AI news archive.
4,966 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsConstraint Decay: The Fragility of LLM Agents in Backend Code Generation
arXiv:2605.06445v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, production-grade software requ…
- arXiv cs.AIagentsAgenticRL: Agentic Reinforcement Learning with Self-Refinement for Complex UAV Navigation
arXiv:2606.03963v4 Announce Type: replace-cross Abstract: Deep reinforcement learning enables autonomous robots to learn complex navigation tasks, but still relies heavily on time consuming manual reward design and fine…
- arXiv cs.AIagentsSelf-Reference in Large Language Models: The Introspection Threshold for Recursive Self-Improvement
arXiv:2607.04277v2 Announce Type: replace-cross Abstract: The pursuit of self-evolving AI raises a critical question: when is autonomous self-improvement sustainable rather than degenerative? Drawing an analogy to von Ne…
- arXiv cs.AIagentsGit-Assistant: Planning-Based Support for Updating Git Repositories
arXiv:2607.09224v3 Announce Type: replace-cross Abstract: Version control systems are essential for collaborative software development, yet tools like git remain challenging for many practitioners. Recent advances in Lar…
- arXiv cs.AIagentsStaying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing
arXiv:2609.07344v2 Announce Type: replace-cross Abstract: Large language model (LLM) based agents are increasingly applied to cybersecurity tasks such as vulnerability discovery and automated penetration testing. On long…
- arXiv cs.AIagentsFrom Momentary Emotion Inference to Sustained Emotion Support: Evaluating a Companion Agent in a Longitudinal Study
arXiv:2609.16344v2 Announce Type: replace-cross Abstract: Sustained emotional support is a long-horizon interaction task closely tied to human well-being. Recent research demonstrates generative agents' capacity for mome…
- OpenAI NewsagentsV7 cuts costs 78% while boosting accuracy with GPT-5.6 Luna
Using GPT-5.6, V7 turns scattered company files into context agents can use to complete complex, source-linked work.
- Simon Willison's WeblogagentsMCP was always a bad idea?
My comment on MCP was always a bad idea? — Hacker News. This article entirely misses the value that MCP brings today. Sure, there's almost no reason to use MCPs if you are running a full-blown terminal agent (Claude Code…
- TechRadar AIagentsAn AI agent tried to guess what wine I was drinking based on my description — and the results were mixed to say the least
Mainstream AI news from a large tech publication.
- Engadget AIagentsSpaceXAI's Grok Bot is in early beta - Here's how to try it
SpaceXAI's Grok Bot is a digital 'teammate' that can handle complex and boring tasks that would otherwise clutter your day. Here's how to get up and running.
- SiliconANGLE AIagentsAI governance moves from observability to provable control
As artificial intelligence agents move from experimental tools into production systems, enterprise governance is being forced to answer a harder question. It is no longer enough to know what an agent did. Organizations i…
- The Verge AIagentsMeta’s Muse is creepy, but maybe not for the reasons you think
Meta's Muse is apparently an effective AI assistant, but one that's a little creepy. Part of that is because of its new Mac app, which can access Messages, Calendar, and Notes. But for all its smarts, Muse doesn't actual…
- SiliconANGLE AIagentsAt AGNTCon Europe, ensuring AI agents don’t kill us all
At this past week’s AGNTCon + MCPCon Europe 2026 conference in Amsterdam, the buzz around agentic artificial intelligence was palpable – but nobody was particularly worried that AI was going to kill us all. The frontier…
- SiliconANGLE AIagentsSalesforce after Dreamforce: How the CRM giant can grow beyond its own interface
Salesforce Inc.’s next growth opportunity just may come from customers spending less time in its interface, and having artificial intelligence agents do more of the work. Coming out of the customer relationship managemen…
- The DecoderagentsUnity launches official plugins for Claude Code and OpenAI Codex to stop AI agents from using outdated tutorials
Unity has released official plugins for Claude Code and OpenAI's Codex. The article Unity launches official plugins for Claude Code and OpenAI Codex to stop AI agents from using outdated tutorials appeared first on The D…
- The DecoderagentsGoogle Deepmind's Dream-RSI helps AI agents improve by “dreaming” about past attempts
Google and Deepmind's Dream-RSI lets AI agents "dream" through past search runs to test new strategies without costly recalculations. In tests, it matched or beat existing results, cutting iterations by a factor of up to…
- The Register AI + MLagentsClaude Code revamps projects so you can work and pay in parallel
Running multiple Claude sessions at once means less waiting around to hit your usage limit
- Simon Willison's WeblogagentsQuoting Thariq Shihipar
We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. AGENTS.md support is built off of Claude Code mods, our…
- TechCrunch AIagentsGoogle’s new ‘CC’ is an AI agent that helps families run their households
Google is refocusing its CC AI agent on household coordination, letting families share emails, schedules, and tasks so the AI can manage calendars, fill out forms, make shopping lists, plan meals, and more.
- AWS Machine Learning BlogagentsMigrating multi-model AI agents to Amazon Bedrock AgentCore runtime
Migrate a multi-model healthcare AI agent from self-managed Amazon ECS with AWS Fargate to Amazon Bedrock AgentCore runtime, preserving triple-model orchestration and vector-enhanced knowledge retrieval while reducing in…
- AWS Machine Learning BlogagentsThe new AgentCore runtime: Elastic, optimized, and consistently fast starts
Today we are announcing the new AgentCore runtime, a capability of Amazon Bedrock AgentCore built for the speed, flexibility, and cost efficiency that production agents demand. It reclaims memory as sessions release it a…
- AWS Machine Learning BlogagentsDeploy Hugging Face models on Amazon SageMaker AI with coding agents
Deploy production-ready Hugging Face models on Amazon SageMaker AI using six open-source agent skills. Point a coding agent at a model and get back a real-time endpoint with the right serving container, autoscaling, Amaz…
- TechCrunch AIagentsMeta’s Muse hits Mac, letting the AI take actions on your computer
Muse is now available on the Mac, where it can work with your files and apps to take action on your behalf.
- SiliconANGLE AIagentsFor AI agents, it’s the best of times, it’s the worst of times
And in a desperate attempt to turn a cliche into a sharper analogy to today’s AI era, let’s complete Charles Dickens’ first line in “A Tale of Two Cities,” which honestly does kind of fit: “… it was the age of wisdom, it…
- The Register AI + MLagentsThe ideal database for AI agents doesn't exist yet, says Percona CEO
Iterative workloads caught vendors off guard, but requirements for a clean-slate solution remain unclear
- arXiv cs.AIagentsPosition: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer
arXiv:2609.19203v1 Announce Type: new Abstract: AI applications have shifted from single, monolithic foundation models (FM) to compound agentic systems. Yet today's stacks remain fragmented: even as protocols (e.g., MCP,…
- arXiv cs.AIagentsCharacterizing Web Search by Conversational LLM Agents: From Search Decisions and Strategies to Results and Responses
arXiv:2609.19244v1 Announce Type: new Abstract: Conversational LLM agents increasingly rely on Web search, yet the end-to-end lifecycle of agentic search remains poorly understood. We present the first study of Web searc…
- arXiv cs.AIagentsDo AI Agents Understand Computer Architecture?
arXiv:2609.19387v1 Announce Type: new Abstract: Agents are increasingly asked to design hardware, and increasingly reported to succeed. Such reports establish that a design improved; they cannot establish why. An agent t…
- arXiv cs.AIagentsMAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs
arXiv:2609.19391v1 Announce Type: new Abstract: LLM coding agents now generate complex programs at a scale that makes thorough human review increasingly difficult, raising the risk of safety and security failures. Common…
- arXiv cs.AIagentsClosed-World Resolution Against Tool Hallucination in LLM Agents
arXiv:2609.19425v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents fail in a way no tool-selection or tool-security method addresses: they call tools that do not exist and pass arguments no…
- arXiv cs.AIagentsSafety Beyond the Interface: Detecting Harm via Latent States in Large Language Models
arXiv:2609.19472v1 Announce Type: new Abstract: Autonomous systems increasingly rely on Large Language Models (LLMs) yet the safety infrastructure surrounding these models introduces latency and compute overhead. This li…
- arXiv cs.AIagentsAn Architecture for Long-Horizon Agents: Levels, Ticks and Cascaded Intelligence
arXiv:2609.19519v1 Announce Type: new Abstract: Language-model agents are increasingly asked to carry out work spanning days or weeks, such as an operations remediation or a research programme. Such a task outlives any c…
- arXiv cs.AIagentsEconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data
arXiv:2609.19523v2 Announce Type: replace Abstract: Web agents often revisit the same sites, yet most evaluations discard the procedures learned in earlier successful interactions. We introduce EconSkills, a skill librar…
- arXiv cs.AIagentsA Unified Evaluation Framework for Trustworthy Large Language Models, Agentic AI, and Multimodal Systems
arXiv:2609.19524v2 Announce Type: replace Abstract: Benchmark scores alone provide an incomplete basis for assessing the trustworthiness of modern artificial intelligence systems. Large language models (LLMs), agentic sy…
- arXiv cs.AIagentsSelf Improvement via Fast Tree-search
arXiv:2609.19526v1 Announce Type: new Abstract: Coding agents can recursively modify their own implementations, forming a loop of self-improvement. While prior work shows this can boost performance on coding benchmarks,…
- arXiv cs.AIagentsWhen Hiring Becomes Agent-Mediated: Evaluating Access and Recurrence in Two-Agent R\'esum\'e Screening
arXiv:2609.19530v1 Announce Type: new Abstract: Hiring is bilateral: employers assess fit, while candidates present and defend evidence of their qualifications. Yet r\'esum\'e screening, the first gate, is commonly autom…
- arXiv cs.AIagentsAgentic AI Networking for Heterogeneous Unmanned Aerial Systems in Low-Altitude Wireless Networks
arXiv:2609.19538v1 Announce Type: new Abstract: Low-altitude wireless networks (LAWNs) are emerging as a key infrastructure for heterogeneous unmanned aerial systems that support concurrent services within a shared three…
- arXiv cs.AIagentsSIMLIFE: Pattern Understanding for Long-Horizon Human-Agent Partnership
arXiv:2609.19610v2 Announce Type: replace Abstract: Understanding humans over long horizons requires agents to infer not only what people need in the moment, but also how routines form, why they repeat, and when they cha…
- arXiv cs.AIagentsFrom Intent to Action: Benchmarking LLM Safety in Vehicle Voice Command Authorization
arXiv:2609.19630v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into vehicle voice assistants. But linking natural-language requests to vehicle functions creates a safety-critical…
- arXiv cs.AIagentsReach or Solve? Deep Diving into Agentic RL Gains with Checkpoint Handoffs
arXiv:2609.19636v2 Announce Type: replace Abstract: Reinforcement learning (RL) is widely used to improve language-model agents, and its gains are usually measured by final task success. However, an agent's earlier actio…
- arXiv cs.AIagentsScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI
arXiv:2609.19644v1 Announce Type: new Abstract: Scientific discovery is defined by the ability to identify the boundaries of existing knowledge and venture into unexplored territory. The ultimate vision for AI in science…
- arXiv cs.AIagentsReplan, Repair, or Edit? A Unified Empirical Evaluation of Travel Agents for Itinerary Revision under Resource Disruptions
arXiv:2609.19654v1 Announce Type: new Abstract: Travel-planning agents generate itineraries that may become infeasible after acceptance because of flight cancellations, hotel unavailability, or attraction closures. Revis…
- arXiv cs.AIagentsFINSKILLOPS: A Self-Evolving Multi-Agent System for SEC Filing QA
arXiv:2609.19680v1 Announce Type: new Abstract: Financial QA systems are typically improved before deployment through better retrieval, prompting, or agent coordination, leaving their reliability behavior fixed thereafte…
- arXiv cs.AIagentsLearnActCoder: Role-Aware Error Memory for Adaptive Clinical Coding Agents
arXiv:2609.19721v1 Announce Type: new Abstract: Clinical coding agents repeatedly encounter the same failure modes, including unsupported codes, missed documented conditions, specificity errors, and procedure-coding conv…
- arXiv cs.AIagentsAutoData: Agentic Search for Pre-training Data Selection
arXiv:2609.19754v1 Announce Type: new Abstract: LLM agents have recently shown promise in automating machine learning engineering by editing model and training code under execution feedback. Data, however, remains largel…
- arXiv cs.AIagentsRethinking Multi-Agent Collaboration: When More Is Less
arXiv:2609.19759v2 Announce Type: replace Abstract: The rapid advancement of large language models and single-agent harnesses has reshaped the landscape of autonomous systems, raising a critical question of when multi-ag…
- arXiv cs.AIagentsContagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems
arXiv:2609.19789v1 Announce Type: new Abstract: Multi-agent trading systems built on large language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to adversarial inputs is largely unk…
- arXiv cs.AIagentsDual-Axis Policy Optimization for LLM Agents: Bayesian Feedback Attribution and Trajectory Mass Normalization
arXiv:2609.19830v1 Announce Type: new Abstract: Reinforcement learning for LLM agents involves two distinct optimization di- mensions: how environment feedback is exploited within a trajectory, and how complete trajector…
- arXiv cs.AIagentsA Dual-Process Perspective on Nudge Susceptibility in LLM-Based GUI Agents
arXiv:2609.19843v1 Announce Type: new Abstract: LLM-based GUI agents increasingly act on behalf of users in digital environments that were designed with human users in mind. These graphical user interfaces were designed…
- arXiv cs.AIagentsTRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives
arXiv:2609.19897v1 Announce Type: new Abstract: Historical archives pose a difficult retrieval problem for retrievalaugmented generation systems: documents are OCR-degraded, heterogeneous across genres and sources, and r…