How a team of AIs discovered a promising lung-cancer drug

Researchers built a “virtual biotech” comprising up to 37,000 autonomous AI agents, coordinated by a lead “chief scientist” agent, that identified a promising lung-cancer drug candidate. The multi-agent system handled tasks spanning target identification, molecular design, and optimisation that would normally require a full drug-discovery organisation. Published in Nature, the work demonstrates a scalable AI-driven pipeline for oncology drug discovery, though the compound has not yet entered clinical trials.