{"version":1,"type":"story","url":"https://digestai.news/story/paper2agent-turns-research-papers-into-interactive-ai-agents","json":"https://digestai.news/story/paper2agent-turns-research-papers-into-interactive-ai-agents.json","markdown":"https://digestai.news/story/paper2agent-turns-research-papers-into-interactive-ai-agents.md","slug":"paper2agent-turns-research-papers-into-interactive-ai-agents","headline":"Paper2Agent turns research papers into interactive AI agents","summary":"Paper2Agent is an open‑source framework that automatically converts academic papers, their code and data into runnable AI agents.  Stanford computer scientist James Zou and his team described the system in a Nature paper on September 16 and demonstrated it on the AlphaGenome deep‑learning model, which predicts DNA‑mutation effects.  Feeding the AlphaGenome documentation into Paper2Agent produced 22 functional tools in about 45 minutes on a laptop for under US $15 of compute, and all tools passed automated validation.\n\nThe researchers also linked agents built from two other papers with the AlphaGenome agent, allowing the trio to pinpoint the gene GPR137 as a likely causal factor for psoriasis and to propose ten validation experiments, one of which a human selected and confirmed.  In a broader test of 100 computational‑biology papers, 26 could not be turned into agents because of missing code or documentation, a failure the authors view as a useful diagnostic.  The team has already used Paper2Agent to create a “Virtual Biotech” multi‑agent platform and even generated an agent for the Paper2Agent paper itself, hosted at paper2agent.ai.","keyPoints":["Paper2Agent generated 22 AlphaGenome tools in about 45 minutes for under $15 compute cost.","Of 100 computational‑biology papers tested, 26 could not be converted into agents due to incomplete code or documentation.","Agents collaborated to identify gene GPR137 as a psoriasis candidate and suggested ten validation methods."],"whyItMatters":"Turning static research papers into executable agents could dramatically improve reproducibility, accelerate discovery, and let scientists interact with published methods directly.","category":{"slug":"agents","name":"Agents & Tools","url":"https://digestai.news/category/agents"},"entities":{"companies":["Stanford University","University of Maryland","Weill Cornell Medicine","VirtusLab"],"models":["AlphaGenome"],"people":["James Zou","Dongping Chen","Olivier Elemento","Artur Skowroński"]},"firstPublishedAt":"2026-09-22T15:00:05Z","updatedAt":"2026-09-22T15:00:05Z","sourceCount":1,"hasPrimarySource":false,"sources":[{"outlet":"IEEE Spectrum AI","title":"Why Read a Research Paper When You Can Turn It Into an AI Agent?","url":"https://spectrum.ieee.org/paper2agent-ai-agents-research-papers","publishedAt":"2026-09-22T15:00:05Z","type":"press","primary":false,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"Digest AI, \"Paper2Agent turns research papers into interactive AI agents\", 22 September 2026, https://digestai.news/story/paper2agent-turns-research-papers-into-interactive-ai-agents","publisher":"Digest AI","title":"Paper2Agent turns research papers into interactive AI agents","datePublished":"2026-09-22T15:00:05Z","url":"https://digestai.news/story/paper2agent-turns-research-papers-into-interactive-ai-agents"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse"}