Pu Wang 王普
 |
Pu Wang |
About me
I am a third-year undergraduate student (2023.9 – Present) in Turing Class, Chu Kochen Honors College, Zhejiang University, pursuing a B.E. in Artificial Intelligence with an honors degree. Since March 2025 I have been a research intern at the State Key Lab of CAD&CG, advised by Prof. Yao-Xiang Ding.
My research interests lie in the theory and algorithms of sequential decision-making, with a growing focus on large language models and language agents. I am interested in the algorithmic foundations of how language models and agents reason, plan, optimize behavior, and make decisions in interactive environments. More broadly, I aim to connect ideas from reinforcement learning, imitation learning, and preference learning to modern problems in LLM post-training, RLHF, agentic AI, and alignment.
Research directions
Sequential decision-making. Theory and algorithms for bandits and reinforcement learning, e.g., unified frameworks for best arm identification and regret minimization in dueling bandits.
Imitation & preference learning. Learning from partial or heterogeneous supervision, with connections to RLHF and preference-based optimization.
LLMs & language agents. How language models and agents reason, plan, and make decisions in interactive environments, and how to align them.
News
2026.06 – Our work on a unified framework for dueling bandits (TG-ITE) is available as a preprint on arXiv.
Selected Papers
Tree-Guided Identify-Then-Exploit: A Unified Framework of Best Arm Identification and Regret Minimization for Dueling Bandits
|
For the full list, see Publications.