I am a Ph.D. student at The University of Hong Kong, advised by Prof. Jiayu Chen. My research focuses on reinforcement learning, LLM alignment, preference optimization, and agentic AI systems.
I study the theory and systems behind self-improving language models: online alignment and RLHF, robust preference learning, self-play post-training, and long-horizon agents that reason with tools, memory, and feedback. I am particularly interested in turning principled learning algorithms into reliable, scalable AI systems.
Before joining HKU, I earned a BSc in Information and Computing Science from Dalian University of Technology, ranking 10th out of 195 students.
News
Distributionally Robust Listwise Preference Optimization accepted to NeurIPS 2026. See you in Sydney!
Joining Microsoft in Beijing as a Research Intern, working on Agent RSI and Auto Research.
Started leading EnergyBridge, a long-horizon LLM-agent system for virtual power plant coordination.
On the Convergence of Self-Improving Online LLM Alignment accepted to UAI 2026. See you in Amsterdam!
Occupancy Reward Shaping accepted to ICLR 2026.
Started my Ph.D. at The University of Hong Kong.
Experience
Research Intern
Microsoft · Beijing, China
Research on Agent RSI and Auto Research.
Project Lead, Agentic Intelligence Lab
The University of Hong Kong · Hong Kong SAR
Independently authored multiple research papers and led the development of several research projects.
Research Assistant
University of California, Irvine · Irvine, CA
Worked on LLM-assisted workflow analysis and reporting for the Texera data analytics platform.
Selected Publications and Submissions
All research →-
Distributionally Robust Listwise Preference Optimization
Xudong Wu, Jian Qian, Pangpang Liu, Vaneet Aggarwal, and Jiayu Chen.
NeurIPS 2026 -
On the Convergence of Self-Improving Online LLM Alignment
Xudong Wu, Pangpang Liu, Vaneet Aggarwal, and Jiayu Chen.
UAI 2026 -
Occupancy Reward Shaping: Improving Credit Assignment for Offline Goal-Conditioned Reinforcement Learning
Aravind Venugopal, Jiayu Chen, Xudong Wu, Chongyi Zheng, Benjamin Eysenbach, and Jeff Schneider.
ICLR 2026 -
Population-Based Self-Play for LLM Safety Training
Wentse Chen*, Xudong Wu*, Yu Gan, Guangchen Lan, Zhihan Zhang, Arvind Krishnamurthy, Jiayu Chen, and Jeff Schneider.
Submitted to International Conference on Learning Representations (ICLR), 2027 -
Target-based Semi-amortized Dynamic Programming for Complex Crowd Evacuation
Shijie Pan, Xudong Wu, Qixiu Cheng, Jiayu Chen, and Wenjie Huang.
Submitted to Decision Analysis -
Hierarchical Deep Counterfactual Regret Minimization
Jiayu Chen, Xudong Wu, Zhekai Wang, and Vaneet Aggarwal.
Submitted to Journal of Autonomous Agents and Multi-Agent Systems
Research Interests
- LLM post-training and alignment: RLHF/RLAIF, preference optimization, online alignment, and verifier-guided learning.
- Agentic AI: self-improving agents, tool use, persistent memory, multi-agent systems, and long-horizon planning.
- Reinforcement learning: offline and goal-conditioned RL, self-play, game-theoretic learning, and trust-region methods.
Education
The University of Hong Kong
Ph.D. · Reinforcement Learning and LLM Alignment
Dalian University of Technology
BSc Information and Computing Science · Ranked 10/195
Teaching
Fall 2026: Advanced Machine Learning Methods.