AI news archive.
4,958 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsHeterogeneous Co-Evolution Learning for Tool-Efficient Search Agents with Zero Labels
arXiv:2610.39682v1 Announce Type: cross Abstract: Deep search agents extend language models by interleaving reasoning with external retrieval. However, effective search-agent training requires addressing two challenges b…
- arXiv cs.AIagentsPractical Assessment of Agentic Systems in Acoustics
arXiv:2610.39685v1 Announce Type: cross Abstract: In engineering, applications of artificial intelligence have so far been largely limited to surrogate models and optimization tasks. Large language models changed this, a…
- arXiv cs.AIagentsSandman: Building and Operating Sandboxes for Agentic Reinforcement Learning on Shared Kubernetes
arXiv:2610.39711v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) often requires repeated tool calls in task-specific environments. A training job may create thousands of these environments in bursts…
- arXiv cs.AIagentsInferD: A Honeypot Framework for AI Inference Infrastructure
arXiv:2610.39807v1 Announce Type: cross Abstract: Large language model serving stacks, commercial inference APIs, vector databases, and agent orchestration gateways are now ex- posed on the public internet and indexed by…
- arXiv cs.AIagentsLiDAR-SHIELD: A Fully Dockerized Adversarial Robustness Assessment Framework for LiDAR-Based 3D Perception Models
arXiv:2610.39848v1 Announce Type: cross Abstract: LiDAR-based 3D perception underpins autonomous driving and robotics, yet deploying these models safely requires stress-testing them against adversarial inputs before real…
- arXiv cs.AIagentsLearning Calibrated Confidence for Multi-Agent Collaboration
arXiv:2610.39927v1 Announce Type: cross Abstract: Complex information seeking on the Web often requires collecting evidence from multiple documents and reasoning across them, as in multi-hop question answering. Multi-age…
- arXiv cs.AIagentsLearned Terminal Costs for Short-Horizon Model Predictive Control of Autonomous Trucks in Interactive Highway Traffic
arXiv:2610.40257v1 Announce Type: cross Abstract: Autonomous highway driving for heavy-duty trucks is a challenging control problem. The greater mass, dimensions and intricate dynamics increase the requirements for coope…
- arXiv cs.AIagentsTaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents
arXiv:2610.40276v1 Announce Type: cross Abstract: Building general game agents requires both high-level task reasoning and low-latency action control in rapidly changing visual environments. These capabilities favor mode…
- arXiv cs.AIagentsThe Athlete as a Scientist of One: Agentic Bayesian Experimental Design for Individualized Physiology from Consumer Wearables
arXiv:2610.40370v1 Announce Type: cross Abstract: Large language model (LLM) agents for personal health read wearable data and recommend, but do not learn about the individual in a way that can be audited or falsified. W…
- arXiv cs.AIagentsGym-Anything for Robotics: Scaling physical simulations with digital agents
arXiv:2610.40565v1 Announce Type: cross Abstract: Realistic, fast robotics simulations could enable large-scale training of embodied AI models that transfer to the real world. However, despite decades of progress, availa…
- arXiv cs.AIagentsWhen to Assist and What to Suggest: Joint Gating and Memory-Grounded Hint Generation in One Compact Decoder
arXiv:2610.40611v1 Announce Type: cross Abstract: Proactive assistants offer short, memory-grounded hints during a conversation, deciding when to assist and what to suggest. Current systems split this between a gate and…
- arXiv cs.AIagentsFrom extreme weather to agricultural consequences with agentic AI
arXiv:2610.40641v1 Announce Type: cross Abstract: Extreme weather is forecast days ahead, yet its consequences for agriculture remain hard to predict: a forecast says where a storm will strike, not which crops will suffe…
- arXiv cs.AIagentsPRISM: Festina Lente Proactivity -- Risk-Sensitive, Uncertainty-Aware Deliberation for Proactive Agents
arXiv:2602.01532v2 Announce Type: replace Abstract: Proactive agents must decide not only what to say but also whether and when to intervene. Many current systems rely on brittle heuristics or indiscriminate long reasoni…
- arXiv cs.AIagentsLearning to Model Optimization Problems from Solver Outcomes
arXiv:2604.00442v2 Announce Type: replace Abstract: Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on…
- arXiv cs.AIagentsExploration and Exploitation Errors Are Measurable for Language Model Agents
arXiv:2604.13151v2 Announce Type: replace Abstract: Language Model (LM) agents are increasingly used in complex decision-making tasks, from AI coding to physical AI, where they must both explore a search space and exploi…
- arXiv cs.AIagentsAEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning
arXiv:2605.00425v4 Announce Type: replace Abstract: Reinforcement learning (RL) has substantially improved the ability of large language model (LLM) agents to interact with environments and solve multi-turn tasks. Howeve…
- arXiv cs.AIagentsWhen Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
arXiv:2605.07313v2 Announce Type: replace Abstract: Memory-agent evaluations report fixed-snapshot accuracy or retrieval quality, but these scores do not show whether evidence remains usable as irrelevant sessions (sessi…
- arXiv cs.AIagentsRobust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning
arXiv:2605.12655v4 Announce Type: replace Abstract: Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external natural language instructions that interrupt ongoing behavior and confli…
- arXiv cs.AIagentsINFRAMIND: Infrastructure-Aware Multi-Agent Orchestration
arXiv:2606.11440v2 Announce Type: replace Abstract: Multi-agent LLM systems spend additional computation on reasoning and collaboration, but shared serving queues can prevent that computation from producing answers befor…
- arXiv cs.AIagentsPoisoning Agentic Alpha: Adversarial Vulnerabilities Across Roles and Architectures in Multi-Agent Trading Systems
arXiv:2608.24069v2 Announce Type: replace Abstract: LLM-based multi-agent trading systems are moving from research prototypes to live deployments that control real assets. They ingest news and social media from the open…
- arXiv cs.AIagentsRePolicy: Learning to Select and Apply Safety Policies for Agent Safeguards
arXiv:2608.24275v3 Announce Type: replace Abstract: Agent safeguards must determine whether an agent's behavior violates the safety rules of the current task, environment, and user. Because these rules vary across contex…
- arXiv cs.AIagentsATLAS: Dual-Horizon Diagnostic Evaluation for Tool-Use Agents in Meituan Xiaotua
arXiv:2608.30685v2 Announce Type: replace Abstract: LLM-based assistants on web-scale service platforms increasingly address local-service needs through multi-step planning and tool use. Under dynamic business conditions…
- arXiv cs.AIagentsVoiceLongMemEval: Do Assistants Remember How You Sounded?
arXiv:2609.00570v3 Announce Type: replace Abstract: With the growing scale of multi-agent architectures and large language models, deployed AI assistants are increasingly tasked with reasoning over long, continuous, mult…
- arXiv cs.AIagentsGeneralized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement
arXiv:2609.13406v2 Announce Type: replace Abstract: When we speak of recursive self-improvement (RSI), are we speaking of a phenomenon, a mechanism, or a prospect? Towards autonomous and evolving intelligence, RSI is bei…
- arXiv cs.AIagentsEvaluation Metrics for Safe Reinforcement Learning
arXiv:2609.15315v2 Announce Type: replace Abstract: Safe reinforcement learning (RL) is commonly formalized as a Constrained Markov Decision Process (CMDP), in which an agent maximizes expected reward while keeping its e…
- arXiv cs.AIagentsWorld Model Science: Self-Organized Criticality, Weak Chaos, and Metastable Belief Dynamics in Long-Horizon LLM Agents
arXiv:2609.17419v2 Announce Type: replace Abstract: Long-horizon LLM agents must maintain and update a world model over extended sequences of observations, actions, decisions and tool calls. We study the dynamics of long…
- arXiv cs.AIagentsExact Algorithms for Multiagent Path Finding with Communication Constraints on Tree-Like Structures
arXiv:2412.08556v4 Announce Type: replace-cross Abstract: Consider the scenario where multiple agents have to move in an optimal way through a network, each one towards their ending position while avoiding collisions. By…
- arXiv cs.AIagentsAligned Delta-Triplane Transformers as Occupancy World Models
arXiv:2503.07338v5 Announce Type: replace-cross Abstract: Occupancy World Models (OWMs) aim to predict future 3D occupancy scenes from historical observations and future ego motions, providing a useful world simulation t…
- arXiv cs.AIagentsThe Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural Network
arXiv:2508.21380v4 Announce Type: replace-cross Abstract: Recent mechanistic work has uncovered learned algorithms within neural networks, from modular arithmetic to search and planning in game-playing agents. But does a…
- arXiv cs.AIagentsDualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents
arXiv:2511.20709v3 Announce Type: replace-cross Abstract: Large language models (LLMs) and LLM-based coding agents are now used to generate code from natural-language specifications, yet ensuring such code is both functi…
- arXiv cs.AIagentsAnagent For Enhancing Scientific Table & Figure Analysis
arXiv:2602.10081v3 Announce Type: replace-cross Abstract: In scientific research, analysis requires accurately interpreting complex multimodal knowledge, integrating evidence from different sources, and drawing inference…
- arXiv cs.AIagentsMulti-Agent LLMs for Adaptive Acquisition in Bayesian Optimization
arXiv:2603.28959v2 Announce Type: replace-cross Abstract: The exploration-exploitation trade-off is central to sequential decision-making and black-box optimization, yet how Large Language Models (LLMs) reason about and…
- arXiv cs.AIagentsIncentives Shape How Humans Co-Create with Generative AI
arXiv:2604.03529v2 Announce Type: replace-cross Abstract: Generative AI is quickly becoming an integral part of people's everyday workflows. Early evidence has shown that while generative AI can increase individual-level…
- arXiv cs.AIagentsGUITestScape: Towards Open-set Evaluation on Exploratory GUI Testing
arXiv:2605.29532v2 Announce Type: replace-cross Abstract: Exploratory GUI testing is a particularly demanding setting for MLLM agents: without predefined test scripts, an agent must autonomously navigate an application a…
- arXiv cs.AIagentsReal-World Evaluation of an AI Agent Drafting Translational Impact Summaries
arXiv:2607.16989v3 Announce Type: replace-cross Abstract: Introduction. Clinical and Translational Science Award (CTSA) programs must document their scholars' research impact, but assembling each scholar's record by hand…
- arXiv cs.AIagentsBreadcrumbing Search Agents: Per-Turn Scheming Over Long-Horizon Trajectories
arXiv:2608.04565v3 Announce Type: replace-cross Abstract: LLM-based search agents are widely used for information-seeking tasks, but their reliance on external tool returns introduces a critical security risk: web conten…
- arXiv cs.AIagentsKumbhDoot: A Scale-Ready, LLM-Bounded Architecture for Mass-Gathering Public-Service Assistants
arXiv:2608.07520v2 Announce Type: replace-cross Abstract: Mass religious gatherings such as the Kumbh Mela concentrate tens of millions of people into a single region over a few weeks, producing intense, repetitive, mult…
- arXiv cs.AIagentsDo Personalized Skills Help Coding Agents? An Empirical Study of Developer Interaction Traces
arXiv:2608.10319v3 Announce Type: replace-cross Abstract: As human developers increasingly collaborate with large language model (LLM)-powered coding agents, adapting to individual developer preferences, potentially via…
- SiliconANGLE AIagentsMonday.com bets on deployment experts to turn AI agents into real returns
Enterprises have embraced AI for everyday tasks, but turning autonomous agents into measurable business returns is proving far harder. The bottleneck is no longer the technology but the organizational change needed to re…
- SiliconANGLE AIagentsHPE cuts executive status meetings with no-code apps built on monday.com
Enterprises are learning that no-code apps deliver the most value when the people closest to the work build them. As AI agents arrive inside work management platforms, the harder task is getting employees comfortable eno…
- TechCrunch AIagentsRivian expands joint venture with VW to include AI assistant
Rivian doesn't disclose if the value of its $5.8 billion joint venture will expand as a result.
- The Register AI + MLagentsStartup wants to make AI agents safe for DevOps duty
Infrastructure automation needs something better than prompt and pray
- Tom's Guide AIagentsAmazon just added 100+ new ways to use Alexa for Shopping —and these are the ones I'm trying first
Consumer AI launches, tools, and practical coverage.
- The Verge AIagentsYou can generate and edit Google Docs files directly in Gemini chats now
Now you can generate, preview, and edit PDFs, Google Docs, Google Sheets, slide decks, Markdown files, TXT files, and code directly within Google Gemini. The new file editing capabilities are available starting today for…
- SiliconANGLE AIagentsMotion Picture Association runs its legal operations on a CRM built for sales
Legal operations teams are finding that software built for sales pipelines can just as easily run investigations and member communications. As AI agents take on triage work, even nontechnical teams are building those wor…
- AWS Machine Learning BlogagentsBuilding intent-driven UI testing with Amazon Nova Act
Epsilon's Agentic Platform team delivers UI testing as a managed, multi-tenant service built on Amazon Nova Act and Amazon Bedrock AgentCore Browser Tool. Tests are written in plain English and run on browsers managed by…
- SiliconANGLE AIagentsContinuous close could make accountants everyday business advisors
Continuous close, in which a company’s books are closed every day instead of weeks after month-end, could change how accounting firms serve clients. As artificial intelligence shrinks the lag between a transaction and th…
- Simon Willison's WeblogagentsBuilding a multiplayer game world with autonomous Fable-class models
How I Built the Most AI-Pilled Company in the World Don't be put off by the clickbait headline, this piece by Jacob Sansbury describing how they are building Spawn is a fascinating exploration of the bleeding edge of wha…
- AWS Machine Learning BlogagentsHow MoEngage turned over 400 APIs into agent tools with AgentCore Gateway
MoEngage turned roughly 400 private REST APIs across 7 AWS Regions into permission-scoped agent tools with Amazon Bedrock AgentCore Gateway. No per-service MCP servers, no public endpoints, and no 400-tool context bloat.…
- Guardian AIagentsWhat is it like to work when your co-workers are AI agents?
Using AI for roles from executive assistants to chiefs of staff, companies are boasting about doing more with less, creating tension with their human workers On an average workday, Dhruv Amin chats with dozens of colleag…