PalanerFree on the App Store
Get
Reading Group (+πŸ•): Reimagining Research Papers As Interactive and Reliable AI Agents
WorkFree

Reading Group (+πŸ•): Reimagining Research Papers As Interactive and Reliable AI Agents

Wednesday 18 November 2026, 16:30Venue time (Los Angeles)
FreeTickets sold by luma.com
Book Β· Freevia luma.com
Add to calendar

Downloads an .ics file Β· Times are in America/Los_Angeles Β· Google Calendar

Join the Snorkel AI Reading Group, a recurring forum to explore the latest frontier developments in AI while building meaningful connections within the community.

Research papers are how science spreads, but for centuries they have functioned as static vessel – a record of discovery but not, in itself, a tool. Researchers lose days to hunting down repos, fixing dependencies, and decoding undocumented code before they can run a single analysis on their own data. What if you could turn a paper into something capable of executing the very methods it describes?

In this session, Stanford HAI Postdoctoral Fellow Jiacheng Miao presents Paper2Agent, an open source framework that turns a paper and its codebase into an interactive AI agent that can run the paper's methods and even team up with agents from other papers to explore questions no single paper answered. In one case, paper agents collaborated to identify a likely causal gene for psoriasis, with a human researcher steering the validation!

Learn about:

A multi-agent pipeline that finds the code, builds the environment, runs the paper’s tutorials, and packages the methods as an MCP server of tools, resources, and prompts.

How validation is built in to test tools against the original paper’s outputs, repaired if it fails, and dropped if it can’t be fixed.

Modular paper agents that can collaborate: On 100 computational biology papers, 74 were successfully converted, and resulting collaboration outperformed a general-purpose coding agent.

Agenda:4:30 pm - doors open5:00 pm - talk begins6:00 pm - discussion, networking, Paper2Agent pizza party

πŸ•πŸ•πŸ• Pizza & beverages will be provided πŸ•πŸ•πŸ•

This work is published in Nature, and an arXiv preprint is available here.

Jiacheng Miao is a Postdoctoral Fellow at the Stanford Institute of Human-Centered AI, whose work has been featured by Anthropic, The Scientist, and Stanford Medicine, and recognized with the NOMIS & Science Young Explorer Award.

Ask Palaner

Going to Reading Group (+πŸ•)? Ask me anything about it.

I read the organiser's pages and answer in a few seconds.

Answers are AI-generated Β· Privacy