AI news archive.
4,959 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsCodeMeepo: A Multi-Agent Workflow for Repository-Level Code Migration and Optimization
arXiv:2610.34633v1 Announce Type: cross Abstract: Repository-level code migration rewrites an entire project in a new programming language while preserving its observable behavior. It is challenging because behavior span…
- arXiv cs.AIagentsAgentProofBench: Benchmarking Reusable Verifiers for Web Agents
arXiv:2610.34634v1 Announce Type: cross Abstract: Reusable Web-agent verification requires a rule to follow changing requirements and support subsequent execution. We introduce AgentProofBench, which connects paired test…
- arXiv cs.AIagentsIntrinsic Goals for Autonomous Agents: Hierarchical Exploration Captures Future Volitional Action in Drosophila
arXiv:2610.34638v1 Announce Type: cross Abstract: Animals have a remarkable capacity for autonomy---driven by intrinsic motivation---without external sensory cues or extrinsic objectives, yet the computational mechanisms…
- arXiv cs.AIagentsRobotAgentBench: Towards Open-world Robot Autonomy
arXiv:2610.34649v1 Announce Type: cross Abstract: Recent advances in vision-language-action (VLA) and world-action models (WAMs) have significantly improved robotic manipulation, yet deploying robots in the open world de…
- arXiv cs.AIagentsThinking-in-Bets at Test Time Reduces Sycophantic Revisions in LLM Agents
arXiv:2610.34654v1 Announce Type: cross Abstract: Language model agents often abandon correct work when a user challenges it, yet simply telling them to stand firm makes them ignore real mistakes. Once an agent reads a c…
- arXiv cs.AIagentsAgent Memory as Recommendation: Recommender-System Design for Long-Term Memory of LLM Agents
arXiv:2610.34673v1 Announce Type: cross Abstract: Large language model (LLM) agents that serve users across many sessions must choose, for every request, the few stored memories that enter a limited context window. This…
- arXiv cs.AIagentsSceneAgent: An Agentic Pipeline from 3D and 4D Captures to Simulation Environments
arXiv:2610.34745v1 Announce Type: cross Abstract: Visual captures provide detailed scene appearance, but converting them into interactive simulation environments requires object reconstruction, physical modeling, and cor…
- arXiv cs.AIagentsBabysitting AI Agents: A User-Centered Taxonomy and Study of Agentic Delegation Failures
arXiv:2610.34748v1 Announce Type: cross Abstract: Users are increasingly delegating tasks to AI agents, allowing agents to perform long-running, multi-step workflows on their behalf. However, agents may perform these tas…
- arXiv cs.AIagentsThe Physical Cost of Context: Quality-Constrained Resource Accounting for Coding Agents
arXiv:2610.34763v1 Announce Type: cross Abstract: Coding agents resend a growing context on every model call, and context policies are usually judged by the prompt tokens they save. Executed work also depends on call cou…
- arXiv cs.AIagentsSilent and Costly: Characterizing and Detecting Prompt-Caching Mis-Integration in LLM Agents
arXiv:2610.34817v2 Announce Type: replace-cross Abstract: Large language model (LLM) services process massive volumes of user requests, resulting in substantial inference costs. To reduce both cost and latency, providers…
- arXiv cs.AIagentsAdaptive Retrieval, Selective Answers: Evaluating Conformal Factuality in Agentic RAG
arXiv:2610.34872v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) can improve factual grounding without guaranteeing that every generated claim is supported. Previous work has studied claim-level con…
- arXiv cs.AIagentsNumTrace: Auditing the Number Provenance of Financial Analyst Agents
arXiv:2610.34887v1 Announce Type: cross Abstract: A numerical claim generated by a financial analyst agent can match a number in a company filing but refer to the wrong entity, concept, period, unit or scope. A check bas…
- arXiv cs.AIagentsAIPC: Evidence-Guided Agent Workflows for PyTorch Project Deployment
arXiv:2610.34890v1 Announce Type: cross Abstract: Deploying and optimizing a PyTorch inference project on a dedicated accelerator, especially an on-device NPU, requires more than using a framework device API as with CUDA…
- arXiv cs.AIagentsHow Do Coding-Agent Harnesses Self-Evolve? An Empirical Study of Retrospective Adaptation
arXiv:2610.34938v1 Announce Type: cross Abstract: Coding agents can adapt their harnesses, the software, configuration, and instructions used to run them, based on experience from earlier tasks, but whether these adaptat…
- arXiv cs.AIagentsGUIFlow: Temporal Redundancy-Aware Incremental Inference for GUI Agents
arXiv:2610.34959v1 Announce Type: cross Abstract: GUI agents built on vision-language models interact with continuously evolving interfaces, yet conventional inference repeatedly recomputes representations of largely ove…
- arXiv cs.AIagentsThe Target Agent Is Its Own Best Critic but a Poor Proposer: Self-Improved Red Teaming
arXiv:2610.34965v1 Announce Type: cross Abstract: Automatic red teaming increasingly relies on large language models (LLMs) to iteratively diagnose failed attacks and propose improved adversarial prompts or injections. A…
- arXiv cs.AIagentsAskGLP1: A Knowledge Graph LLM Agent for Exploring GLP-1 Experience from Online Patient Narratives
arXiv:2610.34987v1 Announce Type: cross Abstract: GLP-1 medications are increasingly used for weight management, and many people share their experiences online. These narratives show why people take the drugs and what th…
- arXiv cs.AIagentsCoSA: The Conflict of Skills Attack in Real-World LLM Agent Ecosystems
arXiv:2610.35082v1 Announce Type: cross Abstract: Agent Skills allow LLM agents to combine reusable capabilities, but checking each Skill in isolation cannot rule out policy violations when they are composed. We term suc…
- arXiv cs.AIagentsV$^3$AST-Bench: Verifiable, Valid, and Versatile Safety Evaluation for Coding Agents
arXiv:2610.35188v1 Announce Type: cross Abstract: Large language models increasingly act through code, modifying repositories, executing programs, and interacting with services in agent form. Their actions introduce risk…
- arXiv cs.AIagentsSkillLifeBench: Benchmarking Security Across the Lifecycle of Agent Skills
arXiv:2610.35215v1 Announce Type: cross Abstract: Web agents reuse skills whose stored code, selected version, and loaded implementation can diverge across tasks and updates. SkillLifeBench links these states to task out…
- arXiv cs.AIagentsJoint Latent Reasoning and Observation for Agentic Video Understanding
arXiv:2610.35229v2 Announce Type: replace-cross Abstract: Effective video agents must learn not only how to answer, but also where to look next. Transferring this capability to smaller models is challenging because each…
- arXiv cs.AIagentsRepoTrace: Improving Requirement Tracing in Multi-Round Agent Interactions
arXiv:2610.35333v1 Announce Type: cross Abstract: Code agents have become increasingly capable of performing software engineering tasks through interaction with software environments. However, agents tend to degrade as t…
- arXiv cs.AIagentsMarkovSim: an LLM Agent Harness with Bounded Context for Long-Horizon Computational Simulation
arXiv:2610.35349v1 Announce Type: cross Abstract: Recent studies have applied large language model (LLM) agent systems to computational simulation workflows. Such workflows are long-horizon, so the information generated…
- arXiv cs.AIagentsAutonomous Structural Discovery Of Bioprocess Dynamics And Kinetics Via LLM-Driven Agents
arXiv:2610.35391v1 Announce Type: cross Abstract: High-fidelity digital twins in continuous biomanufacturing are often bottlenecked by incomplete kinetic models, while standard data-driven algorithms (e.g., SINDy, PINNs)…
- arXiv cs.AIagentsThe Hidden Costs of Forgetting: A Study of Trajectory Deletion in Software Engineering Agents
arXiv:2610.35496v1 Announce Type: cross Abstract: Software engineering agents resend their entire trajectory to an LLM at every turn, motivating online trajectory reduction. Prior work shows that randomly deleting 75% of…
- arXiv cs.AIagentsThe Agent in the Middle: How AI-Mediated Access Reshapes Web Vulnerability Exploitation
arXiv:2610.35541v2 Announce Type: replace-cross Abstract: Web services increasingly expose backend interfaces that let users delegate tasks to AI agents, which invoke service operations directly without navigating websit…
- arXiv cs.AIagentsKAPPA: Checking the Proofs in Statistics Papers with Lean 4 and Language Model Agents
arXiv:2610.35596v1 Announce Type: cross Abstract: Papers in statistical theory rest on long proofs that few readers check line by line. We present KAPPA (Kit of Agents for Proof-checking Papers with a proof Assistant), o…
- arXiv cs.AIagentsFrom Language to Drives: A Multimodal Framework for Aligning Autonomous Robots with Human Purposes
arXiv:2610.35629v1 Announce Type: cross Abstract: This work explores a multimodal approach to the alignment of the behavior of open-ended learning autonomous robots with human purposes through the use of large language m…
- arXiv cs.AIagentsMiRL: Error-Targeted Reinforcement Learning for Correcting Terminal Agent Misbehaviors
arXiv:2610.35697v1 Announce Type: cross Abstract: Error-targeted learning gives a legible way to improve a model: identify specific weaknesses of the model, train the model to fix these weaknesses, and check whether the…
- arXiv cs.AIagentsPretraining Knows What, Simulation Teaches How: Compositional Generalization in a Sim-Trained Robot Agent
arXiv:2610.35817v2 Announce Type: replace-cross Abstract: A robot policy needs to understand what a task is asking for in a scene, and how to move the robot to accomplish that task. To achieve these two skills, we introd…
- arXiv cs.AIagentsReva: Real-Time Vulnerability Detection through Contextual Probing of Large Language Models
arXiv:2610.35829v1 Announce Type: cross Abstract: A vulnerability costs more to fix the later it is discovered. As coding agents generate code faster than developers can review it, software needs a first line of defense…
- arXiv cs.AIagentsProfiling a Frontier Agent with EBench: From Direct Control to Harness with Policy
arXiv:2610.35832v1 Announce Type: cross Abstract: Frontier multimodal large language models (MLLMs) can control robots without robot-specific training, but how their capabilities compare and interact with post-trained vi…
- arXiv cs.AIagentsI-HITL: Inalienable Human-in-the-Loop
arXiv:2610.35835v3 Announce Type: replace-cross Abstract: Human oversight is a pillar of AI safety. It is often exercised by a human in the loop (HITL) who approves critical actions taken by an AI agent. AI agents' incre…
- arXiv cs.AIagentsArtificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory
arXiv:2406.14373v4 Announce Type: replace Abstract: The emergence of Large Language Models (LLMs) and advancements in Artificial Intelligence (AI) offer an opportunity for computational social science research at scale.…
- arXiv cs.AIagentsEfficient Generation of Diverse Cooperative Agents with World Models
arXiv:2506.07450v2 Announce Type: replace Abstract: A major bottleneck in the training process for Zero-Shot Coordination (ZSC) agents is the generation of diverse partner agents via Population-based Training (PBT). Prom…
- arXiv cs.AIagentsClosing the empirical loop: autonomous AI agents conduct end-to-end research with human participants
arXiv:2508.13421v3 Announce Type: replace Abstract: Artificial intelligence systems are transforming scientific discovery by accelerating specific research tasks, from protein structure prediction to materials design, ye…
- arXiv cs.AIagentsAgentic AI Empowered Intent-Based Networking for 6G
arXiv:2601.06640v2 Announce Type: replace Abstract: The transition towards sixth-generation (6G) wireless networks necessitates autonomous orchestration mechanisms capable of translating high-level operational intents in…
- arXiv cs.AIagentsCAFE: Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning
arXiv:2602.16435v2 Announce Type: replace Abstract: Automated feature engineering (AFE) enables AI systems to autonomously construct high-utility representations from raw tabular data. However, existing AFE methods rely…
- arXiv cs.AIagentsAutoB2G: Agentic Simulation and Reinforcement Learning for Spatio-Temporal Grid-Interactive Building Control
arXiv:2603.26005v3 Announce Type: replace Abstract: Grid-interactive building control can improve demand-side flexibility, but realistic evaluation requires coordinated co-simulation of buildings, reinforcement learning…
- arXiv cs.AIagentsTerminus-4B: Can a Smaller Model Replace Frontier LLMs at Agentic Execution Tasks?
arXiv:2605.03195v3 Announce Type: replace Abstract: Modern coding agents increasingly delegate specialized subtasks to subagents, which are smaller, focused agentic loops that handle narrow responsibilities like search,…
- arXiv cs.AIagentsMulti-Agent Debate for Belief Optimization in Defeasible Domains
arXiv:2605.12718v2 Announce Type: replace Abstract: Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain structural limitations:…
- arXiv cs.AIagentsAgents for Experiments, Experiments for Agents: A Design Grammar for AI-Enabled Experimental Science
arXiv:2605.17746v2 Announce Type: replace Abstract: Human-AI experiments vary who receives information, who can act, and who holds decision authority. Precise descriptions of individual studies do not by themselves provi…
- arXiv cs.AIagentsVitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data
arXiv:2605.29483v3 Announce Type: replace Abstract: Wearable devices provide continuous access to physiological signals such as ECG and PPG, offering a path to answering users' questions about their own physiological sta…
- arXiv cs.AIagentsHealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents
arXiv:2606.31179v2 Announce Type: replace Abstract: As AI agents become increasingly capable of complex, long-horizon reasoning, rigorous evaluation is essential for measuring progress toward real-world healthcare applic…
- arXiv cs.AIagentsCIPHER: A Decoupled Exploration-Selection Framework for Test-Time Scaling of Data Science Agents
arXiv:2607.14386v2 Announce Type: replace Abstract: Enterprise data science and analytics spans closed-ended information extraction with verifiable answers and open-ended insight discovery. Agents are evaluated on one or…
- arXiv cs.AIagentsArbiGraph: Arbitrarily Scalable Verifiable Task Graphs for Evaluating Context Management
arXiv:2607.20764v2 Announce Type: replace Abstract: We introduce ARBIGRAPH, a benchmark generator for evaluating whether tool-assisted language agents can retain, update, compose, and discard task-relevant context across…
- arXiv cs.AIagentsSpatialCLI: Learning to Reason With Spatial Tools, Then Without Them
arXiv:2607.27703v3 Announce Type: replace Abstract: Vision-language models (VLMs) are increasingly used in embodied agents to interpret visual inputs, reason about spatial relationships, and make task-level decisions bas…
- arXiv cs.AIagentsMeasurement Without Validity: The Compounding Reliability Problem in Agentic AI Evaluation
arXiv:2608.00794v5 Announce Type: replace Abstract: Agentic AI evaluation pipelines produce benchmark scores that justify deployment decisions, safety certifications, and regulatory compliance claims. No formal framework…
- arXiv cs.AIagentsGENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis
arXiv:2608.09921v3 Announce Type: replace Abstract: Foundation models are transforming business workflows and boosting productivity, yet they remain largely absent from engineering domains such as power system analysis,…
- arXiv cs.AIagentsRecovering Wasted Compute in Autoresearch Agents
arXiv:2608.10424v2 Announce Type: replace Abstract: A slew of recent works develop agents for solving research problems end-to-end, a paradigm increasingly referred to as autoresearch. Such agents have inspired large ind…