Scholar
Baoxiang Wang
Google Scholar ID: cQe4OeYAAAAJ
Assistant Professor, The Chinese University of Hong Kong Shenzhen
reinforcement learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
684
H-index
15
i10-index
19
Publications
20
Co-authors
10
list available
Publications
23 items
Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning
2026
Cited
0
Solver-Guided Reasoning for Mixed-Equilibrium Strategies
2026
Cited
0
PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers
2026
Cited
0
The Reciprocity Gradient
2026
Cited
0
Epistemic Gain, Aleatoric Cost: Uncertainty Decomposition in Multi-Agent Debate for Math Reasoning
2026
Cited
0
Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents
2026
Cited
0
The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL
2026
Cited
0
Trust Region Masking for Long-Horizon LLM Reinforcement Learning
2025
Cited
0
Load more
Co-authors
8 total
Shuai Li (李帅)
Shanghai Jiao Tong University
Jing Dong
The Chinese University of Hong Kong, Shenzhen
Hongyuan Zha
The Chinese University of Hong Kong, Shenzhen
Kun Kuang
Zhejiang University
Furui Liu
Zhejiang Lab and UCAS and Zhejiang University
Fei Wu
Professor of Computer Science, Zhejiang University
Jun XIAO （肖俊）
Institute of Artificial Intelligence, Zhejiang University
Matthew E. Taylor
Professor, University of Alberta
