Xuefeng Liu

Research: My research spans two complementary directions.

• Machine Learning Foundations: I develop practically driven, theoretically grounded methods in reinforcement learning, Agentic AI,and generative modeling.

• AI for Biomedical Discovery: My research primarily focuses on building   Agentic Reinforcement Learning Systems for Automated Biomedical Discovery, encompassing scientific reasoning and hypothesis generation, adaptive experimental design, lab automation, multimodal feedback learning, and self-evolution. A central goal is to advance these systems in terms of efficiency, trustworthiness, autonomy, cost-effectiveness, adaptability, and reliability in achieving scientific discoveries.

In parallel, I develop novel generative AI models as core components of these systems, with the ultimate goal of accelerating disease diagnosis and therapeutic discovery. My research interests include, but are not limited to:

• Reinforcement Learning
  • RL in pretraining, post-training, decoding optimization
  • Reasoning, planning, decision-making under uncertainty and sequential experiment design
• Agentic AI Systems
  • Agentic reinforcement learning, self-distillation, and self-evolution
  • Autonomous scientific discovery, auto-research, and lab automation
• Generative AI and Foundation Models
  • Generative modeling for biomedicine and beyond
• Human-AI co-scientist
  • Human–AI collaboration for scientific reasoning, hypothesis generation, and discovery
• AI for Biomedicine
  • Biomolecular design, drug discovery, biomarker discovery, lead optimization
  • Physics- and Biology-informed machine learning

About Me: Before joining UF, I was a Postdoctoral Fellow at School of Medicine, Stanford University, working with Prof. Le Cong and Prof. Mengdi Wang (Princeton University). Prior to Stanford, I received my Ph.D. in Computer Science from University of Chicago, where I was advised by Prof. Rick L. Stevens, with co-advisors Prof. Yuxin Chen and Prof. Jinbo Xu, and mentorship from Prof. Tobin R. Sosnick. I also served as a AI Researcher at Argonne National Laboratory, where my work focuses on AI for Biomedicine.

Open Opportunities:

• [Recruiting] My lab is actively recruiting motivated PhD students and Postdoc researchers. If you are interested in our research, please send your CV, a brief summary of your research experience, and a description of your research interests to xuefeng.liu@ufl.edu.

• [Research Students] I have open research opportunities, including on-site visiting student positions. Feel free to email me if you are interested! Candidates are expected to have earned an A- or A in Deep Learning or a related course.

Teaching:

• [CAI 6734] Applied Generative AI in Medicine — Fall 2026

Team:

I am fortunate to work with the following talented and motivated students and researchers: (* Visiting, in person/remote)

• Postdoctoral Researchers:
  • Yisel Martinez Noa, Ph.D., University of Florida
  • Xiao Luo, Ph.D., University of Chicago *
  • Xiaotian Duan, Ph.D., Argonne National Laboratory *
• Ph.D. Students:
  • Mingxuan Cao, University of Chicago *
  • Zhenya Liu, University of Chicago *
  • Luna Lyu, Stanford University *
  • Minghao Guo, MIT *
  • Jingtian Ji, Toyota Technological Institute at Chicago *
• Master Students:
  • Weiyi Tian, University of Chicago *
• Undergraduate Students:
  • Tianyi Chen, University of Wisconsin–Madison *
  • Meitong Chen, University of North Carolina at Chapel Hill *
  • Lilah Chen, Barnard College, Columbia University *
  • Siyuan Jiang, Tsinghua University *