Manuscripts-turned AI agents can now 'talk' to each other and make new discoveries
Stanford researchers have developed 'Paper2Agent,' an AI program that converts static scientific manuscripts into interactive agents. These agents can explain their research, apply methods to new data, and collaborate with other paper agents.
Why it matters
This innovation could fundamentally change how scientific knowledge is stored and shared, moving from passive documents to active, interconnected digital entities.
edited by Sadie Harley , reviewed by Robert Egan
This article has been reviewed according to Science X's editorial process and policies . Editors have highlighted the following attributes while ensuring the content's credibility:
Add as preferred source Workflow of Paper2Agent. Credit: arXiv (2025). DOI: 10.48550/arxiv.2509.06917 Since 1665, scholarly journals have served as written records of scientific advancement—static words on a page, references written by people for other people to read. That's about to change.
A team of Stanford Medicine researchers led by postdoctoral scholar Jiacheng Miao, Ph.D., and associate professor of biomedical data science James Zou, Ph.D., designed an artificial intelligence program called Paper2Agent that turns any scientific manuscript—including the text, figures and data—into an interactive AI agent that can chat about the paper and interact with other paper agents.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in