Abstract: Recent advances in large language models (LLMs) and reinforcement learning (RL) have paved the way for the emergence of self-evolving agents. This talk first explores how the integration of LLMs and RL is transforming healthcare. We then discuss the paradigm shift from static models to autonomous agents that operate in real-world healthcare settings, highlighting opportunities, challenges, and lessons from early deployments.
Bio: Jiacheng is a Ph.D. candidate in Computer Science at the University of Illinois Urbana-Champaign, advised by Prof. Jimeng Sun. He received his B.Eng. and M.S. degrees in Automation from Tsinghua University. His research focuses on foundation models—such as large language models (LLMs) and multi-modal models—and reinforcement learning (RL), with applications in healthcare, biomedicine, and recommendation systems. He is particularly interested in enabling these models to perform reasoning, retrieval, and decision-making in complex real-world scenarios.