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 (RL), large language model (LLM) post-training, and AI co-scientists for chemistry and drug discovery. His representative works include QFANG, PDVN, RetroChimera, and TDPO. Previously, he was a Senior Researcher at Microsoft Research Asia, where he worked on deep reinforcement learning and real-world AI systems, including Suphx, a Mahjong AI, and Inspector, an AI game-testing system developed with Xbox Game Studios. 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 (2022-2026)

  1. Token-Importance Guided Direct Preference Optimization (TDPO-v2) [Paper]
    Ning Yang, Hai Lin, Yibo Liu, Baoliang Tian, Guoqing Liu, Haijun Zhang
    Fourteenth International Conference on Learning Representations (ICLR 2026 Oral)
  2. 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.
  3. Chemist-aligned retrosynthesis by ensembling diverse inductive bias models (RetroChimera) [Paper][News]
    Krzysztof Maziarz*, Guoqing Liu*, Hubert Misztela, Austin Tripp, Junren Li, Aleksei Kornev, Piotr Gaiński, Holger Hoefling, Mike Fortunato, Rishi Gupta, 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 (NMI 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 2025 Workshop on Machine Learning for Genomics Explorations (ICLR 2025-W)
  7. Token-level Direct Preference Optimization (TDPO) [Paper]
    Yongcheng Zeng, Guoqing Liu, Weiyu Ma, Ning Yang, Haifeng Zhang, Jun Wang
    Forty-first International Conference on Machine Learning (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
    Twelfth International Conference on Learning Representations (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
    Thirty-seventh Conference on Neural Information Processing Systems (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
    Fortieth International Conference on Machine Learning (ICML 2023)

(Deep) Reinforcement Learning, Game Intelligence (2016-2022)

  1. Proactive Constrained Policy Optimization with Preemptive Penalty [Paper]
    Ning Yang, Pengyu Wang, Guoqing Liu, Haifeng Zhang, Pin Lv, Jun Wang
    The Fortieth AAAI Conference on Artificial Intelligence (AAAI 2026)
  2. Reinforcement Learning from Bagged Reward [Paper]
    Yuting Tang, Xin-Qiang Cai, Yao-Xiang Ding, Qiyu Wu, Guoqing Liu, Masashi Sugiyama
    Transactions on Machine Learning Research (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 Conference on Games 2022 (COG 2022, Oral)
  5. Independence-aware Advantage Estimation [Paper]
    Pushi Zhang, Li Zhao, Guoqing Liu, Jiang Bian, Minlie Huang, Tao Qin, Tie-Yan Liu
    30th International Joint Conference on Artificial Intelligence (IJCAI 2021)
  6. Demonstration Actor Critic [Paper]
    Guoqing Liu, Li Zhao, Pushi Zhang, Jiang Bian, Tao Qin, Nenghai Yu, Tie- Yan Liu
    Neurocomputing, Volume 434, 28 April 2021, Pages 194-202 (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
    Ninth International Conference on Learning Representations (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
    Thirty-Third AAAI Conference on Artificial Intelligence (AAAI 2019)
Mentorship
Education
Professional Activities
Honors and Awards