教师简介:
刘咏梅，中山大学计算机学院教授，博士生导师。于加拿大多伦多大学计算机科学系获博士学位。研究方向为人工智能，知识表示与推理，自然语言处理，智能规划。于国际人工智能会议IJCAI, AAAI，ECAI，ACL，和EMNLP上发表学术论文40余篇。主持国家自然科学基金面上项目多项。长期担任国际人工智能会议IJCAI，AAAI，ECAI，ICAPS，AAMAS，KR等的程序委员会委员。
招生信息：
本研究组致力于探索神经符号人工智能，将经典的符号逻辑、形式化方法与前沿的大语言模型、强化学习技术相结合，构建具备深度推理、自主规划和可信决策能力的下一代智能体。目前，本研究组围绕四个前沿方向开展研究。欢迎感兴趣的同学加入我们！
1.自然语言上的综合逻辑推理：逻辑推理是人类智能的基石。虽然大语言模型在自然语言处理上表现出色，但在复杂推理任务上仍存在局限。我们的研究将经典知识表示与推理理论（如演绎推理、缺省推理、信念推理）与最新的大语言模型技术相结合，提升机器对自然语言的深度理解与综合推理能力。
2.通用规划和认知规划：规划能力是智能的核心，无论是制定旅行路线还是完成复杂任务。我们研究自动规划：其中通用规划旨在为一类相似的规划问题生成通解，让机器具备“举一反三”的泛化能力；认知规划则重点关注如何通过执行具有认知前提和效果的动作，来实现认知目标。
3.多智能体系统的形式化研究：当多个智能体（如机器人、软件程序）共同存在时，它们如何高效地协作或博弈？我们研究多智能体系统的行为规律。运用逻辑、博弈论等形式化方法，严格刻画智能体的知识、信念、意图、协作与策略行为，并进行严谨的推理和验证，为设计更可靠的分布式智能系统提供理论支撑。
4. 逻辑规范引导的强化学习：在自动驾驶、医疗诊断等安全攸关场景中，智能体的行为必须满足严格的安全约束。我们研究基于形式化逻辑规范（如线性时序逻辑LTL）的强化学习，让智能体在与环境交互的过程中，不仅追求最大化累积奖励，还要确保行为始终符合逻辑约束，为实现可信、可解释的强化学习奠定基础。
研究领域:
人工智能，知识表示与推理，自然语言处理，智能规划
教育背景:
多伦多大学计算机科学硕士，博士，武汉大学计算机科学学士
工作经历:
2007年12月至今，中山大学，教授，博士生导师
海外经历:
访问教授: 荷兰阿姆斯特丹大学，意大利罗马大学，法国图卢兹大学，德国亚琛工业大学，澳洲新南威尔士大学
科研项目:
1. 国家自然科学基金项目， 基于逻辑程序设计的自然语言上的综合逻辑推理的神经符号方法
2. 国家自然科学基金项目， 通用规划的理论基础及有效求解方法研究
3. 国家自然科学基金项目， 多智能体动作推理及高级控制的理论与技术研究
4. 国家自然科学基金项目， 情景演算中的关键推理技术及其应用研究
教授课程:
研究生课程：数理逻辑，知识表示与推理
本科生课程：离散数学，人工智能，数理逻辑
代表性论著:
DBLP链接：https://dblp.org/pid/73/4188-1.html
• Ruiqi Jin, Shuyi Li, Yongmei Liu: Enhancing Strategy Logic with Procedural Rationality. In Proceedings of the 40th AAAI Conference on Artificial Intelligence (AAAI-26), 2026
• Yeliang Xiu, Yongmei Liu: MultiLogicNMR(er): A Benchmark and Neural-Symbolic Framework for Non-monotonic Reasoning with Multiple Extensions. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025), 2025
• Ruikang Hu, Shaoyu Lin, Yeliang Xiu, Yongmei Liu. LTRAG: Enhancing autoformalization and self-refinement for logical reasoning with Thought-Guided RAG. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Findings) (ACL-2025), 2025
• Zheyuan Shi, Hao Dong, Yongmei Liu: Solving QNP and FOND+ with Generating, Testing and Forbidding. In Proceedings of the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025), 2025
• Hao Dong, Zheyuan Shi, Hemeng Zeng, Yongmei Liu: An Automatic Sound and Complete Abstraction Method for Generalized Planning with Baggable Types. In Proceedings of the Thirty-Ninthth AAAI Conference on Artificial Intelligence (AAAI-25), 2025
• Ruiqi Jin, Yongmei Liu, Liping Xiong: A Modal Logic for Joint Abilities of Structured Strategies with Bounded Complexity. In Proceedings of the Thirty-Ninthth AAAI Conference on Artificial Intelligence (AAAI-25), 2025
• Weinan He, Canming Huang, Zhanhao Xiao, Yongmei Liu: Exploring the Capacity of Pretrained Language Models for Reasoning about Actions and Change. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023), 2023
• Zhenhe Cui, Weidu Kuang, Yongmei Liu: Automatic Verification for Soundness of Bounded QNP Abstractions for Generalized Planning. In Proceedings of the 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023), 2023
• Aiting Liang, Yongmei Liu: A Model-Theoretic Approach to Belief Revision in Multi-Agent Belief Logic and Its Syntactic Characterizations. In Proceedings of the 26th European Conference on Artificial Intelligence (ECAI 2023), 2023
• Zhaoshuai Liu, Aiting Liang, Yongmei Liu: Epistemic JAADL: A Modal Logic for Joint Abilities with Imperfect Information. In Proceedings of the 26th European Conference on Artificial Intelligence, (ECAI 2023), 2023
• H. Zeng, Y. Liang ad Y. Liu. A Native Qualitative Numeric Planning Solver Based on AND/OR Graph Search. In Proceedings of the Thirty-first International Joint Conference on Artificial Intelligence (IJCAI-22), 2022.
• S. Ou and Y. Liu. Learning to Generate Programs for Table Fact Verification via Structure-Aware Semantic Parsing. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (ACL-2022), 2022
• Y. Xiu, Z. Xiao and Y. Liu. LogicNMR: Probing the Non-monotonic Reasoning Ability of Pre-trained Language Models. In Proceedings of The 2022 Conference on Empirical Methods in Natural Language Processing (Findings) (EMNLP-2022), 2022
• K. Luo and Y. Liu. Automated Synthesis of Generalized Invariant Strategies via Counterexample-Guided Strategy Refinement. In Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22), 2022.
• W. He, C. Huang, Y. Liu and X. Zhu. WINOLOGIC: A Zero-Shot Logic-based Diagnostic Dataset for Winograd Schema Challenge. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing(EMNLP-2021), 2021
• C. Huang, W. He and Y. Liu. Improving Unsupervised Commonsense Reasoning Using Knowledge-Enabled Natural Language Inference. In Proceedings of The 2021 Conference on Empirical Methods in Natural Language Processing (Findings) (EMNLP-2021), 2021
• H. Wan, B. Fang and Y. Liu. A General Multi-agent Epistemic Planner Based on Higher-order Belief Change. Artificial Intelligence 301 (2021) 103562.
• Z. Cui, Y. Liu and K. Luo. A Uniform Abstraction Framework for Generalized Planning. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21), 2021.
• Z. Liu, L. Xiong, Y. Liu, Y. Lespérance, R. Xu and H. Shi. A Modal Logic for Joint Abilities under Strategy Commitments. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence (IJCAI-20), 2020.
• K. Luo, Y. Liu, Y. Lespérance, and Z. Lin. Agent Abstraction via Forgetting in the Situation Calculus. In Proceedings of the Twenty-Fourth European Conference on Artificial Intelligence (ECAI-20), 2020.
• J. Li and Y. Liu. Automatic Verification of Liveness Properties in the Situation Calculus. In Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), 2020.
• K. Luo and Y. Liu. Automatic Verification of FSA Strategies via Counterexample-Guided Local Search for Invariants. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19), 2019.
• L. Fang, Y. Liu and H. van Ditmarsch. Forgetting in multi-agent modal logics. Artificial Intelligence, 266: 51-80, 2019.
• Q. Liu and Y. Liu. Multi-agent Epistemic Planning with Common Knowledge. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI-18), 2018.
• X. Huang, B. Fang, H. Wan and Y. Liu. A General Multi-agent Epistemic Planner Based on Higher-order Belief Change. In Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (IJCAI-17), 2017.
• P. Mo, N. Li and Y. Liu. Automatic Verification of Golog Programs via Predicate Abstraction. In Proceedings of the Twenty-Second European Conference on Artificial Intelligence (ECAI-16), 2016.
• L. Xiong and Y. Liu. Strategy Representation and Reasoning in the Situation Calculus. In Proceedings of the Twenty-Second European Conference on Artificial Intelligence (ECAI-16), 2016.
• L. Xiong and Y. Liu. Strategy Representation and Reasoning for Incomplete Information Concurrent Games in the Situation Calculus. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16), 2016.
• L. Fang, Y. Liu and H. van Ditmarsch. Forgetting in Multi-Agent Modal Logics. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-16), 2016.
• H. Wan, R. Yang, L. Fang, Y. Liu and H. Xu. A Complete Epistemic Planner without the Epistemic Closed World Assumption. In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-15), 2015.
• L. Fang, Y. Liu and X. Wen. On the Progression of Knowledge and Belief for Nondeterministic Actions in the Situation Calculus. In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-15), 2015.
• N. Li and Y. Liu. Automatic Verification of Partial Correctness of Golog Programs. In Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-15), 2015.
• X. Wang and Y. Liu. Automated fault localization via hierarchical multiple predicate switching. Journal of Systems and Software, 104:69-81, 2015.
