Tianqi Liu

Beyond Markovian: Reflective Exploration via Bayes-Adaptive RL for LLM Reasoning

Reward-Guided Prompt Evolving in Reinforcement Learning for LLMs

Building Math Agents with Multi-Turn Iterative Preference Learning

RRM: Robust Reward Model Training Mitigates Reward Hacking

Evolving Alignment via Asymmetric Self-Play