AI news archive.
4,966 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsVEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails
arXiv:2610.12813v1 Announce Type: new Abstract: LLM agents increasingly operate over sensitive resources, such as private documents and mutable system states, which can create serious safety and security risks. Runtime g…
- arXiv cs.AIagentsReward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems
arXiv:2610.12822v2 Announce Type: replace Abstract: Multi-agent systems are increasingly used to solve coding tasks by coordinating agents that share code and plans. These agents are often optimized with reinforcement le…
- arXiv cs.AIagentsAI-Mediation in Retail Markets: Revenue Effects and Assortment Optimization
arXiv:2610.12917v1 Announce Type: new Abstract: AI shopping assistants increasingly influence which products consumers consider. We study retail assortment planning under AI mediation, where a retailer chooses a catalog,…
- arXiv cs.AIagentsSmartSalesBench: A Resistance-Aware Multi-Turn Benchmark for Evaluating LLM Sales Agents
arXiv:2610.12975v1 Announce Type: new Abstract: We present SmartSalesBench, the first multi-turn conversational benchmark explicitly designed to evaluate large language model (LLM) sales agents against psychologically gr…
- arXiv cs.AIagentsWork2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction
arXiv:2610.12984v1 Announce Type: new Abstract: Computer-use agents can perform increasingly complex GUI tasks, yet unfamiliar software and workflows requiring human domain knowledge remain challenging. Human demonstrati…
- arXiv cs.AIagentsHindsight Structured Advice Distillation: Steering Executor Agents with Advisors Trained on Their Failures and Task Characteristics
arXiv:2610.13000v1 Announce Type: new Abstract: Language-model agents are used for specialized work such as financial research, healthcare and law. Such agents are often capable enough for a task but still miss its detai…
- arXiv cs.AIagentsScaling Empowered Agents
arXiv:2610.13002v1 Announce Type: new Abstract: Empowerment measures the capacity of an agent to actively control its environment. In this work, we explain the connection between skill learning and empowerment. While ski…
- arXiv cs.AIagentsEmbodiedCLBench: Evaluating Continual Learning for Self-Evolving Embodied Agents
arXiv:2610.13021v1 Announce Type: new Abstract: Continual learning requires models to accumulate past experience and transfer it to new tasks. Despite substantial research on continual learning, existing work remains lar…
- arXiv cs.AIagentsTravel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents
arXiv:2610.13058v1 Announce Type: new Abstract: Large language model agents increasingly operate in long-horizon environments where early mistakes can trigger cascading failures and trap agents in dead-end trajectories.…
- arXiv cs.AIagentsLongHarness: Advancing Agentic Reasoning over 100M-Token Corpora via Stateful Evidence Management
arXiv:2610.13075v1 Announce Type: new Abstract: Corpus-level long-context reasoning requires agents to acquire and integrate evidence across document collections that exceed their context windows. Existing agent harnesse…
- arXiv cs.AIagentsWhen Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent Workflows
arXiv:2610.13092v1 Announce Type: new Abstract: AI agents depend on repeated decisions to accomplish tasks, with large language models (LLMs) commonly serving as their core decision makers. The recent emergence of Jev of…
- arXiv cs.AIagentsVETR: Execution-Grounded Self-Improving Agent for Symbolic Graphics Reasoning
arXiv:2610.13098v2 Announce Type: replace Abstract: Visual agents for symbolic graphics reasoning depend on executable world representations, yet continued improvement remains bottlenecked by ambiguous supervision from f…
- arXiv cs.AIagentsDRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design
arXiv:2610.13116v1 Announce Type: new Abstract: As large language models (LLMs) acquire advanced biological design capabilities, they offer substantial research benefits but simultaneously introduce severe dual-use risks…
- arXiv cs.AIagentsLocate, Judge, Read: Role-Specialized Tool Agents over a Knowledge-Point Index for Open-Domain Multimodal Document QA
arXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-augmented agents giv…
- arXiv cs.AIagentsCompetence-Aware Orchestration for LLM-Based Multi-Agent Systems
arXiv:2610.13144v1 Announce Type: new Abstract: LLM-based multi-agent systems (MAS) have emerged as a promising paradigm for enhancing complex reasoning through role specialization and collaboration, yet a key challenge…
- arXiv cs.AIagentsQuality, Not Just Outcome: A Structural Scoring Framework for Selecting Coding-Agent Trajectories for Supervised Fine-Tuning
arXiv:2610.13152v1 Announce Type: new Abstract: Open coding agents are commonly trained through supervised fine-tuning on interaction trajectories whose final patches pass the benchmark test suite. However, this outcome-…
- arXiv cs.AIagentsRoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions
arXiv:2610.13172v1 Announce Type: new Abstract: World models enable large language model (LLM) agents to anticipate action effects and make informed decisions. For generalization, it is desirable for such world models to…
- arXiv cs.AIagentsJANUS: Enhancing Long-Horizon Autonomous Research with Co-Evolving World Models
arXiv:2610.13194v1 Announce Type: new Abstract: Long-horizon autonomous research has shown promise in accelerating scientific progress through sustained cycles of hypothesis generation, implementation, and validation. Ho…
- arXiv cs.AIagentsForgetting is Not Always Bad: A Neuro-Inspired Memory Repair Mechanism for Poisoned LLM Agents
arXiv:2610.13267v1 Announce Type: new Abstract: Large language model (LLM) agents are highly vulnerable to memory-poisoning attacks. Existing defenses primarily rely on external modules for either static memory isolation…
- arXiv cs.AIagentsMasked Diffusion Language Agents for Tool-Integrated Chemical Reasoning
arXiv:2610.13330v1 Announce Type: new Abstract: Designing tool-integrated reasoning agent systems for complex chemical tasks remains a fundamental challenge. Although recent chemical agents have demonstrated promising pe…
- arXiv cs.AIagentsSWE-Critix: Post-Training Generalist Verifiers for Assessing Coding-Agent Trajectories
arXiv:2610.13356v2 Announce Type: replace Abstract: Coding agents are increasingly deployed for end-to-end software engineering tasks, where a readily available oracle evaluator that defines the success criteria is often…
- arXiv cs.AIagentsWeb$hell: A Unified Interface for Agentic Web Access
arXiv:2610.13416v1 Announce Type: new Abstract: Large language model (LLM) agents are becoming direct users of the open web. As they take on increasingly complex and information-intensive tasks, effective web access is b…
- arXiv cs.AIagentsRollout-Time Intervention: Unlocking Agentic Reinforcement Learning Beyond Policy Limits
arXiv:2610.13438v2 Announce Type: replace Abstract: Reinforcement learning (RL) has emerged as a key paradigm for improving large language model (LLM) agents, enabling stronger reasoning, planning, and tool-use in intera…
- arXiv cs.AIagentsAgentic Large Language Models
arXiv:2610.13455v1 Announce Type: new Abstract: Large language models (LLMs) have taken the world by storm. Their ability to communicate with us in our own language, and to reason about our world, has made them a favorit…
- arXiv cs.AIagentsA Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance
arXiv:2610.13479v1 Announce Type: new Abstract: Generating edge case scenarios is crucial for training, testing and safety assuring autonomous systems. This identifies hazardous failures to increase system reliability an…
- arXiv cs.AIagentsHumanize MLE Agents: Multi-Agent Session Alternation Beyond Single-Agent Limits
arXiv:2610.13494v1 Announce Type: new Abstract: Existing LLM-based agent approaches for long-horizon machine learning engineering (MLE) often use context engineering, implemented through custom harnesses that manage tool…
- arXiv cs.AIagentsMAGMA-Bench: Evaluating Long-Horizon Embodied Agents under Dynamic Tasks and Execution Failures
arXiv:2610.13534v1 Announce Type: new Abstract: Long-horizon embodied agents must maintain task-relevant information, coordinate heterogeneous robots, and adapt their decisions as execution unfolds. Existing benchmarks i…
- arXiv cs.AIagentsHumanize Olympiad Agents: A Multi-Session Workflow for Olympiad Problem Solving with Solve, Review, Wiki, Verify
arXiv:2610.13632v1 Announce Type: new Abstract: Large language model (LLM) agents are rapidly improving on long-horizon scientific and olympiad tasks. Recent systems have produced a Lean-formalized resolution of the Navi…
- arXiv cs.AIagentsA Multi-Agent LLM System for Automated Tuning of Specialized Neural Network Models
arXiv:2610.13663v1 Announce Type: new Abstract: Many machine learning approaches are two-level: an expert selects a class of methods, within this class the choice of key components is critical and usually manual. This pa…
- arXiv cs.AIagentsA Baseline Assessment for the Agentic Web Technology Stack
arXiv:2610.13703v1 Announce Type: new Abstract: The fast pace in which protocols, frameworks, and technologies are being proposed for LLM-based agents results in a complex scenario for anyone aiming to create state-of-th…
- arXiv cs.AIagentsX-AgentRed: Red-Teaming Personal Agents in Evolving Multi-Service Ecosystems
arXiv:2610.13886v1 Announce Type: new Abstract: Personal agents increasingly connect to services across the web and applications by using tools. As the effects of their actions accumulate and interact across services, un…
- arXiv cs.AIagentsRATED: Reliability-Aware AI Agent Tool Retrieval via Execution Dynamics
arXiv:2610.13889v1 Announce Type: new Abstract: As AI agents increasingly rely on external tools, accurate retrieval is essential for reliable behavior. Existing methods optimize semantic relevance but largely ignore too…
- arXiv cs.AIagentsRecurrent Harness for Agentic Continual Learning
arXiv:2610.12668v1 Announce Type: cross Abstract: Language model agents increasingly operate over long interaction streams, requiring online adaptation to distribution shifts through continual learning. However, existing…
- arXiv cs.AIagentsTrajectory Prediction for Autonomous Driving in Road Construction Zones Using Human-in-the-Loop Driving Data
arXiv:2610.12747v1 Announce Type: cross Abstract: Ego-trajectory prediction in urban roadway work zones remains an underexplored topic in autonomous-driving research, with limited dedicated data and systematic evaluation…
- arXiv cs.AIagentsCo-Modifying Application Code and Deployment Infrastructure: A Causal Study of AI Agent Pull Requests
arXiv:2610.12849v1 Announce Type: cross Abstract: Current software engineering agents are evaluated predominantly inside isolated sandboxes against synchronous local tests. However, deploying features in collaborative re…
- arXiv cs.AIagentsJoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents
arXiv:2610.12957v1 Announce Type: cross Abstract: Embodied agents must translate multimodal observations and user requests into executable actions while adapting to product constraints, changing goals, and execution feed…
- arXiv cs.AIagentsAgent4Spec: An LLM-based Agentic System to Optimize API Specifications through Automated Validation and Market Analysis
arXiv:2610.13273v1 Announce Type: cross Abstract: API specifications serve as critical documentation for modern software development, directly impacting integration efficiency and client code generation. While recent adv…
- arXiv cs.AIagentsPRIME: Pre-Retrieval Index Modeling Enhancement for Structured Document Retrieval-Real
arXiv:2610.13296v1 Announce Type: cross Abstract: High-precision retrieval over external knowledge bases is essential for LLM agents to operate effectively. However, existing Information Retrieval (IR) research primarily…
- arXiv cs.AIagentsAgentSWE: Can Coding Agents Build the Agent You Actually Want?
arXiv:2610.13361v1 Announce Type: cross Abstract: As the production of software passes into the hands of software itself, coding agents are increasingly commissioned to build agents fitted to their users' own workflows.…
- arXiv cs.AIagentsProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents
arXiv:2610.13395v1 Announce Type: cross Abstract: Coding agents are increasingly used to build programs from scratch as software engineers do rather than to resolve issues within a repository or to generate a repository…
- arXiv cs.AIagentsCollective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human Drivers
arXiv:2610.13439v1 Announce Type: cross Abstract: Collective Autonomous Vehicle (AV) route choices in real-world traffic networks can create externalities for Human-Driven Vehicles (HDVs), as routes that benefit AVs may…
- arXiv cs.AIagentsSafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning
arXiv:2610.13737v1 Announce Type: cross Abstract: Cooperative multi-agent tasks often impose constraints on a shared objective or collective safety. A team level violation cost function can measure this constraint outcom…
- arXiv cs.AIagentsMatched-Context Group Policy Optimization for LLM Agent Training
arXiv:2610.13755v1 Announce Type: cross Abstract: Training long-horizon language model agents requires assigning credit to intermediate decisions from sparse terminal feedback. Within a finite group of sibling rollouts,…
- arXiv cs.AIagentsMC-EvoBench: Auditing Experience-Driven Self-Improvement in Minecraft Agents
arXiv:2610.13829v1 Announce Type: cross Abstract: A central challenge in embodied recursive self-improvement is enabling agents to convert interaction history into capabilities that persist beyond one world and transfer…
- arXiv cs.AIagentsCoMMa: Contribution-Aware Medical Multi-Agents for Decentralized Oncology Decision Support
arXiv:2602.09159v3 Announce Type: replace Abstract: Recent multi-agent frameworks have shown promise for oncology decision support, yet most assume centralized data access and rely on prompt-based assignment, limiting th…
- arXiv cs.AIagentsAutoControl Arena: Synthesizing Executable Test Environments for Frontier AI Risk Evaluation
arXiv:2603.07427v3 Announce Type: replace Abstract: As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based s…
- arXiv cs.AIagentsCan Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning
arXiv:2605.07251v2 Announce Type: replace Abstract: Large Language Models (LLMs) have become increasingly capable as tool-using agents, with benchmarks spanning diverse general agentic tasks. Yet rigorous evaluation of s…
- arXiv cs.AIagentsWhen Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
arXiv:2605.11928v2 Announce Type: replace Abstract: Tool-use language agents are evaluated on benchmarks that assume clean inputs, unambiguous tool registries, and reliable APIs. Real deployments violate all these assump…
- arXiv cs.AIagentsEvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents
arXiv:2606.03678v2 Announce Type: replace Abstract: Generating safety-critical scenarios is essential for validating and improving autonomous driving systems, yet it inherently requires maximizing adversariality to expos…
- arXiv cs.AIagentsThe Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents
arXiv:2606.04296v2 Announce Type: replace Abstract: As autonomous AI agents move from conversational systems to long-horizon software execution, runtime safety layers that decide when to interrupt an agent have become es…