Autonomous biomedical research with an artificial intelligence agent

• 成果类型: Article
• 署名作者: Huang, Kexin; Zhang, Serena; Wang, Hanchen; Qu, Yuanhao; Lu, Yingzhou; Li, Ryan; Roohani, Yusuf; Qiu, Lin; Cao, Shiyi; Li, Gavin; Zhang, Junze; Yin, Di; Wierenga, Rick; Kavi, Deniz; Liu, Sherry; She, Tianwei; Marwaha, Shruti; Carter, Jennefer N.; Zhou, Xin; Wheeler, Matthew T.; Bernstein, Jonathan A.; Wang, Mengdi; He, Peng; Zhou, Jingtian; Snyder, Michael P.; Cong, Le; Regev, Aviv; Leskovec, Jure
• 署名单位: Stanford University; Stanford Medicine; Stanford University; Stanford University; Stanford University; University of Washington; University of Washington Seattle; University of California System; University of California Berkeley; Stanford University; Stanford University; Princeton University; University of California System; University of California San Francisco
• 刊物名称: SCIENCE
• ISSN/ISSBN: 0036-8075; 1095-9203
• DOI: 10.1126/science.adz4351
• 发表日期: 2026-08-20
• 页码: eadz4351
• 关键词: multiple sequence alignment; read alignment; database; library; association; inference; platform; catalog; package; atlas

摘要

Biomedical research is increasingly constrained by repetitive, fragmented workflows that slow discovery. We introduce Biomni, a general-purpose biomedical artificial intelligence agent that autonomously executes diverse research tasks. To map the biomedical action space, Biomni's action-discovery agent mines tools, databases, and protocols from thousands of publications across 25 domains, building a unified agentic environment. Its general-purpose architecture integrates large language model reasoning with retrieval-augmented planning and code-based execution, dynamically composing workflows without predefined templates. Systematic benchmarking shows strong generalization across heterogeneous tasks-causal gene prioritization, drug repurposing, rare-disease diagnosis, microbiome analysis, and molecular cloning-without task-specific tuning. Real-world case studies demonstrate Biomni interpreting multimodal datasets, optimizing protein stability, orchestrating wet-lab instruments, and generating experimentally testable protocols. Biomni envisions artificial intelligence augmenting human scientists and accelerating discovery.