AutoScientists NeurIPS paper: self-organizing AI research teams hit 74.4 percentile on BioML-Bench

marinkazitnik · x · 2026-09-25

AutoScientists, a NeurIPS-accepted paper from Shanghua Gao, Ada Fang, and Marinka Zitnik, introduces a decentralized team of AI agents for long-running computational scientific experimentation.

Results under matched budgets: 74.4% mean leaderboard percentile across 24 BioML-Bench tasks (imaging, protein engineering, single-cell omics, drug discovery), +8.33% over the strongest prior biomedical agent; on LLM training optimization it reaches the target validation bits-per-byte 1.9× faster than autoresearch. Paper and code are public.

Original post →

More from coding & agent

coding & agent channel →