AI news archive.
4,966 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsAutonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery
arXiv:2610.18449v1 Announce Type: new Abstract: AI agents for autonomous scientific discovery must decide which experiments to run under a limited budget. Most benchmarks for science agents provide fixed datasets, while…
- arXiv cs.AIagentsReTerm: Recovery Training for Self-Improving Terminal Agents
arXiv:2610.18484v2 Announce Type: replace Abstract: Terminal agents have shown strong abilities in complex coding tasks. However, they often struggle to recover from errors during long-running execution (e.g., command er…
- arXiv cs.AIagentsJudges Follow the Reference: The Derivation Gap in Verifying Tool-Call Arguments
arXiv:2610.18497v1 Announce Type: new Abstract: Tool-call judges evaluate argument values proposed by LLM agents. We find that they accept a correct value less often when their input holds no reference for it, that is, n…
- arXiv cs.AIagentsLost in Implicit Routing: How LLM Agents Fail to Load Relevant Skills at Scale
arXiv:2610.18522v1 Announce Type: new Abstract: Reusable skills let LLM agents load task-specific instructions on demand, but they make execution depend on implicit routing over skill metadata. We test whether this desig…
- arXiv cs.AIagentsLLM Agents for Automated Post-Training via Structured Recipe Optimization
arXiv:2610.18572v1 Announce Type: new Abstract: Automated post-training transforms pre-trained large language models (LLMs) into models capable of handling diverse domains by automatically constructing and optimizing a r…
- arXiv cs.AIagentsReading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops
arXiv:2610.18579v1 Announce Type: new Abstract: System One models choose an agent's next action by scoring a supplied set of options in a single pass. This makes them fast and cheap, but when they choose wrongly there is…
- arXiv cs.AIagentsAuditing Future-Memory Use in Point-in-Time Language Agents
arXiv:2610.18602v1 Announce Type: new Abstract: Point-in-time (PIT) agents can recall post-cutoff facts even when their external evidence respects a historical cutoff. We examine whether this access predicts evidence gat…
- arXiv cs.AIagentsAgentStripes: An Evidence-Graded Maturity Model for AI Agents
arXiv:2610.18603v2 Announce Type: replace Abstract: Benchmarks report what an Artificial Intelligence (AI) agent can do on a task suite, but not whether one released version has been engineered with the controls that mak…
- arXiv cs.AIagentsCan an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents
arXiv:2610.18614v1 Announce Type: new Abstract: Controlling an acting LLM agent means deciding, at each step of a long-horizon task, whether to trust its next action, abstain, or hand off to a human. That decision needs…
- arXiv cs.AIagentsTwo Routes to Interoceptive Prioritisation: Dissociating Likelihood Precision and Preference Reweighting in Active Inference
arXiv:2610.18617v1 Announce Type: new Abstract: An embodied agent must prioritise among competing bodily needs. In active inference, it can respond to an urgent need by increasing the precision of information about that…
- arXiv cs.AIagentsKnowing the User Is Not Knowing What We Established: Grounding Awareness in Personal Agents
arXiv:2610.18684v1 Announce Type: new Abstract: Personal-agent memory has largely focused on learning what users know, prefer, and want. However, knowing the user does not necessarily mean knowing what the user and the a…
- arXiv cs.AIagentsBeyond the Verdict: Agentic Code Judging with Verifiable Feedback
arXiv:2610.18760v1 Announce Type: new Abstract: Test-time scaling for large language models (LLMs) can involve generating multiple candidate solutions for selection or revising an earlier attempt. To guide selection and…
- arXiv cs.AIagentsBLADE: Auditing Information Use for Failure Attribution in LLM Multi-Agent Systems
arXiv:2610.18780v1 Announce Type: new Abstract: Large language model multi-agent systems extend individual agents' capabilities through collaboration across specialized roles, tools, and workflows. Yet collaboration make…
- arXiv cs.AIagentsPack Light, CarryOn: Building Object-Oriented Context for Long-Horizon Agents
arXiv:2610.18784v2 Announce Type: replace Abstract: Long-horizon agents accumulate progress in persistent task state, yet repeatedly process interaction histories describing how that progress was achieved. This raises a…
- arXiv cs.AIagentsSelf-Evolving Agent Harness
arXiv:2610.18813v1 Announce Type: new Abstract: Harness self-evolution revises an agent's software scaffolding, including prompts, memory, workflows, and executable components, while keeping model weights fixed. We forma…
- arXiv cs.AIagentsWho Improves the Robot? Toward Physical Recursive Self-Improvement
arXiv:2610.18842v1 Announce Type: new Abstract: Robots are increasingly autonomous in task execution, yet their improvement remains largely human-driven. This study investigates Physical Recursive Self-Improvement (Physi…
- arXiv cs.AIagentsSelective Knowledge Control for Continual GUI Agent Learning over Application Streams
arXiv:2609.06530v1 Announce Type: cross Abstract: Continual learning is a crucial capability for Graphical User Interface (GUI) agents to adapt to evolving applications while retaining knowledge acquired from previous ap…
- arXiv cs.AIagentsPredict Before You Modify: Learning Improvement Dynamics for Self-Evolving Agents
arXiv:2610.13991v2 Announce Type: replace-cross Abstract: Self-evolving agents improve through repeated cycles of modification and evaluation. However, existing methods receive feedback on modifications only after costly…
- arXiv cs.AIagentsVH-GPO: Verified Handoff for LLM Agent Reinforcement Learning
arXiv:2610.14000v1 Announce Type: cross Abstract: Group-relative reinforcement learning methods such as GRPO train large language model (LLM) agents by comparing rollouts for the same task. When every trajectory in a gro…
- arXiv cs.AIagentsCoding LLMs Can Be Harnessed to Learn Interpretable Models from Data
arXiv:2610.14006v1 Announce Type: cross Abstract: Since compact, interpretable classifiers correspond to simple programs, it is natural to ask if LLM-based coding agents can be used to learn interpretable models from dat…
- arXiv cs.AIagentsCoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection
arXiv:2610.14021v1 Announce Type: cross Abstract: Training multi-agent collaboration requires trajectories of checking, feedback, and repair, yet task-solving rollouts may end in immediate approval or repeat unsuccessful…
- arXiv cs.AIagentsAuditing LLM Program Search for Bermudan Stopping with Primal--Dual Certificates
arXiv:2610.14063v1 Announce Type: cross Abstract: LLM program-search agents are usually judged by the score that drives their search. We study LLM-driven search over Python exercise policies for Bermudan options, an opti…
- arXiv cs.AIagentsLoose Lips: Understanding Privacy Leakage in Agentic Dialogue
arXiv:2610.14071v1 Announce Type: cross Abstract: As LLM agents are increasingly deployed in high-stakes enterprise settings, understanding how they handle sensitive information in agentic dialogue has become critical. P…
- arXiv cs.AIagentsTwo-Stage Multi-modal Learning for Dynamic Audio-Visual Navigation: From Physical Alignment to Scene Aggregation
arXiv:2610.14077v1 Announce Type: cross Abstract: Embodied Audio-Visual Navigation (AVN) requires an agent to locate sound targets by jointly leveraging visual and auditory cues. While prior work has achieved notable suc…
- arXiv cs.AIagentsSAGE: Efficient Protected Vision-Language Inference on Smart Glasses
arXiv:2610.14089v1 Announce Type: cross Abstract: Smart glasses are a promising platform for vision-language assistants, but private split inference remains expensive: protecting visual representations before transmissio…
- arXiv cs.AIagentsCortex: Measurement-Gated Evolution and Pruning of Coding-Agent Skills and Rules
arXiv:2610.14216v1 Announce Type: cross Abstract: Coding agents such as Claude Code also follow text files that developers write for them: a project file, skills the agent may choose to open, and rules that load automati…
- arXiv cs.AIagentsLatent World Action Model for GUI Agents
arXiv:2610.14228v1 Announce Type: cross Abstract: Pixel-space world models have recently emerged as a promising approach for GUI agents, predicting future screens prior to execution and subsequently re-perceiving them fo…
- arXiv cs.AIagentsAgentic Data Engineering for LLMs: System Design and a Controlled Empirical Study
arXiv:2610.14238v1 Announce Type: cross Abstract: LLM data engineering requires iterative experimentation to determine how data selection, rewards, and curricula affect model learning, making it a natural setting for AI-…
- arXiv cs.AIagentsNatural Code Transformation Confuses Agents in Vulnerability Analysis
arXiv:2610.14350v2 Announce Type: replace-cross Abstract: Having demonstrated a strong potential for automating vulnerability discovery, AI agents can also be used to attack software systems at scale. Today's software sy…
- arXiv cs.AIagentsRealityBench: Simulated Environments to Evaluate a Vision Language Model's Ability to Document Human Physical Work
arXiv:2610.14397v2 Announce Type: replace-cross Abstract: Augmenting worker capabilities in the physical world through guidance has been a decades-long goal for AI agents. One key supporting capability is to understand w…
- arXiv cs.AIagentsJevolution: A Framework for Studying Communication and Collective Dynamics in AI Agents
arXiv:2610.14449v1 Announce Type: cross Abstract: Experiments with remote decision-making agents depend on more than the policy: the world may change during inference, the simulator determines which actions are available…
- arXiv cs.AIagentsWhat Counts as the Same Task? Executable Contracts for Robustness Evaluation of Tool-Using Agents
arXiv:2610.14477v1 Announce Type: cross Abstract: Robustness tests for tool-using agents often change the agent's environment, for example by hiding a hostile note in an invoice, and then judge the agent by what it does.…
- arXiv cs.AIagentsA Self-Defining Operator for Distributed Applications
arXiv:2610.14547v2 Announce Type: replace-cross Abstract: To operate distributed applications with high availability, operators must rapidly diagnose and mitigate any incident. LLM-based agents can help, but unlike exper…
- arXiv cs.AIagentsActive Neural Matter: A Finite-Window Response Framework for Physical Systems and Distributed AI Workflows
arXiv:2610.14549v1 Announce Type: cross Abstract: Physical systems and distributed AI workflows can retain past information, receive delayed feedback and combine conflicting signals. These features pose a common modeling…
- arXiv cs.AIagentsVela: User Behavior as Supervision Sparks LLM Intelligence
arXiv:2610.14709v1 Announce Type: cross Abstract: Large language models are increasingly deployed in applications that act on users' long-term behavior histories, from personal assistants to recommendation and advertisin…
- arXiv cs.AIagentsSelf-improving data synthesis can scale embedding-model adaptation across domains and tasks
arXiv:2610.14730v3 Announce Type: replace-cross Abstract: AI agents require specialised retrieval across domains and tasks, but adapting embedding models is constrained by costly manual training-data design. Here we intr…
- arXiv cs.AIagentsPTGPO: Prefix Tree Group Policy Optimization
arXiv:2610.14737v1 Announce Type: cross Abstract: Training language agents on long-horizon interactive tasks is challenging because sparse terminal rewards provide weak credit signals for intermediate actions. Existing g…
- arXiv cs.AIagentsLast Secure Code Benchmark: Is the Code You Vibe Secure?
arXiv:2610.14766v1 Announce Type: cross Abstract: AI coding agents now write much of the code that ships, yet whether that code is secure remains unclear. We introduce the Last Secure Code Benchmark, a comprehensive eval…
- arXiv cs.AIagentsYOUDrive: Driving Style as a Composable Direction for End-to-End Autonomous Driving
arXiv:2610.14802v1 Announce Type: cross Abstract: End-to-end driving policies can achieve strong task performance while offering limited control over their driving style. Driving style describes how a vehicle accelerates…
- arXiv cs.AIagentsGetting Space Right: Agentic Rewards for Image Generation
arXiv:2610.14852v1 Announce Type: cross Abstract: Reinforcement learning (RL) is promising for spatial text-to-image generation, but existing work largely focuses on policy optimization, assuming accurate rewards and eff…
- arXiv cs.AIagentsHumans vs. Machines: A Comparison With AI Agents in Software Reverse Engineering
arXiv:2610.14960v1 Announce Type: cross Abstract: Can an autonomous AI agent reverse engineer a binary as well as a skilled human analyst? Do they adopt the same strategy, and can agents scale to real-world programs? We…
- arXiv cs.AIagentsTurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents
arXiv:2610.15093v1 Announce Type: cross Abstract: AI coding agents operate in iterative loops: they modify code, run tools, inspect the results, and decide what to do next. We call the design of this process loop enginee…
- arXiv cs.AIagentsRIECNN: Real-Time Image Enhanced CNN for Traffic Sign Recognition
arXiv:2610.15127v1 Announce Type: cross Abstract: Traffic sign recognition plays a crucial role in the development of autonomous cars to reduce the accident rate and promote road safety. It has been a necessity to addres…
- arXiv cs.AIagentsPANINI-DR: Controlled Deep Research through Generative Semantic Workspaces
arXiv:2610.15208v2 Announce Type: replace-cross Abstract: Deep research requires connecting multiple steps of search, reasoning, and computation, with intermediate findings guiding what to investigate next. As investigat…
- arXiv cs.AIagentsEvolvAttack: Backdooring self Evolving VLM Agents
arXiv:2610.15244v1 Announce Type: cross Abstract: Self-evolving mechanisms let vision-language model (VLM) agents continually adapt through evolving memory, but they also allow malicious behavior to emerge only after dep…
- arXiv cs.AIagentsSequent-Prover: Training Agents for Formal, Checkable SMT-based Reasoning
arXiv:2610.15258v1 Announce Type: cross Abstract: We introduce Sequent-Prover, a family of verifier-using language-model agents, and the post-training framework that produces them. Agents reason in an executable SMT-LIB…
- arXiv cs.AIagentsAdversarial Detection for Pre-trained Classifiers via Lipschitz-Margin Analysis with Certification
arXiv:2610.15359v1 Announce Type: cross Abstract: Deep classifiers deployed in safety-critical services like autonomous-driving perception remain vulnerable to small adversarial perturbations. Certified $\ell_2$ defenses…
- arXiv cs.AIagentsSensitivity or Criterion? Measuring and Moving When Language Models Act
arXiv:2610.15415v1 Announce Type: cross Abstract: Before an agent acts, it must decide whether action is warranted. A single accuracy cannot distinguish failure to recognize a warranted action from reluctance to act. Sig…
- arXiv cs.AIagentsWhen Messages Go Wrong: Understanding Communication Faults in LLM-Based Multi-Agent Systems
arXiv:2610.15459v1 Announce Type: cross Abstract: LLM-based multi-agent systems (LLM-MAS) use specialized agents that exchange messages to accomplish complex tasks. Their reliance on networked protocols, remote tools, an…
- arXiv cs.AIagentsImproving the Bounds on Approximating Weighted Maximin Share for Chores
arXiv:2610.15520v1 Announce Type: cross Abstract: We investigate the problem of allocating indivisible chores among agents with arbitrary positive weights and additive nonnegative cost functions. An allocation is said to…