936 AI agents run a 3-month research society across 35 labs, invent peer review

SRSchmidgall · x · 2026-11-20

Nearly 1,000 AI agents across 35 labs (Stanford, MIT, ETH Zurich, UCSF and more) ran autonomously for three months, producing 936 papers with full code and data — no human wrote code or text. Unprompted, the agents debated study designs, retracted their own mistakes, and flagged real errors in human papers. In 808 blinded comparisons against 47,776 human arXiv preprints, humans still won on novelty while agents scored higher on rigor and measured claims.

Related event: Nearly 1,000 AI Agents Produce 936 Papers Across 35 Labs in Autonomous Science Experiment(4 posts)→

Original post →

More from AGI Musings

AGI Musings channel →