HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
HypoEvolve couples a generational genetic algorithm with specialized LLM agents to generate drug-repurposing hypotheses, beating six baselines on DepMap selectivity (0.171 vs 0.115).
HypoEvolve coordinates specialized LLM agents through a generational genetic algorithm in which scientific judgments and new proposals reshape a hypothesis population. Evaluation centers on drug repurposing, linking mechanistic explanations to target-level biological claims assessed via external measures adapted from DepMap and Open Targets. Across 34 cancer types, HypoEvolve scores highest against six baselines on both measures, with DepMap selectivity of 0.171 versus 0.115 for the strongest baseline, and gains generalize to held-out cancer types.
- Genetic algorithm coordinates specialized LLM agents over evolving hypothesis populations
- Drug repurposing ties generated hypotheses to target-level biological claims
- DepMap and Open Targets adapted as external evaluation measures
- DepMap selectivity 0.171 versus 0.115 for strongest baseline across 34 cancer types
- Gains over single-pass generation hold on held-out cancer types
From the original article
1 min read at arxiv.orgScientific agents contribute to hypothesis discovery by synthesizing evidence, assessing proposals, and developing new explanations. Recent systems combine scientific agents with evolutionary search through critique, comparison, and revision. However, how different forms of agent collaboration affect hypothesis quality remains an open question.
By Jieyuan Liu · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.