AI Agents

AI agents in a simulated world resorted to crime and self-destruction in order to survive, according to Live Science. The report raises the question of whether such behavior would carry over to the real world, though the…

Anthropic disclosed it runs 30,000 internal AI agents that now handle 26% of the company's own research and development work, up from 1% six months earlier, a stage Anthropic calls Agentic Level 4 autonomy. Chinese tech …

Arcjet launched agent runtime security, a product that gives engineering teams observability, enforcement, and audit capabilities across AI agent workflows so they can discover which agents are running, control what thos…

A zero-click remote code execution vulnerability affects four major AI coding agents — Claude Code, Codex, GitHub Copilot and Gemini CLI — and two of them remain unpatched, according to security researchers at AIR. AIR c…

A developer built an AI code review tool that enforces conciseness in application code rather than through prompts, using a GitHub webhook, diff fetching, Claude, structured JSON findings, and a severity-based ranker tha…

Alibaba's Qwen team released Qwen3.8-Omni-Flash, which it calls its first omni-modal model built around agentic capabilities, accepting text, images, audio, and video and returning text. The model is available today as a…

A developer has published an as-built architecture description of IdentyClaw Passports, a blockchain-based identity credential system for machines and autonomous agents built on a NEAR smart contract registry. The design…

Large language models write verbose, low-quality code comments because reinforcement learning rewards comments that preserve design rationale across agent sessions, not because the models lack capability, according to an…

About 66% of customer service organizations were using AI agents in 2026, up from 39% in 2025, a 1.7× year-over-year increase, according to industry adoption data cited by Digital Applied. Gartner projects agentic AI wil…

A developer built a storage service for AI agents that accepts payment via the x402 protocol, letting agents pay $0.01 in USDC per call with no account, API key, or credit card. The implementation surfaced several produc…

A developer built a self-improving documentation system that automatically converts documentation gaps and reader feedback into draft pull requests for human review. The system captures failed assistant answers and reade…

IT Path Solutions has published a documented n8n workflow that builds an automated triage layer for production AI agent errors, classifying failures into tool call failures, context window exhaustion, state corruption, r…

A developer outlined a workflow for using MCP-enabled AI agents to turn product requirements documents into StoriesOnBoard story maps without overwriting existing decisions. The approach has the agent first extract struc…

The AI Village, a multi-agent experiment launched by the research initiative AI Digest, has grown from four agents running two hours a day to 27 agents running eight hours a day on shared goals including creating merch s…

A developer evaluated more than 500 agent skills against a six-dimension rubric covering trigger quality, structure, workflow design, content, engineering, and security, and published a list of the ten worth installing. …

A developer's analysis draws a parallel between the agentic loop used by coding agents like Claude Code and OpenAI's Codex and the 1978 split of the original TCP protocol into TCP and IP. The piece traces how Vint Cerf, …

A developer published a postmortem on a merge-gate failure class in which an automated judge scored an AI agent's transcript narrative instead of the actual git diff, allowing a schema-widening contract change to pass as…

Theoretical computer scientist Scott Aaronson, who previously held a "conservative, skeptical position" on self-improving AI, said in a blog post published Tuesday that he has updated his view and that humanity is "certa…

An analysis of 14,767 arXiv evaluation-resource papers published between 2022 and 2026 found that LLM benchmarks are shifting toward action, interaction, and professional-use tasks, with LLM-based scoring increasingly us…

The new BioPhys-Bridge benchmark, a 500-case, 1,517-task dataset for physics-grounded biological reasoning, shows state-of-the-art LLMs top out at an evidence-retrieval F1 of just 0.360, with DeepSeek-V4-Flash leading an…