Guoqing Liu (刘国庆)
Senior Researcher
Microsoft Research AI for Science

Google Scholar | Github

guoqingliu (at) microsoft.com
21 Station Road, Cambridge, CB1 2FB, United Kingdom
Biography
Guoqing Liu is a Senior Researcher at Microsoft Research AI for Science in Cambridge, UK. His research focuses on reinforcement learning, foundation model post-training, and AI for scientific discovery. His representative works include QFANG, RetroChimera, PDVN, and TDPO. Previously, he was a Senior Researcher at Microsoft Research Asia, where he worked on reinforcement learning algorithms and real-world AI systems, including Suphx, a superhuman Mahjong AI, and Inspector, a game-testing agent for Xbox. He received his Ph.D. from the University of Science and Technology of China through a joint program with Microsoft Research Asia (2016–2021), advised by Tie-Yan Liu and Nenghai Yu.

Publications
("*": equal contribution; "†": correspondence)

LLM Post-Training, Reinforcement Learning, AI for Science

  1. Chemist-aligned retrosynthesis by ensembling diverse inductive bias models (RetroChimera) [Paper] [News]
    Krzysztof Maziarz*, Guoqing Liu*, Felix Pultar*, John Gardner, Tobias Gensch, Jean Helie, Hubert Misztela, Austin Tripp, Junren Li, Aleksei Kornev, Piotr Gaiński, Holger Hoefling, Mike Fortunato, Rishi Gupta, Andrew Baxter, Darren L. Poole, Jennifer M. Elward, Adrian Krzyzanowski, Peter Pogány, Stephen D. Pickett, Ian D. Wall, Christopher M. Bishop, Philip G. Humphreys, James A. Lumley, Mario P. Wiesenfeldt, Marwin H. S. Segler. Nature, 2026.
  2. Token-Importance Guided Direct Preference Optimization (TDPO-v2) [Paper]
    Ning Yang, Hai Lin, Yibo Liu, Baoliang Tian, Guoqing Liu, Haijun Zhang. ICLR, 2026, Oral.
  3. A Scientific Reasoning Model for Organic Synthesis Procedure Generation (QFANG) [Paper]
    Guoqing Liu*, Junren Li*, Zihan Zhao*, Eray Inanc, Krzysztof Maziarz, Jose Garrido Torres, Victor Garcia Satorras, Shoko Ueda, Christopher M. Bishop, Marwin Segler. arXiv, 2025.
  4. Accelerating protein engineering with fitness landscape modelling and reinforcement learning (MuProtein) [Paper] [News]
    Haoran Sun*, Liang He*, Pan Deng*, Guoqing Liu*, Zhiyu Zhao, Yuliang Jiang, Chuan Cao, Fusong Ju, Lijun Wu, Haiguang Liu, Tao Qin, Tie-Yan Liu. Nature Machine Intelligence, 2025.
  5. NatureLM: Deciphering the Language of Nature for Scientific Discovery [Paper]
    Yingce Xia*, Peiran Jin*, Shufang Xie*, Liang He*, Chuan Cao*, Renqian Luo*, Guoqing Liu*, Yue Wang*, Zequn Liu*, Yuan-Jyue Chen*, Zekun Guo*, etc. arXiv, 2025.
  6. HybriDNA: A Hybrid Transformer-Mamba2 Long-Range DNA Language Model [Paper]
    Mingqian Ma*, Guoqing Liu*, Chuan Cao*, Pan Deng*, Tri Dao, Albert Gu, Peiran Jin, Zhao Yang, Yingce Xia, Renqian Luo, Pipi Hu, Zun Wang, Yuan-Jyue Chen, Haiguang Liu, Tao Qin. ICLR MLGenX Workshop, 2025.
  7. Token-level Direct Preference Optimization (TDPO) [Paper]
    Yongcheng Zeng, Guoqing Liu, Weiyu Ma, Ning Yang, Haifeng Zhang, Jun Wang. ICML, 2024.
  8. Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers (EvoPrompt) [Paper]
    Qingyan Guo, Rui Wang, Junliang Guo, Bei Li, Kaitao Song, Xu Tan, Guoqing Liu, Jiang Bian, Yujiu Yang. ICLR, 2024.
  9. De novo Drug Design using Reinforcement Learning with Multiple GPT Agents (MolRL-MGPT) [Paper]
    Xiuyuan Hu, Guoqing Liu†, Yang Zhao, Hao Zhang. NeurIPS, 2023.
  10. Retrosynthetic Planning with Dual Value Networks (PDVN) [Paper]
    Guoqing Liu*, Di Xue*, Shufang Xie, Yingce Xia, Austin Tripp, Krzysztof Maziarz, Marwin Segler, Tao Qin, Zongzhang Zhang, Tie-Yan Liu. ICML, 2023.

Reinforcement Learning, Sequential Decision Making

  1. Proactive Constrained Policy Optimization with Preemptive Penalty [Paper]
    Ning Yang, Pengyu Wang, Guoqing Liu, Haifeng Zhang, Pin Lv, Jun Wang. AAAI, 2026.
  2. Reinforcement Learning from Bagged Reward [Paper]
    Yuting Tang, Xin-Qiang Cai, Yao-Xiang Ding, Qiyu Wu, Guoqing Liu, Masashi Sugiyama. TMLR, 2025.
  3. You May Not Need Ratio Clipping in PPO [Paper]
    Mingfei Sun, Vitaly Kurin, Guoqing Liu, Sam Devlin, Tao Qin, Katja Hofmann, Shimon Whiteson. arXiv, 2022.
  4. Inspector: Pixel-based Automated Game Testing via Exploration, Detection, and Investigation [Paper]
    Guoqing Liu, Mengzhang Cai, Li Zhao, Tao Qin, Adrian Brown, Jimmy Bischoff and Tie-Yan Liu. IEEE CoG, 2022, Oral.
  5. Independence-aware Advantage Estimation [Paper]
    Pushi Zhang, Li Zhao, Guoqing Liu, Jiang Bian, Minlie Huang, Tao Qin, Tie-Yan Liu. IJCAI, 2021.
  6. Demonstration Actor Critic [Paper]
    Guoqing Liu, Li Zhao, Pushi Zhang, Jiang Bian, Tao Qin, Nenghai Yu, Tie-Yan Liu. Neurocomputing, 2021.
  7. Return-based Contrastive Representation Learning for Reinforcement Learning [Paper]
    Guoqing Liu*, Chuheng Zhang*, Li Zhao, Tao Qin, Jinhua Zhu, Jian Li, Nenghai Yu, Tie-Yan Liu. ICLR, 2021.
  8. Suphx: Mastering Mahjong with Deep Reinforcement Learning [Paper] [News]
    Junjie Li, Sotetsu Koyamada, Qiwei Ye, Guoqing Liu, Chao Wang, Ruihan Yang, Li Zhao, Tao Qin, Tie-Yan Liu, Hsiao-Wuen Hon. arXiv, 2020.
  9. Trust Region Evolution Strategies [Paper]
    Guoqing Liu, Li Zhao, Feidiao Yang, Jiang Bian, Tao Qin, Nenghai Yu, Tie-Yan Liu. AAAI, 2019.
Mentorship
Education
Professional Activities
Honors and Awards