AI news archive.
4,966 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsState Trace Rationale As Auxiliary Task in Reinforcement Learning
arXiv:2609.36867v1 Announce Type: new Abstract: We propose STRAT, an auxiliary task that trains deep reinforcement learning (RL) agents to predict a short textual trace of their own state. Inspired by human spatial navig…
- arXiv cs.AIagentsWEFT: Scaling Tool-Use Post-Training for General-Purpose Agents
arXiv:2609.36887v1 Announce Type: new Abstract: Recent efforts to scale tool-use post-training have largely centered on the synthesis of executable environments, which constitute only one component of a broader agentic i…
- arXiv cs.AIagentsHarness Evolution as Learning: Approximation, Generalization, and Optimization Limits of Self-Improving Personal Agents
arXiv:2609.36892v1 Announce Type: new Abstract: As the capabilities of large language models (LLMs) continue to advance, increasing attention is turning to how to translate their abilities into useful behavior. Personal…
- arXiv cs.AIagentsPrecogUI: Proactive GUI Agents via Pre-cognitive Simulation and Experience Retrieval
arXiv:2609.36923v1 Announce Type: new Abstract: Existing reactive Graphical User Interface (GUI) agents often fail in long-horizon, dynamic scenarios, where unexpected disturbances trigger attention-diverting and cascadi…
- arXiv cs.AIagentsNeuro-Symbolic Computer Use: Learning Reusable Policies for Reliable and Efficient Execution
arXiv:2609.36927v1 Announce Type: new Abstract: Many computer tasks recur: the same workflow runs many times, with new inputs and from different starting states. Current computer-use agents re-plan every step of every ru…
- arXiv cs.AIagentsSCA: Spatial Credit Assignment for Reinforcement Learning of GUI Agents
arXiv:2609.36939v1 Announce Type: new Abstract: GUI agents automate tasks on digital devices by grounding language instructions in visual interfaces. Existing group-relative reinforcement learning improves GUI action pre…
- arXiv cs.AIagentsCADOC: Cache-Aware Dynamic Object Context for Long-Horizon Agents
arXiv:2609.37012v1 Announce Type: new Abstract: For a long-horizon agent, context is the bottleneck: the history is resent with every request, the window caps task length, and reasoning degrades as the history grows. Rep…
- arXiv cs.AIagentsPhysics-Informed Multi-Agent Coordination for Hospital Patient Flow Optimization
arXiv:2609.37022v1 Announce Type: new Abstract: Efficient patient flow coordination across autonomous hospital departments is critical for mitigating overcrowding and balancing resource utilization. While classical queue…
- arXiv cs.AIagentsAnyAct: Universal Action for Self-Evolving Agents
arXiv:2609.37025v1 Announce Type: new Abstract: As large language models (LLMs) advance, AI agents are increasingly deployed in open-world environments to tackle complex sequential tasks (e.g., document processing, cross…
- arXiv cs.AIagentsMatToolBench: Benchmarking Multimodal Agents in Real-World Materials Science Workflows
arXiv:2609.37053v1 Announce Type: new Abstract: Multimodal GUI agents have achieved impressive results on general software benchmarks, yet their ability to operate professional scientific software remains largely unexplo…
- arXiv cs.AIagentsLearning from Viable Failure Prefixes: Milestone Viability Potential Policy Optimization for Long-Horizon LLM Agents
arXiv:2609.37111v2 Announce Type: replace Abstract: Long-horizon LLM agents require reinforcement learning methods that can assign credit to intermediate decisions under sparse and delayed rewards. Existing group-based m…
- arXiv cs.AIagentsWhen Should Agents Check External State? Budgeting Observations for Stored Intentions
arXiv:2609.37125v3 Announce Type: replace Abstract: Prospective memory allows an agent to retain an intention tied to a future condition, but the stored intention does not reveal whether that condition currently holds. C…
- arXiv cs.AIagentsWhen Tools Silently Lie: Evaluating and Mitigating Blind Compliance in Tool-Augmented Data Agents
arXiv:2609.37153v1 Announce Type: new Abstract: Tool-augmented data agents rely on tool outputs for analytical decisions. Yet successful execution can return plausible but incorrect evidence, requiring agents to decide w…
- arXiv cs.AIagentsSimpleEvol: An Agent-Loop Framework for LLM-Driven Automated Heuristic Design with Minimal Human Priors
arXiv:2609.37172v2 Announce Type: replace Abstract: Large language models (LLMs) have emerged as powerful tools for automated heuristic design (AHD), enabling iterative generation and refinement of heuristics. However, t…
- arXiv cs.AIagentsAbsorbed in Inertia: Activation Analysis for Computer-Use Agents
arXiv:2609.37176v1 Announce Type: new Abstract: Computer-use agents have become increasingly capable of executing tasks on live desktops through natural-language instructions, based on trajectories of screenshots, action…
- arXiv cs.AIagentsAsking for What Was Never Requested: Horizontal and Vertical Proactivity in Agents
arXiv:2609.37236v1 Announce Type: new Abstract: An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require information the user never requested. Work on proactive ag…
- arXiv cs.AIagentsFoundations of Proactive Agents: Principles, Technical Layers, and Proactivity-Gym
arXiv:2609.37267v1 Announce Type: new Abstract: Proactive LLM agents can turn idle compute into useful support before users ask. Yet even correct work can misread user context, impose review costs, or undermine trust. Th…
- arXiv cs.AIagentsReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents
arXiv:2609.37311v2 Announce Type: replace Abstract: Recent Recommendation Agents (RecAgents) offer a promising alternative by shifting recommendation to an active, user-side paradigm, where generative agents autonomously…
- arXiv cs.AIagentsSeek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation
arXiv:2609.37353v1 Announce Type: new Abstract: Vision-Language Navigation (VLN) requires agents to continuously ground task progress from long-horizon instructions and partial egocentric observations. Existing VLM-based…
- arXiv cs.AIagentsCommitment Hierarchies under Intent Revision: A Belief-Revision Account of Salvage in Tool-Use Agents
arXiv:2609.37453v1 Announce Type: new Abstract: When a user changes their mind partway through a task, an agent that has already split the task into sub-goals and paid for tool calls must decide, per cached sub-result, w…
- arXiv cs.AIagentsGoverning the Edge: Automating Commercial Property and Casualty Insurance Underwriting via a Hybrid Local-Cloud Multi-Agent Framework
arXiv:2609.37454v1 Announce Type: new Abstract: Underwriters in commercial Property and Casualty (P&C) insurance spend 30 to 40% of their time on administrative work rather than risk judgment, and a single submission tak…
- arXiv cs.AIagentsVeriWeave Govern: Evidence-Gated Deterministic Runtime Governance for Enterprise AI Agents
arXiv:2609.37457v1 Announce Type: new Abstract: Enterprise artificial-intelligence agents increasingly call tools, modify infrastructure, and process protected data, creating a need to separate action generation from act…
- arXiv cs.AIagentsBoundary-State Control for Tool-Using Language-Model Agents: Commit-Time Consistency under State Drift
arXiv:2609.37475v1 Announce Type: new Abstract: Tool-using language-model agents can decide that an action is permissible and execute it only after security-relevant state has changed. We study this proposal-to-commit ga…
- arXiv cs.AIagentsSkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation
arXiv:2609.37539v1 Announce Type: new Abstract: Skills equip LLM agents with professional knowledge and guidance to complete long-horizon and complex tasks. Although skills have been widely adopted in recent agent paradi…
- arXiv cs.AIagentsHow Can Recommendation Feedback Evolve Agent Memory?
arXiv:2609.37544v2 Announce Type: replace Abstract: Content-generation agents continuously receive impressions, clicks, conversions, and negative feedback from recommendation systems, providing real-world outcome signals…
- arXiv cs.AIagentsRational Clarification by Assistive Agents via Value-of-Information Reasoning
arXiv:2609.37588v1 Announce Type: new Abstract: Users of language-based assistive agents often make ambiguous requests. In response, an assistant can either directly act on its interpretation of the request --- risking m…
- arXiv cs.AIagentsFOCUS: Training-Free Decision-Preserving Context Compression for LLM Agents
arXiv:2609.37590v1 Announce Type: new Abstract: LLM agents accumulate interaction histories that grow linearly with task length, causing quadratic inference cost scaling and performance degradation from attention dilutio…
- arXiv cs.AIagentsEnterpriseBench: Benchmarking LLM Agents on Enterprise-Level Strategic Reasoning and Decision-Making
arXiv:2609.37658v2 Announce Type: replace Abstract: LLM agents are increasingly expected to support enterprise workflows, where tasks often involve missing information, uncertainty, feedback, and long-term trade-offs. Ho…
- arXiv cs.AIagentsKUPAS MASTER: Distilling the Tacit Expertise of Master Practitioners into Agent-Ready Experience Corpora
arXiv:2609.37673v1 Announce Type: new Abstract: Experienced professionals know more than just facts and conclusions. They know which cues matter, why a judgment is reasonable, and which action to take. Routine work recor…
- arXiv cs.AIagentsEngiWorld: What Can Frontier Agents Deliver in Professional Engineering Environments?
arXiv:2609.37686v2 Announce Type: replace Abstract: Autonomous agents have made rapid progress in general-purpose computer use, yet reliable automation of professional industrial engineering remains out of reach. Enginee…
- arXiv cs.AIagentsContextRender: From Execution Dependencies to Agent Context
arXiv:2609.37743v1 Announce Type: new Abstract: LLM agents performing long-horizon tasks accumulate tool results that later steps may need. Passing the full history to every invocation is costly even when it fits within…
- arXiv cs.AIagentsOmniVCBench: Benchmarking Evidence-Grounded Multimodal Reasoning Towards AI Virtual Cells
arXiv:2609.37773v1 Announce Type: new Abstract: Artificial Intelligence Virtual Cells (AIVCs) are envisioned as scientific agents that simulate cellular responses, explain underlying mechanisms, and support hypothesis-dr…
- arXiv cs.AIagentsMixture of Self-Improving Branches For Agent Harness Optimization
arXiv:2609.37834v1 Announce Type: new Abstract: Harness optimization provides a practical setting for recursive self-improvement (RSI), where agent-generated modifications inform subsequent changes through execution feed…
- arXiv cs.AIagentsGuide, Then Let Go: Gap-Adaptive Teacher Scheduling for Sparse-Reward Agentic RL
arXiv:2609.37898v1 Announce Type: new Abstract: Reinforcement learning for long-horizon agents typically relies on sparse outcome-based rewards. This leads to a severe cold-start problem, as early-stage policies often fa…
- arXiv cs.AIagentsPixels to Keys: Exploring Spatial and Motion Cues in Gameplay Inverse Dynamics
arXiv:2609.37907v2 Announce Type: replace Abstract: Video games offer scalable environments for studying perception and control in embodied agents. Abundant online gameplay videos could supply demonstrations, but they ra…
- arXiv cs.AIagentsVideo-RSI: Recursive Self-Improvement of Video Understanding Agents via Harness Evolution
arXiv:2609.37950v1 Announce Type: new Abstract: Video understanding agents acquire evidence through an executable harness that controls what they observe and how they use those observations. However, execution traces con…
- arXiv cs.AIagentsTopological Coherence for Self-evolving Multi-agent Systems
arXiv:2609.37953v1 Announce Type: new Abstract: Complex tasks inherently couple workflow structure, agent responsibility, collaboration, and memory access: task regions delimit responsibility and tool scope, cross-region…
- arXiv cs.AIagentsSelfSearch: Reward-Free Search for Self-Improving Agents
arXiv:2609.37968v2 Announce Type: replace Abstract: Advances in the coding capabilities of LLM agents allow them to inspect and modify their own instructions, tools, and execution procedures. Existing approaches use this…
- arXiv cs.AIagentsDiagnosing and Improving Probabilistic Reasoning in Large Language Models
arXiv:2609.38005v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly proposed as decision assistants who must reason probabilistically from available evidence under explicit decision costs. W…
- arXiv cs.AIagentsBrain-SAD: A Brain-Inspired Safe Autonomous Driving Control Framework with Dynamic Fear-Oriented Constraint on Dual-Policy
arXiv:2609.38016v1 Announce Type: new Abstract: Constrained Reinforcement Learning has recently gained increasing attention in the field of Safe Autonomous Driving, where the general mechanism is to maximize the expected…
- arXiv cs.AIagentsRetrieval-Augmented Skill Optimization via Cross-Harness Adaptation
arXiv:2609.38024v1 Announce Type: new Abstract: An agent skill is a reusable, actionable natural-language artifact that guides an agent to perform a task effectively under a given harness. Recent studies have explored th…
- arXiv cs.AIagentsUserProxyBench: Evaluating LLM User Simulators for Agent Benchmarks and Training
arXiv:2609.38043v1 Announce Type: new Abstract: Interactive agent benchmarks and multi-turn reinforcement learning increasingly place a second language model in the role of the user. This simulated user controls what inf…
- arXiv cs.AIagentsCharacter Training for Risk-Averse Agents
arXiv:2609.38093v1 Announce Type: new Abstract: Risk aversion in resources could prevent misaligned AI agents from causing catastrophic harm. Misaligned but risk-averse agents would tend to favor safer strategies like ma…
- arXiv cs.AIagentsDo LLM Agents Execute the Plans They Declare? From Planning-Mode Declaration to Pattern-Specific Execution
arXiv:2609.38108v1 Announce Type: new Abstract: Large language models (LLMs) enable agents to solve long-horizon tasks by generating a plan and then executing it in an environment. However, successful planning requires t…
- arXiv cs.AIagentsLearning Meta-Skills for Agent Harness Design in Test-Time AI4AI
arXiv:2609.38143v2 Announce Type: replace Abstract: Agent performance depends on both reasoning ability and the environment in which it acts. We study test-time AI-for-AI, asking how a Builder can learn to construct bett…
- arXiv cs.AIagentsThinking Before Thinking: Scaling Agentic Inference Through Meta-Reasoning
arXiv:2609.38147v1 Announce Type: new Abstract: As agents take on longer and more complex problems, controlling the execution becomes a task in its own right. Each step in the run brings new control choices, like which p…
- arXiv cs.AIagentsEvaluating the Effects of Prompt Perturbation on Bias and Hallucination in Large Language Models
arXiv:2609.35804v1 Announce Type: cross Abstract: Large language models (LLMs) have shown remarkable capabilities in various natural language processing tasks, leading to their widespread deployment as intelligent assist…
- arXiv cs.AIagentsFrom Lexical Baselines to Agentic Retrieval-Augmented Generation: Structured Skill and Responsibility-Level Extraction with the SFIA Framework
arXiv:2609.35806v1 Announce Type: cross Abstract: Automated skill extraction underpins workforce planning, yet most systems represent skills as flat labels with no notion of the responsibility level at which a skill is p…
- arXiv cs.AIagentsEnvironment Steering: Using Data Flow Control to Improve Agent Utility and Safety
arXiv:2609.35807v1 Announce Type: cross Abstract: LLM agents can make unsafe tool calls even when instructed to behave safely. Existing defenses constrain agents before execution, modify tool inputs/outputs, or rely on L…
- arXiv cs.AIagentsWhen Successful Memories Mislead Embodied Agents:Memory Adaption For Task-Conditioned Execution
arXiv:2609.35808v1 Announce Type: cross Abstract: Experience reuse can reduce repeated exploration in embodied agents, but a trajectory that succeeded previously may be unsuitable for the current execution context. Exist…