Entity · technique
AGENTS.md
techniqueactive
agents-md-d45d4db8·5 events·first seen Aliases: AGENTS.md
Co-occurring entities
Linux FoundationAgentic AI FoundationOpenAIQwen3.5-35B-A3BSWE-Bench VerifiedNVIDIA Nemotron-3-Nano-30B-A3BProbe-and-Refine Tuning of Repository Guidance for Coding AgentsMicrosoftBlockGoogleBloomberggooseCloudflareMCP RegistryAmazon Web ServicesAnthropicModel Context ProtocolSQLiteSimon WillisonMistral AI
More like this (12)
Recent events (5)
Probe-and-Refine Tuning improves coding agent performance via iterative repository guidance refinement
A new arXiv paper introduces probe-and-refine tuning, a procedure that uses synthetic bug-fix probes to iteratively improve AGENTS.md repository guidance files for LLM-based coding agents without requiring an agent loop during tuning. Evaluated on SWE-bench Verified with Qwen3.5-35B-A3B, the method achieves 33.0% mean resolve rate versus 28.3% for a static knowledge base baseline and 25.5% for an unguided baseline. The improvement is attributed to coverage gains—refined guidance helps agents locate the correct files rather than improving patch quality—and a step-budget experiment shows guidance is necessary for agents to productively use larger compute budgets.
Anthropic Donates Model Context Protocol to Linux Foundation, Co-founds Agentic AI Foundation
Anthropic is donating the Model Context Protocol (MCP) to the newly established Agentic AI Foundation (AAIF), a directed fund under the Linux Foundation co-founded by Anthropic, Block, and OpenAI, with support from Google, Microsoft, AWS, Cloudflare, and Bloomberg. MCP has reached significant adoption milestones including 10,000+ active public servers, 97M+ monthly SDK downloads, and integration into ChatGPT, Gemini, Microsoft Copilot, and Visual Studio Code. The AAIF will also house Block's goose and OpenAI's AGENTS.md as founding projects, aiming to foster open, vendor-neutral standards for agentic AI. MCP governance will remain community-driven with existing maintainers continuing their roles.
sqlite AGENTS.md
Simon Willison publishes an AGENTS.md file for the SQLite project, a convention for providing AI coding agents with project-specific instructions and context. This follows the emerging practice of including agent-readable documentation files in codebases to guide LLM-based tools. The post reflects the growing ecosystem of conventions around agentic coding workflows.
OpenAI co-founds Agentic AI Foundation, donates AGENTS.md
OpenAI has co-founded the Agentic AI Foundation, a new organization housed under the Linux Foundation, aimed at developing open and interoperable standards for safe agentic AI systems. As part of this initiative, OpenAI is donating AGENTS.md, a specification document, to the foundation. The move signals OpenAI's intent to shape industry-wide norms around agentic AI through open governance structures rather than proprietary control.
Mistral Builds Autonomous Rails Test-Writing Agent Using Vibe Coding Assistant
Mistral's Applied AI Proto team built an autonomous agent that reads Ruby on Rails source files and generates or improves RSpec tests with no human intervention, running in parallel across large codebases inside CI/CD pipelines. The agent is built on Vibe, Mistral's open-source coding assistant, and uses context engineering via AGENTS.md files, per-file-type skill files, and custom tools for linting and coverage validation. Key techniques include forced self-review prompts, specialized skill files per Rails file category, and careful handling of shared RSpec factories. The approach improved a quality score from 0.68 to 0.74 through structured prompt engineering alone.