AI news archive.
4,966 articles filed under Agents, newest first, from the outlets listed on the sources page.
- arXiv cs.AIagentsAutoResearch: An Execution-Grounded Multi-Agent Framework for Reliable Research Workflow Automation
arXiv:2607.02520v2 Announce Type: replace-cross Abstract: Automated research agents increasingly generate code, retrieve literature, and draft scientific artifacts, but they often fail to verify whether generated experim…
- arXiv cs.AIagentsTabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Data
arXiv:2607.03926v2 Announce Type: replace-cross Abstract: Synthetic tabular data support use cases like data sharing, model development under access restrictions, and rapid prototyping of analytical workflows. Modern gen…
- arXiv cs.AIagentsHarnessMDP: Learning to Control LLM Agent Harnesses with Offline Reinforcement Learning
arXiv:2607.05458v3 Announce Type: replace-cross Abstract: The execution harness is a critical component of LLM agents, shaping how the agent interacts with its environment and organizes multi-step execution. Prior work h…
- arXiv cs.AIagentsMulti-Agent AI Control: Distributed Attacks Hamper Per-Instance Monitors
arXiv:2607.07368v2 Announce Type: replace-cross Abstract: AI control is a family of techniques to prevent an AI with malicious goals from subverting its operator's intent. AI Control usually studies a single agent in one…
- arXiv cs.AIagentsAn LLM-powered Agentic Recommendation System for Connected TV Content Discovery
arXiv:2607.09988v4 Announce Type: replace-cross Abstract: Recommendation systems, from traditional multi-stage to recent unified generative architectures, face challenges in incorporating diverse contextual signals, such…
- arXiv cs.AIagentsBulkhead: Automated Semantic Detection and Remediation of Container Escape Vulnerabilities
arXiv:2607.12723v2 Announce Type: replace-cross Abstract: Container filesystem isolation depends on safely resolving container-controlled paths during privileged host-container interactions. As third-party plugins and ag…
- arXiv cs.AIagentsChannelGuard: From Borrowed Safety to Application-Controlled Defenses in Multi-Agent LLMs
arXiv:2607.19430v3 Announce Type: replace-cross Abstract: AI assistants increasingly work as teams, where one model makes a plan, others search the web, use tools, or read stored information, and another writes the final…
- arXiv cs.AIagentsREGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning
arXiv:2607.19450v4 Announce Type: replace-cross Abstract: Large-scale online reinforcement learning (RL) is the predominant means of eliciting advanced abilities including long-term reasoning and agentic tool use in larg…
- arXiv cs.AIagentsDBA-Bench: A Production-Fidelity Benchmark for LLM-Based Database Operations Agents
arXiv:2607.22165v2 Announce Type: replace-cross Abstract: LLM-based database agents show promise, but differences in task scope, testbeds, and success criteria hinder direct comparison. A shared benchmark must also prese…
- arXiv cs.AIagentsMission-Level Runtime Assurance for LLM-Assisted ISR Swarms over a Verification-Aware Fabric
arXiv:2607.23532v3 Announce Type: replace-cross Abstract: Swarms of LLM-assisted autonomous robots are increasingly proposed for cooperative intelligence, surveillance, and reconnaissance (ISR) in contested environments.…
- arXiv cs.AIagentsAI Alignment and Fiduciary Obligation
arXiv:2608.02660v3 Announce Type: replace-cross Abstract: Advanced AI assistants engage users in extended interactions across a widening range of roles, including advice, decision support, collaboration, learning, emotio…
- arXiv cs.AIagentsSearch-G1: Co-Evolving Representation-Based Rewards for Selective Grounded Search
arXiv:2608.07531v4 Announce Type: replace-cross Abstract: Search-augmented language agents should retrieve external information only when necessary and ground their answers in retrieved evidence. Yet terminal correctness…
- arXiv cs.AIagentsListen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization
arXiv:2608.16539v2 Announce Type: replace-cross Abstract: Large Audio Language Models (LALMs) have made rapid progress on standardized benchmarks, yet their deployment in practical media workflows, curation, archival ind…
- arXiv cs.AIagentsDisclosure-Gated User Simulation for Companion-Agent Evaluation
arXiv:2609.00982v2 Announce Type: replace-cross Abstract: Playing the user with a large language model is standard in scalable evaluation, and has a repeatedly diagnosed failure: the simulated user is excessively coopera…
- arXiv cs.AIagentsEmbodiedSkills: World Action Model-augmented Cascaded Skills for Vision-Language-Action Agent
arXiv:2609.01281v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) policies generate executable robot actions, but plausible proposals can have different consequences for the task. We present Embodied…
- TechRadar AIagentsThe hidden risks of AI's increasingly helpful agents
Mainstream AI news from a large tech publication.
- OpenAI NewsagentsThe EU’s next chapter in AI is agentic
New analysis shows how agentic AI adoption is growing across EU enterprises and small businesses—and where deeper use could unlock more value.
- NVIDIA Developer BlogagentsHow to Rewrite Apache Spark UDFs for GPU Acceleration with AI Agents
Enterprise applications have become increasingly demanding. Agentic AI has compounded the need for vast amounts of enterprise data with frequent, complex...
- The Register AI + MLagentsOpenAI's dot assistant burned 300K+ tokens in a day without a single prompt
Geordie's tests recorded 155 activity traces and multiple subagents after dot was given read-only permissions
- AWS Machine Learning BlogagentsBuilding agents that transact with Anchor Browser and AgentCore payments
Learn how the AWS Generative AI Innovation Center Partner Agent Factory and Anchor Browser built AI agents that autonomously pay for x402-protected web resources and APIs. Amazon Bedrock AgentCore payments checks budgets…
- The Verge AIagentsShopify opens its catalog up to more AI agents
More AI agents will soon be able to browse and purchase from Shopify listings, marking an expansion of the company's agentic commerce ambitions. Shopify announced Tuesday it will let shoppers configure their AI agents to…
- The Verge AIagentsSquare’s new kiosk lets you talk to AI for help with your order
Square is launching new hardware: a big kiosk for ordering things that has a touchscreen and lets you talk to an AI. It's called the Square Kiosk. Square says the Kiosk, which has a large pill shape, has an "agentic, con…
- SiliconANGLE AIagentsDeliverance AI puts sovereign AI control to the continuity test
Sovereign AI control is becoming a business continuity issue as autonomous agents take on essential enterprise workflows. Keeping data within national boundaries addresses part of the challenge, but organizations also ne…
- Hugging Face BlogagentsRun fast, private agents on-device with LFM2.5-24B-A2B
Open-source model releases, tooling, and community updates.
- Ars Technica AIagentsGoogle wants to host your personal vibe-coded apps in the Play Store
Google plans to help turn those personal AI-generated apps into wide releases.
- TechCrunch AIagentsGoogle Play now lets anyone build private, vibe-coded apps that run on Android
Google is making it easier to build and use personal Android apps created with AI, without having to make them available to everyone on the Play Store.
- The Verge AIagentsGoogle makes it easier to launch your vibe-coded apps
The next time you vibe-code a custom app with Google's AI Studio, you won't have to connect your phone to a computer to install it. On Tuesday, Google announced a new feature in the US that will allow you to launch perso…
- AWS Machine Learning BlogagentsNatural language security queries at Orca Security using Amazon Bedrock
Orca Security built Discovery AI, a natural language query agent on Amazon Bedrock that converts plain-English questions into Sonar queries. The post shares the multi-stage architecture and the results: 90% lower query c…
- AWS Machine Learning BlogagentsHow ShipStation Global built an AI IT help desk on Amazon Bedrock AgentCore
ShipStation Global's engineering team built Deckhand, an AI IT help desk agent for Slack on Amazon Bedrock AgentCore. It answers routine IT questions from a curated knowledge base, reads error-message screenshots, and fi…
- AWS Machine Learning BlogagentsBuild long-horizon agents with Grok 4.7 on Amazon Bedrock
Grok 4.7 is now available on Amazon Bedrock. In this post, we build a tool-calling agent on Grok 4.7 and evaluate it on three reasoning tasks at four reasoning effort levels, measuring correctness and token cost per comp…
- Simon Willison's WeblogagentsQuoting Geoffrey Huntley
If the agent isn't using my diagnostics library, I could introspect and update AGENTS.md, but there's still a delta, and it'll drift. Instead, I write a pre-commit hook that checks the git diff for direct calls to observ…
- TechCrunch AIagentsAmex introduces a framework to prevent AI agents from making unauthorized purchases
American Express is introducing a new framework designed to ensure AI agents only make purchases their users have authorized, potentially preventing costly mistakes and disputes as AI-powered shopping grows.
- AI BusinessagentsMeta joins enterprise agent race with Muse Wonder, facing a trust gap
The company’s new releases point to an AI market becoming more personal, with agents and models completing tasks, but enterprises still aren’t ready for this new phase of AI.
- Engadget AIagentsGoogle will let you distribute vibe-coded Android apps with just a Google account
The company is revamping the Play Store for the AI era with changes to publishing, recommendations and more.
- Engadget AIagentsHow to use a ChatGPT Dot when it rolls out to you
OpenAI is hoping that Dots will make automating online tasks a lot easier. Here's what you'll need to use them, how to set them up and what they're capable of.
- SiliconANGLE AIagentsMeta releases Muse Wonder AI models built to run personal and professional agents
Meta Platforms Inc. today released Muse Wonder and Muse Wonder Full, two artificial intelligence models it says are its most capable yet at running agents that handle personal and professional tasks. Meta aimed the relea…
- SiliconANGLE AIagentsAI governance shifts to runtime as always-on agents spread
As enterprises move from debating artificial intelligence adoption to deploying it, AI governance has become the harder question. Autonomous agents now run around the clock across a sprawl of platforms, and controls buil…
- Latent SpaceagentsHow Anthropic’s Dynamic Workflows Coordinate Claude Agents (Updated with video!)
At AI Engineer New York, Anthropic drew on lessons from Unix and Linux to explain how agents can tackle bigger projects without overwhelming developers.
- Latent SpaceagentsHow Anthropic’s Dynamic Workflows Coordinate Claude Agents (Updated with video!)
At AI Engineer New York, Anthropic drew on lessons from Unix and Linux to explain how agents can tackle bigger projects without overwhelming developers.
- IEEE Spectrum AIagentsMeet the Anthropic Engineer Keeping Its AI Agent Trustworthy
If you’ve ever wondered how Claude and similar AI agents can answer complex questions in seconds and where they get the information, you’re not alone. Gurmeet Saran works to find that answer every day as an engineer at A…
- SiliconANGLE AIagentsPhasis develops platform for agentic orientation using World APIs and reality layers
When the founders at Phasis Inc. sought to develop a platform for orienting AI agents, they turned to graphs as a way to obtain a measurement of culture. The company wanted to better understand relations not just between…
- AI BusinessagentsPrompt: AI agents are running into the limits of access
As agents take on more work for users, companies are deciding whether to let outside AI systems act on their platforms.
- Engadget AIagentsHow to use Google Gemini to automate tasks
Spark is Google's AI tool that can perform tasks on your behalf.
- TechRadar AIagentsThe more autonomous AI becomes, the more human strategy matters
Mainstream AI news from a large tech publication.
- arXiv cs.AIagentsEqual-Budget Monte Carlo Tree Search versus Randomized-Restart List Scheduling for DAG Workflows: A Controlled Equal-Budget Computational Study
arXiv:2610.12542v1 Announce Type: new Abstract: Monte Carlo Tree Search (MCTS) is often proposed for scheduling directed-acyclic-graph (DAG) workflows, yet most studies never run the comparison that could refute it - giv…
- arXiv cs.AIagentsKnow What You Don't Know: Agentic Data Synthesis by Evolving Generation Space for Closed-Loop Learning
arXiv:2610.12593v1 Announce Type: new Abstract: The continued improvement of large language models increasingly depends on synthetic experience, yet effective data synthesis for interactive agents requires not only execu…
- arXiv cs.AIagentsSpireBench: Evaluating Long-Horizon Strategic Play of Agentic Models with Slay the Spire
arXiv:2610.12596v1 Announce Type: new Abstract: Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short and episodic, and per…
- arXiv cs.AIagentsBeyond Binary Verifiable Rewards: Behavioral Self-Rewarding for SWE Agents
arXiv:2610.12598v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) provides reliable supervision for software engineering agents through executable tests, but binary rewards fail to dis…
- arXiv cs.AIagentsCLEAT: Learning Value-Guided Clarification for Interactive Agents
arXiv:2610.12655v1 Announce Type: new Abstract: LLM agents can execute increasingly complex tasks, but effective assistance also requires aligning their actions with goals and constraints that users may leave unstated. W…
- arXiv cs.AIagentsEvoBelief: Falsifiable World Models for Self-Improving LLM Agents
arXiv:2610.12789v1 Announce Type: new Abstract: Self-evolving LLM agents typically improve how they act through accumulated experience, reflection, or skills. Yet even procedurally capable agents can fail when their beli…