Why Read a Research Paper When You Can Turn It Into an AI Agent?

Have you ever read a paper in Science or Nature and thought, “Man, that research was so cool. I wish I could try that method on my own data,” only to spend a week wrestling with someone else’s undocumented repo, broken dependencies, and half-finished readme.txt?

Well, now you can, more or less.

Say hello to Paper2Agent, a new open-source framework that transforms academic reports into interactive AI agents you can talk to. Give it a paper, along with the accompanying codebase, data, or other supplementary material, and the system automatically extracts the core workflows, then spins up a tested, runnable toolkit that you can use on your own datasets.

The concept may sound a little like Google’s NotebookLM (now called Gemini Notebook ), which lets you upload documents and chat with an AI about what’s in them. But Paper2Agent aims to go a step further: Rather than simply answering questions about a paper, its agents can actually run the methods described in it—and potentially combine those methods with tools from other papers.

The goal, explains Stanford computer scientist James Zou , is to change what a scientific paper fundamentally is. “Knowledge should not be static records,” Zou says. “It really should be dynamic and interactive—and this has many benefits, including making knowledge more reproducible but also enabling all sorts of new kinds of discovery.”

Zou and his colleagues described the tool 16 September in Nature. They tested Paper2Agent across diverse disciplines including statistics, econometrics, and astrophysics. However, the researchers focused their proof-of-concept demonstrations on computational biology, where turning published methods into usable tools can be particularly cumbersome.

From Paper to Prompt

The team started with AlphaGenome, a deep-learning model that predicts how mutations in DNA affect gene regulation. (A companion resource unveiled earlier this month , the AlphaGenome Atlas, cataloged the model’s predictions for all 9 billion possible single-letter changes in the human genome.)

The researchers fed Paper2Agent the corresponding documentation and code. About 45 minutes later, with no human intervention, the AI had produced 22 tools covering different aspects of AlphaGenome’s functionality, all on a personal laptop and for less than US $15 in computing costs. One tool, for example, could predict how a DNA change might affect gene activity, while others could compare those effects across tissues or analyze multiple variants at once.

“The idea of making papers more dynamic and executable through an agentic interface is quite compelling.” —Dongping Chen, University of Maryland

All 22 tools passed automated validation, thanks to a testing agent working behind the scenes to run the various AlphaGenome sub-tools against reference results. If a test failed, the agent would diagnose the problem and try to fix the tool, with up to six attempts per function. If that didn’t work, it could drop the tool altogether.

The validated tools were then packaged into a Model Context Protocol server and connected to Claude Code (though any compatible chat-based AI assistant could do). The result was a user-facing AlphaGenome agent that could take questions in plain English, run the appropriate analyses, and spit back results and visualizations.

The team then put the agent through its paces, hitting it with a battery of questions, ranging from simple requests to open-ended research problems. According to the researchers’ analysis, it outperformed both standard Claude given the AlphaGenome codebase and a specialist AI co-scientist tool called Biomni .

Multi-Agent Research Paper Collaboration

Going one step further, the researchers turned a couple of more papers into interactive agents and linked them with the AlphaGenome agent. (One of the additional papers was on how inherited DNA variants linked to autoimmune disease disrupt cell function, while the other was a more systematic exploration of how silencing every expressed gene alters immune cells.)

Prompted to investigate the genetic basis of psoriasis, an itchy skin disease, the three agents collectively zeroed in on a little-understood gene called GPR137 as a likely causal factor. What’s more, the AI proposed 10 ways to validate this inference. A human researcher selected one, and the resulting analysis found that silencing GPR137 produced changes in gene activity strikingly similar to those caused by the psoriasis-linked variant in immune cells.

“These agents, because they’re able to directly collaborate and communicate, can facilitate all these kinds of collaborations,” says Zou.

Other researchers see plenty of potential as well. “The idea of making papers more dynamic and executable through an agentic interface is quite compelling,” says Dongping Chen , a computer scientist at the University of Maryland in College Park.

“Agentification itself is a useful certificate that says, ‘This work is relatively complete and well documented.’” —James Zou, Stanford University

Olivier Elemento , a computational biologist who directs the Englander Institute for Precision Medicine at Weill Cornell Medicine in New York City, sees the approach as having broader implications for how researchers share their work.

“It’s a real advance in terms of how we think about the publication process,” he says, “with AI at the center and in a way that makes publications more interactive.” (Elemento peer-reviewed the study for Nature .)

The potential applications extend beyond the research side of academia, too. Artur Skowroński , head of application development at the Polish software company VirtusLab, noted in a blog post that Paper2Agent could help bring scientific papers to life in classrooms. For example, students could use the agent to play with methods described in the literature instead of merely reading about them.

The Future of Agentified Research Papers

With Paper2Agent now up and running, Zou and his colleagues have…

News is gathered automatically from public robotics & AI feeds on a schedule.