686v1 Announce Type: cross Abstract: Large language model agents increasingly undertake long-horizon tasks in complex environments characterized by fragmented evidence, partially completed states, and depend…
- arXiv cs.AIagentsNew Model, Old Habits: Behavior Transfer under Model Swapping in Multi-Session LLM Agents
arXiv:2610.19712v1 Announce Type: cross Abstract: Multi-session agents can switch between LLMs to balance performance and inference cost. Such switches require transferring a history for continuity, yet their effects on…
- arXiv cs.AIagentsUncertainty-Driven Self-Play for Robust Multi-Agent Driving Policies
arXiv:2610.19714v1 Announce Type: cross Abstract: Learning robust driving policies that generalize beyond their training domain remains a central challenge in motion planning. We propose an uncertainty-driven self-play s…
- arXiv cs.AIagentsWhat Happens to the Goal? Distinct Failures of Policy Alignment in Goal Misgeneralization
arXiv:2610.19731v2 Announce Type: replace-cross Abstract: Goal misgeneralization is a common failure mode in which an agent behaves competently out of distribution but pursues a proxy that coincided with the intended goa…
- arXiv cs.AIagentsExact Cut Complexity of Equal-Length Proportional Cake Cutting
arXiv:2610.19733v1 Announce Type: cross Abstract: We study proportional cake cutting under an equal-length constraint, where each of $n$ agents must receive a bundle of length exactly $1/n$ that is worth at least $1/n$ t…
- arXiv cs.AIagentsPRISMATIC : Prescription Risk Inspection System for Multi-Agent Treatment Interaction in Clinical Decision-Making
arXiv:2610.19762v1 Announce Type: cross Abstract: Medical prescribing errors for multimorbid patients, who require complex drug regimens, are a major patient safety concern. These errors often stem from fragmented decisi…
- arXiv cs.AIagentsOne Agent per Zone: Decentralised Active Inference under Partial Observability for Multi-Zone HVAC Control on Edge Hardware
arXiv:2610.19790v1 Announce Type: cross Abstract: Multi-zone HVAC control is a shared-resource problem: zones on a floor share one fan and cooling coil, so each zone's demand affects its neighbours and the building's pea…
- arXiv cs.AIagentsDeltaStreamer: Towards Human-Like Agentic Streaming Video Understanding
arXiv:2610.19849v1 Announce Type: cross Abstract: We propose DeltaStreamer, a novel agentic framework for streaming video understanding inspired by how humans observe, remember, and investigate. Streaming video understan…
- arXiv cs.AIagentsAtomSearch: Evidence-Grounded Tree Search for Agent Skill Optimization
arXiv:2610.19951v1 Announce Type: cross Abstract: Agent skills adapt frozen models through editable external instructions. Revising several rules at once makes changes difficult to inspect, while judging each local edit…
- arXiv cs.AIagentsCoRedSkill: Stealthy Skill Composition Attacks via AST-Guided Injection
arXiv:2610.20049v1 Announce Type: cross Abstract: Agents extend their capabilities through reusable skills that package instructions, executable code, and resources. Composing these skills enables complex task workflows,…
- arXiv cs.AIagentsGeoCloak: An Agentic Framework for Semantics-Preserving Geolocation Privacy via Peripheral Clue Manipulation
arXiv:2610.20055v1 Announce Type: cross Abstract: The rapid advancement of large vision language models (LVLMs) has made geolocation inference from images highly accurate and accessible. This poses serious privacy risks:…
- arXiv cs.AIagentsTask-State Governance: A Virtual Machine for Verifiable and Recoverable GUI Agent Execution
arXiv:2610.20100v1 Announce Type: cross Abstract: Graphical user interface (GUI) agents now execute workflows across real applications, but when execution drifts, users must determine what changed, what should have remai…
- arXiv cs.AIagentsSWE-Stream: Scaling Executable Training Data for SWE Agents via Progressive Construction and Elastic Streaming
arXiv:2610.20193v1 Announce Type: cross Abstract: Software engineering agents have advanced rapidly, but scaling their training remains constrained by the limited availability of high-quality executable tasks. Developmen…
- arXiv cs.AIagentsWhat Makes a Social Agent's Interactions Effective? Learning from Verifiable Outcomes in Paired Worlds
arXiv:2610.20195v1 Announce Type: cross Abstract: Effective social interaction requires more than fluent responses: agents must reach plans that fit the participants' needs and circumstances. Existing evaluations of soci…
- arXiv cs.AIagentsWhat and Where in Identifying and Quantifying Conventions in Humans and AI Agents
arXiv:2610.20205v1 Announce Type: cross Abstract: Cooperative success rests in part on implicit communication. Partners converge on conventions: regularities that give an action meaning beyond its direct effect. Yet conv…