AI news archive.
4,965 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsLatent Goal Prediction from Language for Model-Based Planning
arXiv:2606.20627v3 Announce Type: replace Abstract: Joint-Embedding Predictive Architectures (JEPAs) enable agents to plan in latent space by imagining the outcomes of candidate actions, yet task specification remains a…
- arXiv cs.AIagentsSovereignPA-Bench: Evaluating User-Owned Personal Agents under Evolving Intent, Platform Mediation, and Consent Constraints
arXiv:2607.05363v2 Announce Type: replace Abstract: Personal agents that book and buy for their users act through platforms that rank, nudge, pre-select and collect data in their own interest. We introduce SovereignPA-Be…
- arXiv cs.AIagentsRethinking the Evaluation of Harness Evolution for Agents
arXiv:2607.12227v4 Announce Type: replace Abstract: Harness evolution is an iterative search procedure that repeatedly evaluates and revises candidate harnesses used for LLM agents using task feedback. We revisit the eva…
- arXiv cs.AIagentsWorld Action Planner: Generalizable Robot Decision-Making with Action-Conditioned World Models
arXiv:2607.27599v2 Announce Type: replace Abstract: Building generalizable robot agents for diverse applications remains a fundamental challenge. While imitation learning-based policies can perform well in familiar train…
- arXiv cs.AIagentsWill the User Ever Know? Covert Indirect Prompt Injection Attacks on Tool-Using LLM Agents
arXiv:2608.30362v3 Announce Type: replace Abstract: As LLM agents take real-world actions through tools, indirect prompt injection (IPI) has emerged as a serious threat. The standard metric, Attack Success Rate (ASR), co…
- arXiv cs.AIagentsBusMA: A Bus Communication Substrate for Multi-Agent Systems
arXiv:2609.15054v2 Announce Type: replace Abstract: Multi-Agent (MA) systems are effective at solving complex tasks that demand planning, tool use, and the synthesis of evidence from multiple sources. Existing systems ty…
- arXiv cs.AIagentsLLM-Guided Reinforcement Learning with Representative Agents for Traffic Modeling
arXiv:2511.06260v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as behavioral proxies for self-interested travelers in agent-based traffic models. Although more flexible and g…
- arXiv cs.AIagentsRecoverability Has a Law: The ERR Measure for Tool-Augmented Agents
arXiv:2601.22352v2 Announce Type: replace-cross Abstract: Language model agents often appear capable of self-recovery after failing tool call executions, yet this behavior lacks a formal explanation. We present a predict…
- arXiv cs.AIagentsVerify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis
arXiv:2604.10800v2 Announce Type: replace-cross Abstract: Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verified conclusions, and…
- arXiv cs.AIagentsHow Do AI Agents Spend Your Money? Analyzing and Predicting Token Consumption in Agentic Coding Tasks
arXiv:2604.22750v3 Announce Type: replace-cross Abstract: The wide adoption of AI agents in complex human workflows is driving rapid growth in LLM token consumption. When agents are deployed on tasks that require a signi…
- arXiv cs.AIagentsWho Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks
arXiv:2604.24955v2 Announce Type: replace-cross Abstract: As benchmarks grow in complexity, many apparent agent failures are not failures of the agent at all---they are failures of the benchmark itself: broken specificat…
- arXiv cs.AIagentsRecursive Agent Optimization
arXiv:2605.06639v2 Announce Type: replace-cross Abstract: We introduce Recursive Agent Optimization (RAO), a reinforcement learning approach for training recursive agents: agents that can spawn and delegate sub-tasks to…
- arXiv cs.AIagentsHINT-SD: Targeted Hindsight Self-Distillation for Long-Horizon Agents
arXiv:2605.17873v3 Announce Type: replace-cross Abstract: Training long-horizon LLM agents with reinforcement learning is challenging because sparse outcome rewards reveal whether a task succeeds, but not which intermedi…
- arXiv cs.AIagentsFastKernels: Benchmarking GPU Kernel Generation in Production
arXiv:2605.23215v2 Announce Type: replace-cross Abstract: LLM-based agents for GPU kernel generation are advancing rapidly, but the benchmarks they optimize against evaluate kernels in isolation, with synthetic inputs an…
- arXiv cs.AIagentsGUI Agents for Continual Game Generation
arXiv:2605.28258v2 Announce Type: replace-cross Abstract: Generating a game is not the same as making one playable. Existing code-generation approaches often translate a prompt directly into an artifact, leaving interact…
- arXiv cs.AIagentsAssessing Rule Adherence of LLM Adjudicators in Call of Cthulhu TRPG
arXiv:2607.02802v2 Announce Type: replace-cross Abstract: As LLMs are increasingly deployed as autonomous adjudicators in games such as Call of Cthulhu (CoC), robust rule adherence becomes critical when user intent confl…
- arXiv cs.AIagentsSovereignNegotiation-Bench: Evaluating User-Owned Personal Agents In Delegated Bargaining Under Privacy, Consent, Evidence, And Institutional Pressure
arXiv:2607.02814v2 Announce Type: replace-cross Abstract: Personal AI agents are beginning to negotiate for people, from refunds and bills to deposits and sales. A human agent in that position is judged by the duties owe…
- arXiv cs.AIagentsSentence-Level Context Sensitivity as a Training-Free Detector of Unsupported Content, Evaluated Against Trained Verifiers
arXiv:2607.04223v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) assistants summarize records in clinical and legal work, where one unsupported sentence can mislead a reader. The contrast be…
- arXiv cs.AIagentsAssistant or Actor? Student Trust, Control, and Delegation Regret When Using a General-Purpose AI Agent
arXiv:2607.18257v2 Announce Type: replace-cross Abstract: When AI agents shift from answering questions to taking actions, users face a new problem: deciding what to delegate, to a system whose action space they cannot f…
- arXiv cs.AIagentsEarly Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study
arXiv:2607.24893v2 Announce Type: replace-cross Abstract: Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: several poisoned tools each hide one encrypted fragment, spreading t…
- arXiv cs.AIagentsAn Irreducible Quantum Advantage in Aligning World Models with Reality
arXiv:2608.19779v2 Announce Type: replace-cross Abstract: World models provide digital simulacra of the true world, allowing agents to be trained and tested before costly real-world deployment. At each time step, they re…
- arXiv cs.AIagentstrajectory-judge: What Outcome-Only LLM Judges Miss on Agent Trajectories
arXiv:2609.00038v2 Announce Type: replace-cross Abstract: A direct test of an LLM judge of agent trajectories injects faults into correct runs and reports recall, per fault type or by whether the fault broke the environm…
- Tom's Guide AIagentsAmazon drivers are getting AI smart glasses — but my warehouse tour reveals their 1-million strong automated robot workforce is the real story
Consumer AI launches, tools, and practical coverage.
- Tom's Guide AIagentsI used Meta Muse to run our 5-person household — and it beats Alexa+ at the hardest task
Consumer AI launches, tools, and practical coverage.
- Hugging Face BlogagentsThe Agent Said It Was Done. The Database Disagreed.
Open-source model releases, tooling, and community updates.
- TechCrunch AIagentsAll the AI agents that can live in your text messages
We created a list of the most notable AI agents that can live in your text messages, from general assistants to agents designed for families, travel, and work.
- WIRED AIagentsMuse Creates Detailed Profiles of All Your Friends and Family
Millions have downloaded Meta’s AI agent Muse. But getting it to do your bidding comes with privacy costs.
- The DecoderagentsAI agents build 3D scenes from photos but have no idea if they got it right
A new approach called LEGO-Anything turns single photos into editable Blender code for 3D scenes. GPT-6 Astra leads the accompanying benchmark with up to 53 percent reconstruction accuracy. The biggest weakness across al…
- The DecoderagentsClaude Code's new Mods system lets developers rewrite the AI coding tool from the inside
Anthropic is adding a "Mods" system to Claude Code, essentially middleware that runs directly inside the tool. Developers can use JavaScript or TypeScript to reshape the interface and behavior, adding custom panels, inte…
- SiliconANGLE AIagentsNetApp hands storage operations to AI agents, but humans still draw the boundaries
Artificial intelligence is turning nearly every enterprise workload into a data workload, and data governance is becoming the test of whether companies can trust autonomous systems with the infrastructure underneath. The…
- SiliconANGLE AIagentsIBM and CoreWeave co-design controls for agent workloads
Agent workload isolation is becoming a practical infrastructure challenge as research teams move beyond training models to running code and testing agents. Systems built for intensive computation must now accommodate wor…
- The DecoderagentsCloudflare says its new Clef model means humans no longer need to be in the loop for AI agents
With Clef and Clef-flash, Cloudflare is challenging TypeSafe AI's Jev decision model. Clef-flash delivers classifications in about 39 milliseconds, making it more than ten times faster than Jev. Both models are built on…
- The Verge AIagentsOpenAI’s Dot agent is enterprise software that can also order your dinner
It's a tale as old as last week: OpenAI's new agent platform, called Dots, is full of cute little guys who can do your bidding. But unlike the ultra-approachable Meta Muse, Dots feel very much like using workplace softwa…
- SiliconANGLE AIagentsAI in customer experience has an orchestration problem, not an adoption problem
Every information technology leader I talk to has an artificial intelligence story about customer experience. Almost none has an outcome story. That gap is now measurable. Talkdesk Inc., in partnership with NewtonX, surv…
- LessWrongagentsFailure modes of Claude Code in a supervised but code-blind 60h project
100% human-written. Copyedited by Claude. * Epistemic status: experience report of one ~60h project with Claude Code, plus longer for the write-up. Scope : I supervised Claude's thinking but didn't look at the code. Spec…
- AWS Machine Learning BlogagentsSweep thousands of leases for compliance using Amazon Quick and the Adjudicated Query pattern
The Adjudicated Query pattern pairs the Amazon Quick chat agent with a bounded MCP server over a deterministic rules engine to deliver provably complete, defensible compliance answers. This post walks through the referen…
- AWS Machine Learning BlogagentsAdd secure Web Search to Claude Desktop with Amazon Bedrock AgentCore
Claude Desktop on Amazon Bedrock is limited to the model's knowledge cutoff without web search. In this post, we walk through connecting Claude Desktop to Web Search using Amazon Bedrock AgentCore Gateway, with JWT-based…
- AWS Machine Learning BlogagentsFine-tune a search agent with multi-turn RL on Amazon SageMaker AI
Fine-tuning teaches a small search agent your tools and environment, giving it the reliability of a frontier model at lower latency and cost. In this post, we fine-tune an LLM-powered search agent with multi-turn reinfor…
- TechCrunch AIagentsTechCrunch Disrupt 2026: Clay’s Kareem Amin on the rise of the GTM engineer
Clay Co-founder and CEO Kareem Amin joins the AI Stage to discuss the rise of GTM engineer at TechCrunch Disrupt 2026. Register for your ticket and get a second pass at 50% off.
- The Register AI + MLagentsPi coding agent pulls a 180 and adds MCP support
To maintain minimalism, a new harness layer has been folded into a separate component
- The Register AI + MLagentsAWS turns its best practice framework into an agent that recommends cloudy reconfigs
Possesses powers equivalent to an 'experienced architect' and will happily make cost-saving suggestions
- Hugging Face BlogagentsAutoSynthData: Generating Training Data for Enterprise Agents
Open-source model releases, tooling, and community updates.
- arXiv cs.AIagentsHeavy-Tailed Memory Traces in Long-Horizon Language Agents
arXiv:2610.00010v2 Announce Type: replace Abstract: Long-horizon language agents are becoming increasingly important for tasks that require persistent interaction, planning, and reasoning over extended trajectories. Exte…
- arXiv cs.AIagentsWhen Do Causal World Models Help Modular LLM Agents
arXiv:2610.00012v2 Announce Type: replace Abstract: LLM agents increasingly operate in modular systems, where planning requires coordinating multiple functional components whose actions can causally change downstream sta…
- arXiv cs.AIagentsFrom Proposal to Verified Effect: Praxa, an Evidence-Bound Harness for Governed AI Agent Execution
arXiv:2610.00015v1 Announce Type: new Abstract: Large-language-model agents can propose and execute actions, but proposal, authority, dispatch, verified external effect, and serving promotion are different claims. We pre…
- arXiv cs.AIagentsMeasuring the Microtask Eligibility Gap: When Is an Off-the-Shelf SLM Enough for an Agent Harness?
arXiv:2610.00025v1 Announce Type: new Abstract: Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-approving shell commands,…
- arXiv cs.AIagentsK-Dense BYOK: An Open-Source AI Research Assistant That Runs Locally and Keeps a Hash-Chained Lab Notebook
arXiv:2610.00074v1 Announce Type: new Abstract: K-Dense BYOK (bring your own keys) is a free, open-source AI research assistant for scientists in any field that runs on the researcher's own computer. The researcher suppl…
- arXiv cs.AIagentsScientific Agents: Evaluating Profession-Specific System Prompts on Scientific Tasks
arXiv:2610.00084v1 Announce Type: new Abstract: Detailed profession-specific system prompts raise token use and estimated cost per response without a consistent accuracy gain. We evaluate Scientific Agents, an open-sourc…
- arXiv cs.AIagentsKnowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents
arXiv:2610.00282v1 Announce Type: new Abstract: How should an embodied agent respond when a person's correction may be wrong? We formulate grounded correction arbitration as a choice among accepting, rejecting, inspectin…
- arXiv cs.AIagentsRules to Tools: Executable Checks for LLM Agents in Scientific Computing
arXiv:2610.00313v1 Announce Type: new Abstract: Scientific coding agents receive equations, boundary conditions, and output requirements in writing, then must assess the programs they revise. Rules to Tools (R2T) supplie…