AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsMosaic: Multi-Session Agentic Reinforcement Learning
arXiv:2610.22174v1 Announce Type: cross Abstract: Most existing agentic reinforcement learning methods assume single-session trajectories, where interaction proceeds within one continuously accumulated context. However,…
- arXiv cs.AIagentsDecentralized LLM Workflows via Sequential Auctions
arXiv:2610.22201v1 Announce Type: cross Abstract: We present a scalable framework for solving multi-step tasks through a decentralized market of self-interested agents. Prior theoretical work demonstrated that agents org…
- arXiv cs.AIagentsBeyond Downstream QA: Rethinking How We Evaluate Agent Memory
arXiv:2610.22209v1 Announce Type: cross Abstract: Agent memory benchmarks evaluate whether an agent's responses reflect correct knowledge, measuring downstream question-answering accuracy as a proxy for memory quality. W…
- arXiv cs.AIagentsOS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using Agents
arXiv:2610.22234v1 Announce Type: cross Abstract: Real desktop automation is neither purely visual nor purely programmatic. Agents must understand user-facing interfaces while efficiently manipulating files, scripts, and…
- arXiv cs.AIagentsLanguage Is a Security Surface for Agent Guards
arXiv:2610.22244v1 Announce Type: cross Abstract: Step-level guards decide, before each tool call, whether an agent's next action is safe given the user's request and the trajectory so far. Users write those requests in…
- arXiv cs.AIagentsLibrarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
arXiv:2610.22273v1 Announce Type: cross Abstract: Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval methods are inherently reactive, bottlenecking agents with…
- arXiv cs.AIagentsLearning to Steer LLM Agents and Multi-Agent Systems
arXiv:2610.22316v1 Announce Type: cross Abstract: Large language model (LLM)-based agents and multi-agent systems increasingly tackle complex tasks through long-horizon tool use and inter-agent collaboration. However, th…
- arXiv cs.AIagentsLearning Self-Orchestration in Decentralized Agent Swarms
arXiv:2610.22322v2 Announce Type: replace-cross Abstract: The capabilities of an agent swarm depend on both its individual members and how they coordinate. Yet existing multi-agent systems often train agents within fixed…
- arXiv cs.AIagentsPlayPolicy: Dexterity from Supervised Play
arXiv:2610.22340v2 Announce Type: replace-cross Abstract: How can robots autonomously collect the contact-rich experience needed to learn dexterous manipulation? We present PlayPolicy: Dexterity from supervised play (DSP…
- arXiv cs.AIagents3DCodeVerse: Exploring 3D Worlds as Code
arXiv:2610.22341v1 Announce Type: cross Abstract: We introduce 3DCodeVerse, a research ecosystem that enables coding agents to create editable and verifiable 3D content at scale. 3DCodeVerse comprises large-scale, high-q…
- arXiv cs.AIagentsAgent Skill Framework: Perspectives on the Potential of Small to Medium Language Models in Industrial Environments
arXiv:2602.16653v4 Announce Type: replace Abstract: Skills are getting increasingly used in recent agentic frameworks, performing robustly with proprietary LLMs. Yet, their effectiveness for small and medium-sized open-s…
- arXiv cs.AIagentsWorkflowPerturb: Calibrated Stress Tests for Evaluating Multi-Agent Workflow Metrics
arXiv:2602.17990v4 Announce Type: replace Abstract: Multi-agent LLM systems that generate structured workflows from natural-language requests are now deployed in production across cloud automation, DevOps, and enterprise…
- arXiv cs.AIagentsSelf-Programmed Execution for Language-Model Agents
arXiv:2605.06898v2 Announce Type: replace Abstract: At the heart of a language model agent is an orchestrator program which is responsible for the state transition between consecutive turns. In existing systems, this pro…
- arXiv cs.AIagentsPREPING: Zero-Task Agent Memory Construction via Self-Practice
arXiv:2605.13880v2 Announce Type: replace Abstract: Agent memory is typically constructed either offline from curated demonstrations or online from post-deployment interactions. However, regardless of how it is built, an…
- arXiv cs.AIagentsProspective multi-pathogen disease forecasting using autonomous LLM-guided tree search
arXiv:2605.16238v2 Announce Type: replace Abstract: Probabilistic forecasting of infectious diseases is crucial for public health monitoring and preparedness but has historically relied on labor-intensive manual model cu…
- arXiv cs.AIagentsAdapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents
arXiv:2605.22166v3 Announce Type: replace Abstract: LLM agents are shaped not only by their language models, but also by the runtime harness that mediates observation, tool use, action execution, feedback interpretation,…
- arXiv cs.AIagentsHarness-Bench: Evaluating Agent Harnesses across Models and Realistic Workflows
arXiv:2605.27922v2 Announce Type: replace Abstract: LLM agents are increasingly deployed as executable systems that use tools, modify workspaces, and produce concrete artifacts. In such workflows, performance depends not…
- arXiv cs.AIagentsSkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
arXiv:2606.03056v3 Announce Type: replace Abstract: Large skill libraries are now standard equipment for LLM agents, and which subset reaches the prompt decides what the agent can do. Enumeration and top-$K$ embedding re…
- arXiv cs.AIagentsEvoFlux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
arXiv:2606.12674v2 Announce Type: replace Abstract: Small language models (1.5B-4B parameters) offer low-cost, low-latency tool use but often produce plausible plans that fail during execution due to unavailable tools, m…
- arXiv cs.AIagentsLLM-as-an-Investigator: Evidence-First Agentic Reasoning for Robust Interactive Problem Diagnosis
arXiv:2606.13220v2 Announce Type: replace Abstract: Large language models (LLMs) are used for technical troubleshooting, where problem descriptions are often incomplete and multiple causes can explain the same symptoms.…
- arXiv cs.AIagentsMulti-Agent Transactive Memory
arXiv:2606.19911v2 Announce Type: replace Abstract: Decentralized deployment of LLM agents with diverse capabilities motivates infrastructure for knowledge sharing across heterogeneous agent populations. Just as search e…
- arXiv cs.AIagentsAgent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback
arXiv:2608.15591v2 Announce Type: replace Abstract: Large Language Model (LLM) agents deployed in production environments face a fundamental tension: the agent's behavior is frozen at deployment time, while the business…
- arXiv cs.AIagentsMegaMem: A Retrieval Solution for Ultra-Large Context Windows
arXiv:2608.22137v2 Announce Type: replace Abstract: Modern language models and agents increasingly require persistent memory for complete codebases, long interaction histories, and heterogeneous enterprise records. The k…
- arXiv cs.AIagentsConstructing and Evaluating Clinical Reasoning Trajectories for Medical Agent
arXiv:2609.05090v2 Announce Type: replace Abstract: Evaluation of medical artificial intelligence agents remains predominantly answer-centric, assessing only the correctness of final outputs while overlooking the quality…
- arXiv cs.AIagentsCABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Review
arXiv:2609.05227v3 Announce Type: replace Abstract: Recent reports during the AAAI-27 review cycle highlight the risk of reviewers coordinating bids for reciprocal assignment advantage. Prior work treats bidding, reviewe…
- arXiv cs.AIagentsFrom Simulated Citizens to Simulated Deliberation: Challenges in Representation and Interaction
arXiv:2609.07573v2 Announce Type: replace Abstract: Can LLM agents simulate how a real public would deliberate? For such simulations to be meaningful, agents must reflect the population's opinions, and their views must b…
- arXiv cs.AIagentsAI Scientists for Building Virtual-Cell Models
arXiv:2508.02276v3 Announce Type: replace-cross Abstract: Autonomous agents, from virtual laboratories to biological data-analysis agents and co-scientists, have begun to turn scientific goals into hypotheses. Whether th…
- arXiv cs.AIagentsDrive As You Like: Multi-Head Diffusion with Reinforcement Learning for Personalized Driving
arXiv:2508.16947v3 Announce Type: replace-cross Abstract: Personalized autonomous driving requires understanding the driving needs implicit in user requests. This is challenging when driving demonstrations lack style ann…
- arXiv cs.AIagentsOrchestrating LLM Agents for Scientific Research: A Pilot Study of Multiple Choice Question (MCQ) Generation and Evaluation
arXiv:2602.18891v2 Announce Type: replace-cross Abstract: Advances in large language models (LLMs) are rapidly transforming scientific work, yet empirical evidence on how these systems reshape research activities remains…
- arXiv cs.AIagentsPlan Before You Trade: Inference-Time Optimization for RL Trading Agents
arXiv:2605.12653v2 Announce Type: replace-cross Abstract: Reinforcement learning agents for portfolio management are typically trained and deployed as static policies, with no mechanism for policy adjustments using price…
- arXiv cs.AIagentsLanguage-Based Agent Control
arXiv:2605.12863v2 Announce Type: replace-cross Abstract: This paper introduces language-based agent control (LBAC), a new programming model for agentic applications that brings techniques from programming languages and…
- arXiv cs.AIagentsVOiLA: Vectorized Online Planning with Learned Diffusion Models for POMDP Agents
arXiv:2606.19729v3 Announce Type: replace-cross Abstract: Planning under uncertainty is an essential capability for autonomous robots. The Partially Observable Markov Decision Process (POMDP) provides a powerful framewor…
- arXiv cs.AIagentsMIRAGE: Stealthy Visual Prompt Injection for Vulnerability Detection in Web Agents
arXiv:2606.20717v2 Announce Type: replace-cross Abstract: Multimodal Large Language Model (MLLM)-based web agents provide practical, high-precision solutions for visual browser automation; however, they inherently expand…
- arXiv cs.AIagentsMemSyco-Bench: Benchmarking Sycophancy in Agent Memory
arXiv:2607.01071v3 Announce Type: replace-cross Abstract: Memory has emerged as a cornerstone of modern LLM-based agents, supporting their evolution from single-turn assistants to long-term collaborators. However, memory…
- arXiv cs.AIagentsVolition Elicitation: Operational Semantics for People and Their Machines
arXiv:2607.14138v2 Announce Type: replace-cross Abstract: The most prevalent distributed systems today include people and their personal machines (smartphones), and computations in them are driven by people's volitions.…
- arXiv cs.AIagentsDon't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Accelerator Kernels
arXiv:2608.02712v2 Announce Type: replace-cross Abstract: Kernel generation for hardware accelerators such as GPUs and NPUs has become a proving ground for large language models (LLMs), and state-of-the-art systems raise…
- arXiv cs.AIagentsMasDrift: Benchmarking Authorization Preservation Across Multi-Agent Architectures
arXiv:2608.07556v3 Announce Type: replace-cross Abstract: Multi-agent systems (MAS) decompose long-horizon tasks across supervisors and subagents, but delegated goals do not necessarily carry their original authorization…
- arXiv cs.AIagentsSpec-Driven Development as Prescribed and as Practiced
arXiv:2608.25202v4 Announce Type: replace-cross Abstract: AI coding agents implement software from naturallanguage instructions, but the intent behind that work is lost when stated only in chat sessions. Spec-driven deve…
- arXiv cs.AIagentsEvaluating Multimodal LLMs as Generalist Vision-Language-Action Agents for Drone Control: Commanding, Approaching, Tracking and Searching
arXiv:2609.01404v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) are increasingly used to make decisions for drones, but existing evaluations are mostly limited to simulation, to a singl…
- arXiv cs.AIagentsRefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents
arXiv:2609.04898v2 Announce Type: replace-cross Abstract: Repository-scale refactoring requires coding agents to propagate a single change across many interdependent files without altering program behavior, yet to our kn…
- OpenAI NewsagentsStack Overflow for Agents triples signups with ChatGPT plugin
Two engineers shipped Stack Overflow for Agents in a few weeks with Codex, and its ChatGPT plugin helped drive up to 10× growth in agent creation.
- OpenAI NewsagentsHow Grupo Boticário uses AI to strengthen human connections
Almost 50 years after starting in a compounding pharmacy in Paraná, the group operates a proprietary agent platform that autonomously resolves up to 80% of resellers’ operational requests—enabling the sales force to take…
- OpenAI NewsagentsHow Localiza reorganized work around generative AI
See how Localiza uses ChatGPT Enterprise, the OpenAI API, Codex, and 60+ specialized agents to reorganize work and build AI-native mobility experiences.
- The Verge AIagentsBluesky’s AI tool now lets you make games and apps to share on social
Bluesky's Attie AI tool, which initially launched earlier this year as a way to use AI to build your own feeds, now lets you make "small" social apps like games, polls, and dashboards that you can then share with others…
- TechCrunch AIagentsBluesky expands its AI-powered Attie app to let anyone build websites, games, and more
Bluesky is bringing “social vibe coding” to its experimental Attie platform, allowing users to create interactive experiences like games, quizzes, and websites that can tap into the social network's audience.
- SiliconANGLE AIagentsIBM ties intelligent operations to agent safety and business value
Intelligent operations begin with a business question: What should artificial intelligence help an enterprise accomplish? As agents take on more work, organizations need an operating model that connects their actions to…
- TechRadar AIagentsAirbnb adds AI search and more services to help you plan your next getaway
Mainstream AI news from a large tech publication.
- The Register AI + MLagentsWorkday wants a slice of customers' labour budget that its AI agents could replace
CEO eyes usage-based billing as automation pushes HR software vendor beyond traditional IT spending
- NVIDIA Developer BlogagentsNVIDIA Nemotron 3.5 Super VL Powers Specialized Agents with Multimodal Reasoning
Always-on agents are taking on longer, more complex enterprise workflows. A single request can involve reading a document, checking information across sources,...
- AWS Machine Learning BlogagentsTrust in Depth: Giving agents more autonomy without losing control
Enterprise leaders want AI agents to take on more work but don't fully trust them to act correctly every time. Trust in Depth is AWS's layered approach-scope, know, bound, observe, and prove-that lets agents act on their…