{
  "id": 9241103,
  "title": "Paper2Agent from Stanford: Turn research papers into AI agents that run real code",
  "url": "https://urgent.news/2026/09/23/paper2agent-stanford-ai-agent",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-23T01:44:03.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/sarantoon/paper2agent-cchaak-stanford-epliiynngaanwicchayaihepn-ai-agent-thiiranokhdcchring-3omd"
  },
  "original_language": "th",
  "account": "Researchers from Stanford University have developed Paper2Agent, an AI system that converts research papers into interactive agents that can run code and answer questions. The system, published in Nature on September 16, can process GitHub repositories and run code to extract tools and create a server that can be used by others. In tests, Paper2Agent successfully converted 74 out of 100 bioinformatics papers and 9 out of 10 non-bioinformatics papers, with a 98% accuracy rate. The system is available under an MIT license, but requires an external AI agent and may incur API costs, estimated to be around $14 to $15 per repository. A demo is available on Hugging Face Spaces.",
  "summary": "Paper2Agent, developed by a team from Stanford University, is an innovative AI-powered tool that converts research work into executable code. Unlike traditional question-answering systems, which require users to download code, set up environments, and troubleshoot dependencies, Paper2Agent offers a more user-friendly solution. Users can simply provide a GitHub repository containing research work, and the AI will clone the repository, identify relevant files, run the code, and present the results. This approach allows users to quickly test and utilize research findings without the usual hassle of setting up and running code. The tool has been tested on various research papers, achieving high success rates in tasks such as parameter tuning and problem-solving. However, the success rate is not perfect, with around one in four cases requiring human intervention due to incomplete code, poor-quality papers, or unresolved dependencies. Despite this, the research team emphasizes the importance of transparency in reporting, acknowledging that while the tool is promising, it should be used with caution and under the supervision of domain experts. Users can try Paper2Agent for free, but note that costs may apply depending on the usage of external AI APIs.",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}