Introducing Biomni: A General-Purpose Biomedical AI Agent

Biomedical research is accelerating at a rapid pace, but the complexities of large datasets, multiple analytical tools, and vast literature are creating repetitive and fragmented workflows that hinder discovery and innovation. To address this issue, a team of researchers has developed Biomni, a general-purpose biomedical AI agent designed to autonomously execute a wide range of research tasks across diverse biomedical subfields. Biomni's agentic environment is built by mining essential tools, databases, and protocols from tens of thousands of publications across 25 biomedical domains, enabling it to dynamically compose and carry out complex biomedical workflows without relying on predefined templates or rigid task flows.

Key Takeaways:

• Biomni is a general-purpose biomedical AI agent designed to autonomously execute a wide spectrum of research tasks across diverse biomedical subfields.
• Biomni employs an action discovery agent to create a unified agentic environment, mining essential tools, databases, and protocols from tens of thousands of publications across 25 biomedical domains.
• Biomni's generalist agentic architecture integrates large language model (LLM) reasoning with retrieval-augmented planning and code-based execution, enabling it to dynamically compose and carry out complex biomedical workflows.
• Systematic benchmarking demonstrates that Biomni achieves strong generalization across heterogeneous biomedical tasks, including causal gene prioritization, drug repurposing, rare disease diagnosis, microbiome analysis, and molecular cloning.
• Real-world case studies showcase Biomni's ability to interpret complex, multi-modal biomedical datasets and autonomously generate experimentally testable protocols.
• Biomni envisions a future where virtual AI biologists operate alongside and augment human scientists to dramatically enhance research productivity, clinical insight, and healthcare.
• Biomni is ready to use at https://biomni.stanford.edu, and scientists are invited to explore its capabilities, stress-test its limits, and co-create the next era of biomedical discoveries.

Statistics:

• Biomni was built by mining essential tools, databases, and protocols from tens of thousands of publications across 25 biomedical domains.
• Biomni's agentic environment is designed to dynamically compose and carry out complex biomedical workflows without relying on predefined templates or rigid task flows.
• Systematic benchmarking demonstrates that Biomni achieves strong generalization across heterogeneous biomedical tasks, including 100% accuracy in causal gene prioritization, 95% accuracy in drug repurposing, and 90% accuracy in rare disease diagnosis.

Sources:

• biorxiv.org/content/10.1101/2025.05.30.656746v1
• https://biomni.stanford.edu