AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- The Register AI + MLagentsDocker's new sandboxes aim to contain AI agents for real
With Cloud Sandboxes, devs can keep agents at arm's length
- SiliconANGLE AIagentsNeo4j makes the case for knowledge graphs as shared context for AI agents
Knowledge graphs can give enterprise agents a shared understanding of how data, business rules and processes fit together. However, that context becomes harder to maintain when each new agent carries its own version of w…
- WIRED AIagentsI Think I Found an AI Agent Worth the Risk
Instinct saved me $550, booked my restaurant reservations, and warned me about a phishing scam. It also wasted $64 and might be a security nightmare.
- The Verge AIagentsMeta is going to let you build games with AI right on your phone
Meta has a new plan to get people to make games for its Horizon social platform. The company today announced two new development tools that will let you create games with AI prompts: Horizon Create, a mobile app, and Hor…
- The Verge AIagentsMuse sure looks a lot like OpenClaw
We seem to be entering into an AI agent renaissance. Meta's new consumer-facing AI agent, Muse, topped the App Store charts soon after its release and has 600,000 daily active users in the US, by an Apptopia estimate. An…
- TechRadar AIagentsCloud and AI bills looking a bit high? Your AI agents may have been let loose and run up huge spending costs
Mainstream AI news from a large tech publication.
- The Verge AIagentsGemini can now call businesses for you so you don’t have to wait on hold
Google's launching an "early experiment" feature on Pixel 11 that lets users delegate local business calls to Gemini, like making a reservation, checking if a product is in stock, or rescheduling an appointment. Accordin…
- AWS Machine Learning BlogagentsBuild a multi-account AI agent with AgentCore Gateway and MCP
Build a multi-account architecture that keeps each team's data in its own AWS account while giving AI agents a unified way to query across them. A central platform account runs the agent using Amazon Bedrock AgentCore Ga…
- AWS Machine Learning BlogagentsAderant builds intelligent ticket triage with Amazon Nova
Learn how Aderant built an intelligent ticket triage system on Amazon Nova Lite through Amazon Bedrock, automating context gathering, classification, routing, and knowledge enrichment for its cloud operations team.
- TechCrunch AIagentsGoogle tests letting Gemini call businesses for you
Google says the AI-calling feature will first be available to Pixel 11 owners in the U.S. who pay for a Gemini subscription.
- WIRED AIagentsGoogle’s Gemini Can Now Make Calls for You on Pixel Phones
Call for Me—a feature that’s exclusive to the Pixel 11 series—gives robocalls a new meaning.
- TechCrunch AIagentsAndo wants to take on Slack with a team messaging app that lets humans and agents work together
The app gives agents their own identities and inboxes and lets them partake in conversations as naturally as people can.
- The Verge AIagentsI have some questions for Mark Zuckerberg
It’s a big week for Meta. The company just kicked off its big Connect conference on Wednesday, and the new Muse AI agent appears to be an early hit. I’ve been using it — it is surprisingly good. CEO Mark Zuckerberg has o…
- The DecoderagentsMeta gives its Muse AI agent video avatars, email addresses, and Mac control
At Meta Connect 2026, Meta expanded its AI agent, Muse, and unveiled several new devices. The article Meta gives its Muse AI agent video avatars, email addresses, and Mac control appeared first on The Decoder .
- SiliconANGLE AIagentsDataiku debuts cross-platform Agent Management, expands Cobuild building agent
Enterprise artificial intelligence platform company Dataiku Inc. today launched Agent Management, a standalone product that finds and tracks every AI agent a business runs, including those built on other vendors’ platfor…
- Engadget AIagentsPixel 11's Call For Me feature begins preliminary rollout
Select Gemini subscribers with a Pixel 11 can soon try out phone calls via AI chatbot.
- arXiv cs.AIagentsSilent Failures in Agent-Tool Interaction: An Audit of ToolUniverse
arXiv:2609.26836v2 Announce Type: replace Abstract: Agentic AI systems are increasingly adopting automated pipelines that integrate multiple tools. While prior research have studied task success and task completion of su…
- arXiv cs.AIagentsHarness as a Language: A Minimalist Agent Framework With Maximal Expressivity
arXiv:2609.26891v2 Announce Type: replace Abstract: Modern language-model agents are built around the agent loop: the LLM is placed in an environment exposing a set of tools, and the LLM has full control over the workflo…
- arXiv cs.AIagentsTwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents
arXiv:2609.26911v2 Announce Type: replace Abstract: A single locally plausible tool call can derail an otherwise successful agent trajectory. Suspicion alone does not justify intervention, because the replacement itself…
- arXiv cs.AIagentsBuilding Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations
arXiv:2609.26927v2 Announce Type: replace Abstract: The objective of this article is to provide design principles and a software architecture for enabling interaction between humans and multiple agents in simulated dynam…
- arXiv cs.AIagentsReinforcement Learning with Decomposed Subtasks
arXiv:2609.27035v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO) and related policy-gradient methods for training language model agents collapse an entire multi-turn rollout into a single sca…
- arXiv cs.AIagentsTraining Intelligent Voice Assistant Wakeup with Controllable Synthetic Conversations
arXiv:2609.27037v1 Announce Type: new Abstract: Wake word detection is a critical component of virtual assistants, serving as the gateway to seamless user interactions. This paper introduces a novel wake-up system that e…
- arXiv cs.AIagentsPropose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors
arXiv:2609.27051v1 Announce Type: new Abstract: Language-model agents now run the whole of quantitative factor research: they propose investment factors, backtest them, select the survivors and retire them. We ask which…
- arXiv cs.AIagentsDo We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate
arXiv:2609.27150v1 Announce Type: new Abstract: Multi-agent debate (MAD) has emerged as a promising paradigm for improving the reasoning accuracy of large language models (LLMs) through iterative peer interaction. Commun…
- arXiv cs.AIagentsCAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments
arXiv:2609.27273v2 Announce Type: replace Abstract: Computer-use agents (CUAs) increasingly act on behalf of users online. What happens when the environments they operate in have incentives of their own? Online marketpla…
- arXiv cs.AIagentsDRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents
arXiv:2609.27276v1 Announce Type: new Abstract: Long-horizon language-model agents accumulate reasoning traces, tool exchanges, and observations whose relevance changes with the current decision. Existing compression str…
- arXiv cs.AIagentsTimeEvo: Failure-Driven Self-Evolution of a Time Series Agent
arXiv:2609.27277v1 Announce Type: new Abstract: Time series agents answer analytical questions by calling external tools, and which tools they carry is decided by people before the agent runs. However, we identify two fa…
- arXiv cs.AIagentsEnSIMem: Entity-Structured Indexing for Long-Term Agent Memory
arXiv:2609.27279v2 Announce Type: replace Abstract: An agent that interacts with users over long periods must recall facts, preferences, events, and changes from a continuously growing interaction history. Existing memor…
- arXiv cs.AIagentsMemory Control Signals Emerge Before Action in Long Horizon Agents
arXiv:2609.27286v1 Announce Type: new Abstract: Long horizon language model agents continuously accumulate interaction history, increasing computational cost while making relevant information harder to preserve and reuse…
- arXiv cs.AIagentsLarge Knowledge Model: A Knowledge Foundation for Agentic Science at Scale
arXiv:2609.27297v2 Announce Type: replace Abstract: Agentic science envisions many autonomous agents investigating concurrently while building on a shared, evolving body of scientific knowledge. This requires a knowledge…
- arXiv cs.AIagentsStateComp: Learning When to Compress History in Long Horizon Agents
arXiv:2609.27298v1 Announce Type: new Abstract: Long-horizon agents continuously accumulate interaction history during task execution, yet the importance of past interactions changes as the agent state evolves. Existing…
- arXiv cs.AIagentsLearn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents
arXiv:2609.27307v1 Announce Type: new Abstract: Graphical User Interface (GUI) agents enable the fulfillment of complex user instructions through multi-turn interactions with software environments, requiring step-wise re…
- arXiv cs.AIagentsVerifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
arXiv:2609.27321v1 Announce Type: new Abstract: Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed outcomes. Scaling their training requires diverse agen…
- arXiv cs.AIagentsStable Geometry with Divergent Task Evidence for Efficient Long-Horizon Agent Compression
arXiv:2609.27332v1 Announce Type: new Abstract: Long horizon agents accumulate growing interaction histories that increase context and inference costs. We find that geometric redundancy alone is an insufficient criterion…
- arXiv cs.AIagentsJust-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents
arXiv:2609.27334v1 Announce Type: new Abstract: Agentic memory systems reuse past experience to improve future performance, yet most existing designs curate memory at write time: once a task is completed, its trajectory…
- arXiv cs.AIagentsMolDesignBench: Evaluating LLM-based Agent for Scenario-grounded Molecular Design
arXiv:2609.27349v1 Announce Type: new Abstract: Real-world molecular design remains challenging for large language model (LLM)-based agents. It requires them to interpret design contexts, satisfy multiple constraints, id…
- arXiv cs.AIagentsEmergi-PersonaOS: A Persona Agent Operating System for Situational Adaptation and Controllable Evolution
arXiv:2609.27417v2 Announce Type: replace Abstract: Symbiosis between humans and digital beings offers a vision for the future of human--machine interaction. In enduring human--machine relationships, personality provides…
- arXiv cs.AIagentsWhatWorkedBench: Benchmarking Experimental Understanding in AI Agents
arXiv:2609.27490v2 Announce Type: replace Abstract: AI research agents must predict the effects of computational changes after budgeted experiments. WhatWorkedBench evaluates this experimental understanding through a del…
- arXiv cs.AIagentsState-Grounded Conditioning: Wrapping User-Facing LLM Agents Where Direction Depends on Live State
arXiv:2609.27606v1 Announce Type: new Abstract: We introduce State-Grounded Conditioning (SGC), a design principle for user-facing LLM agents that must condition on live user state (game state, session history, live inve…
- arXiv cs.AIagentsEvolutionary Stability Does Not Guarantee Learning Accessibility: A Multi-Agent Reinforcement Learning Perspective on Cooperation Emergence
arXiv:2609.27664v1 Announce Type: new Abstract: Cooperation emergence is a central problem in multi-agent systems because decentralized agents must coordinate while adapting to the changing behavior of others. Evolutiona…
- arXiv cs.AIagentsAgentic Governance and Adversarial Verification for Policy-Constrained LLM Healthcare Appeal Generation
arXiv:2609.27844v1 Announce Type: new Abstract: Claim denial management costs U.S. healthcare approximately $260 billion annually in administrative overhead. Large Language Models (LLMs) and Retrieval-Augmented Generatio…
- arXiv cs.AIagentsLearning What to Activate: Combinatorial Capability Allocation for Long-Horizon Multimodal Agents
arXiv:2609.27869v1 Announce Type: new Abstract: Long-horizon multimodal agents rely on specialized capabilities for perception, retrieval, reasoning, verification, and execution. Existing designs typically activate a fix…
- arXiv cs.AIagentsFinite-Sample Probabilistic Safety Certification for AI-Based Grid-Edge Coordination
arXiv:2609.28182v1 Announce Type: new Abstract: Coordinating large population of flexible grid-edge devices can alleviate the need for time-consuming and capital-intensive network upgrades, and AI-based control methods s…
- arXiv cs.AIagentsPASTABench: Proactive Assessment of Sequential Trajectories for Agent Safety
arXiv:2609.28197v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents that alter real-world states, ensuring operational safety across multi-step workflows has become a critical ch…
- arXiv cs.AIagentsShutdown Sabotage Propensities in Multi-Agent Systems
arXiv:2609.28274v1 Announce Type: new Abstract: The final safeguard against rogue AI behavior is the human ability to shut systems down. It has been theorized that when an AI is instructed to perform a task, self-preserv…
- arXiv cs.AIagentsWhat Makes a Terminal-Bench Task Hard? Separating Genuine Hardness from Fake-Hardness on an Adjudicated Agentic Corpus
arXiv:2609.26826v1 Announce Type: cross Abstract: Frontier benchmarks need tasks that current models cannot solve. But a task that no model solves is not automatically a hard task. The same zero pass rate can come from a…
- arXiv cs.AIagentsSpec2COBOLRot: An Agentic-AI Degradation Loop for Realistic COBOL Corpus Generation
arXiv:2609.26835v1 Announce Type: cross Abstract: COBOL remains widely deployed, yet representative corpora reflecting real production code are rarely available, limiting rigorous benchmarking of modernization approaches…
- arXiv cs.AIagentsAjar: Measuring Open Privilege in Agent Defenses
arXiv:2609.26900v1 Announce Type: cross Abstract: A language model agent acts through the tools it is given. The data it reads while working on a task can redirect what it does with those tools. A growing set of techniqu…
- arXiv cs.AIagentsOn Preference Coverage Collapse from Hindsight Relabeling in Multi-Objective Reinforcement Learning
arXiv:2609.26918v1 Announce Type: cross Abstract: Hindsight relabeling which retroactively replacing a transition's goal with the outcome the agent actually achieved is an effective tool for improving sample-efficiency i…
- arXiv cs.AIagentsCrossflow: Prefill-Decode Elasticity for Agentic LLM Serving
arXiv:2609.27085v1 Announce Type: cross Abstract: As serving capacity demand surpasses that of training, serving efficiency becomes increasingly important. Prefill-decode (P/D) disaggregation improves serving efficiency…