Assista nt Professor
Department of Health Data Science and Biostat istics
UT Southwestern Medical Center
Talk Title: Scaling Biomedical Intelligence in LLM Agents: Toward an Integrated Environment for a Self-Improving AI Co-Scientist
Abstra ct: Progress toward an AI co-scientist\, an agent that formulates hypotheses\, executes analyses\, and reasons toward discovery\, is constrai ned less by the reasoning capacity of large language models (LLMs) than by the infrastructure in which they operate. Biomedical data science research remains fragmented across specialized knowledge sources\, heterogeneous dat abases\, and non-interoperable tools\, so that even capable models yield an alyses that are difficult to reproduce and verify. We propose an integrated environment for agentic biomedical data science that unifies grounded evid ence retrieval\, executable analysis over real biomedical data\, and verifi able feedback into a continuous self-improvement loop. By learning from mea surable outcomes rather than unverified self-assessment\, the agent can ite ratively propose\, test\, critique\, and refine its solutions. Such an envi ronment can serve as both a workspace and a training ground for scalable\, reproducible biomedical intelligence\, advancing the next generation of AI co-scientists.
Host: Dr. Ting Wang
CATEGORIES:SPECIAL SEMINAR LOCATION:Couch Bldg.\, Rm. 6001B GEO:38.634194;-90.260875 ORGANIZER;CN="Michelle Gibbs":MAILTO:gibbsm@wustl.edu URL;VALUE=URI:https://genetics.wustl.edu/events/event/wenqi-shi-2026/ END:VEVENT BEGIN:VTIMEZONE TZID:America/Chicago BEGIN:DAYLIGHT TZOFFSETFROM:-0600 TZOFFSETTO:-0500 DTSTART:20260308T080000 TZNAME:CDT END:DAYLIGHT END:VTIMEZONE END:VCALENDAR