Multi agent large language models for biomedical hypothesis generation in drug combination discovery.

ABSTRACT: Recent advancements in large language models (LLMs) have demonstrated their potential in scientific reasoning, but their ability to open-ended hypotheses in data-scarce domains remains underexplored. Here, we introduce Combinatorial Alzheimer's Disease Therapeutic Efficacy Decision (Coated-LLM), an AI-driven framework that is inspired by scientific collaboration to predict efficacious combinatorial therapy when data-driven prediction is infeasible. Coated-LLM employs multiple specialized LLM agents-Researcher, Reviewer s, and Moderator-to systematically generate and evaluate hypotheses through several in-context learning techniques. Using Alzheimer's disease (AD) as a test case, Coated-LLM outperformed traditional knowledge-bas

SUBMITTER: Xu Q 

PROVIDER: S-EPMC12682125 | biostudies-literature | 2025 Dec

REPOSITORIES: biostudies-literature