FAES Science Insight Series: Trust Through Knowledge Grounding: AI Agents in Biomedicine
This series invites Principal Investigators, Senior Scientists, and Senior Clinicians to share cutting-edge research and developments in their fields in the FAES Learning Labs in Building 10. Each session includes a 20-30 minute presentation followed by a Q&A or journal club discussion, fostering deeper insights and scholarly exchange. Lunch is provided on a first come first served basis.
This event is for members of the NIH community only. You must register with your nih.gov email to confirm your registration.
Trust Through Knowledge Grounding: AI Agents in Biomedicine with Zhiyong Lu, PhD FACMI, FIAHSI, Senior Investigator, NIH, Professor of Computer Science (Adjunct), UIUC
Recent advances in large language models (LLMs) have enabled powerful AI agents for biomedical research, yet their adoption in high-stakes settings remains limited by concerns about hallucination, opacity, and reliability. In this talk, I discuss how expert-curated domain knowledge can be used to help mitigate these challenges in general-purpose LLMs. Drawing on real-world systems and case studies such as GeneAgent (Nature Methods 2025), I will highlight design principles for building AI agents that are scientifically sound, interpretable, and suitable for biomedical research and clinical applications.
Return to News / Events