The abstract is read at the publisher; the summary is JClub's.
Biomni, a general-purpose biomedical AI agent, autonomously executes diverse research tasks and shows strong generalization across heterogeneous domains without task-specific tuning.
- Why it matters: Biomedical discovery is slowed by repetitive, fragmented workflows, and there is a need for an agent that can flexibly run many research activities rather than relying on fixed templates.
- What they did: Biomni maps the biomedical action space by mining tools, databases, and protocols from thousands of publications across 25 domains, then uses large language model reasoning with retrieval-augmented planning and code-based execution.
- The result: Benchmarks indicate strong generalization across causal gene prioritization, drug repurposing, rare-disease diagnosis, microbiome analysis, and molecular cloning, and case studies show it can generate experimentally testable protocols and coordinate wet-lab work.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.