Guoqing Liu is a Senior Researcher at
Microsoft Research AI for Science. His research interests encompass reinforcement learning (RL), the intersection of large language models (LLMs) and RL (e.g., reasoning and agents in natural language form), and their applications in scientific discovery. He gained extensive experience in deep RL research and its real-world applications (e.g.,
Project Suphx: Mahjong AI,
Project Mariana: Game Testing) during his Ph.D. studies and his first year as a researcher at
Microsoft Research Asia. More recently, his work has focused on LLM reasoning, RL agents, and their applications in drug discovery (e.g.,
PDVN,
RetroChimera,
NatureLM, and
MuProtein).
Prior to joining Microsoft Research, he earned his Ph.D. in 2021 from the
University of Science and Technology of China (USTC) through a joint program with
Microsoft Research Asia, supervised by
Tie-Yan Liu and
Nenghai Yu.