About Me
Currently, I am a second-year graduate student of School of Artificial Intelligence in Nanjing University advised by Professor Yu-Feng Li and a member of LAMDA Group, led by professor Zhi-Hua Zhou.
I got my B.Sc. degree in Department of Computer Science and Technology in June 2023 from Nanjing University. In the same year, I was admitted to pursue a Ph.D. degree in Nanjing University without entrance examination.
Research Interests
My research interests include Machine Learning and Artificial General Intelligence (AGI). Currently, I am focusing on the subfields:
- AI4Math: applying AI techniques to mathematical problem solving and research.
- Reasoning in LLMs: improving the reasoning capability of large language models.
- Neural Symbolic Learning: integrating the power of machine learning and logical reasoning to boost the reasoning and planning capabilities of the AI system.
News
- 🎉 [Jan 2025] CARTS is accepted by ICLR2025.
- 🎉 [May 2025] A survey about Neuro-Symbolic Reasoning of LLMs is accepted by IJCAI 2025 Survey Track.
- 🎉 [Nov 2025] Self-Backtracking is accepted by AAAI2026.
- 🎉 [Jan 2026] FormalML and ChinaTravel benchmark is accepted by ICLR2026.
Publication
(* denotes the co-first authors)
Conference Papers
FormalML: A Benchmark for Evaluating Formal Subgoal Completion in Machine Learning Theory. [PDF]
Xiao-Wen Yang*, Zihao Zhang*, Jianuo Cao, Zhi Zhou, Zenan Li, Lan-Zhe Guo, Yuan Yao, Taolue Chen, Yu-Feng Li†, Xiaoxing Ma†.
The 14th International Conference on Learning Representations (ICLR 2026).Step Back to Leap Forward: Self-Backtracking for Symbolic Reasoning and Planning in Language Models. [PDF] [Webpage]
Xiao-Wen Yang, Xuan-Yi Zhu, Ding-Chu Zhang, Wen-Da Wei, Jie-Jing Shao, Zhi Zhou, Lan-Zhe Guo, Yu-Feng Li.
The 40th AAAI Conference on Artificial Intelligence (AAAI 2026).Neuro-Symbolic Artificial Intelligence: Towards Improving the Reasoning Abilities of Large Language Models. [PDF]
Xiao-Wen Yang*, Jie-Jing Shao*, Lan-Zhe Guo*, Bo-Wen Zhang, Zhi Zhou, Lin-Han Jia, Wang-Zhou Dai, Yu-Feng Li.
The 34th International Joint Conference on Artificial Intelligence (IJCAI 2025 Survey Track).CARTS: Advancing Neural Theorem Proving with Diversified Tactic Calibration and Bias-Resistant Tree Search. [PDF] [Webpage]
Xiao-Wen Yang, Zhi Zhou, Haiming Wang, Aoxue Li, Wen-Da Wei, Hui Jin, Zhenguo Li, Yu-Feng Li.
The 13th International Conference on Learning Representations (ICLR 2025).Analysis for Abductive Learning and Neural-Symbolic Reasoning Shortcuts. [PDF] [Webpage]
Xiao-Wen Yang, Wen-Da Wei, Jie-Jing Shao, Yu-Feng Li, Zhi-Hua Zhou.
The 41st International Conference on Machine Learning (ICML 2024).Safe Abductive Learning in the Presence of Inaccurate Rules. [PDF]
Xiao-Wen Yang, Jie-Jing Shao, Wei-Wei Tu, Yu-Feng Li, Wang-Zhou Dai, Zhi-Hua Zhou.
The 38th AAAI Conference on Artificial Intelligence (AAAI 2024).AutoEvolve: Automatically Evolving Queries for Applicable and Scalable Retrieval-Augmented Generation Benchmarking.
Dingchu Zhang, Xiaowen Zhang, Yue Fei, Renjun Hu, Xiaowen Yang, Zhi Zhou, Baixuan Li, Yufeng Li, Xing Shi, Wei Lin.
The 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP 2025).Curriculum Abductive Learning for Mitigating Reasoning Shortcuts.
Wen-Da Wei, Xiao-Wen Yang, Jie-Jing Shao and Lan-Zhe Guo.
The 34th International Joint Conference on Artificial Intelligence (IJCAI 2025).D3: Diversity, Difficulty, and Dependability-Aware Data Selection for Sample-Efficient LLM Instruction Tuning
Jia Zhang, Chen-Xi Zhang, Yao Liu, Yi-Xuan Jin, Xiao-Wen Yang, Bo Zheng, Yi Liu and Lan-Zhe Guo.
The 34th International Joint Conference on Artificial Intelligence (IJCAI 2025).Abductive Learning for Neuro-Symbolic Grounded Imitation. [PDF] [Webpage]
Jie-Jing Shao*, Hao-Ran Hao*, Xiao-Wen Yang, Yu-Feng Li.
The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD’25).LOG: Active Model Adaptation for Label-Efficient OOD Generalization. [PDF]
Jie-Jing Shao, Lan-Zhe Guo, Xiao-Wen Yang, Yu-Feng Li.
The 36th Conference on Neural Information Processing Systems (NeurIPS 2022).
Journal Papers
- Open-Set Learning under Covariate Shift. [PDF]
Jie-Jing Shao*, Xiao-Wen Yang*, Lan-Zhe Guo.
Machine Learning (ML’22).
Other Papers
Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training. [PDF]
Hong-Jie You, Jie-Jing Shao, Xiao-Wen Yang, Lin-Han Jia, Lan-Zhe Guo, Yu-Feng Li.
Preprint, 2025.LawGPT: Knowledge-Guided Data Generation and Its Application to Legal LLM. [PDF]
Zhi Zhou, Kun-Yang Yu, Shi-Yu Tian, Xiao-Wen Yang, Jiang-Xin Shi, Peng-Xiao Song, Yi-Xuan Jin, Lan-Zhe Guo, Yu-Feng Li.
Preprint, 2025.ChinaTravel: A Real-World Benchmark for Language Agent in Chinese Travel Planning. [PDF] [Webpage]
Jie-Jing Shao*, Bo-Wen Zhang*, Xiao-Wen Yang*, Bai-Zhi Chen,
Wen-Da Wei, Guohao Cai, Zhenhua Dong, Lan-Zhe Guo, Yu-Feng Li.
Preprint, 2024.Investigating the Limitation of CLIP Models: The Worst-Performing Categories. [PDF]
Jie-Jing Shao*, Jiang-Xin Shi*, Xiao-Wen Yang*, Lan-Zhe Guo, Yu-Feng Li.
Preprint, 2023.Lightweight Retrieval Tuning for Black-Box Language Models. [PDF]
Xiao-Wen Yang, Hong-Jie You, Peng-Xiao Song, Hao-Ran Hao, Jie-Jing Shao, Yu-Feng Li.
NeurIPS’23 ENSLP Workshop.
Software
- LawGPT: A Large Language Model in the Legal Domain. [GitHub]
Honor
- National Scholarship, Nanjing University, Oct 2024
- Outstanding Student, Nanjing University, Nov 2024
- President’s Scholarship, Nanjing University, Oct 2023
- Outstanding Graduate, Nanjing University, Jun 2023
Academic Service
Reviewer for:
- AAAI 2024, 2025, 2026
- ICLR 2024, 2025, 2026
- ICML 2024, 2025, 2026
- NeurIPS 2023, 2024, 2025
Meta Reviewer for IJCAI 2025