HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
HypoEvolve turns multi-agent scientific work into explicit population updates governed by a genetic algorithm. The result suggests agent collaboration is easier to test when selection and revision are formalized.
HypoEvolve coordinates specialized LLM agents with a **generational genetic algorithm** that revises and retains a population of hypotheses. Agents contribute mechanistic arguments, challenge assumptions, and assess evidence and testability.
Builders of multi-agent research systems can make collaboration measurable by encoding how proposals are combined, selected, and revised instead of relying on an opaque group conversation. Across **34 cancer types**, the method led six baselines on both external measures.
HypoEvolve coordinates specialized LLM agents with a **generational genetic algorithm** that revises and retains a population of hypotheses. Agents contribute mechanistic arguments, challenge assumptions, and assess evidence and testability. Builders of multi-agent research systems can make collaboration measurable by encoding how proposals are combined, selected, and revised instead of relying on an opaque group conversation. Across **34 cancer types**, the method led six baselines on both external measures. DepMap selectivity reached **0.171 versus 0.115** for the strongest baseline, with gains also reported on held-out cancer types. The evidence is specific to drug-repurposing hypotheses and two adapted evaluation measures, so broader scientific generalization remains open.
This makes multi-agent scientific collaboration an explicit population-search algorithm with retained, recombined, challenged, and selected hypotheses. It reinforces collective-search harnesses while narrowing the claimed advantage to drug-repurposing and proxy measures. The design improves traceability of how proposals evolve, but does not resolve whether selection rewards capture genuine discovery or whether the pattern transfers beyond this domain.