EvoThink: Evolving Thinking in Large Reasoning Models via Self-Pruning and Aha-Moment Preference Optimization
Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-ECAI), 2026
* Equal contribution.
Paper ↗About
I studied at the School of Artificial Intelligence, Southeast University (2022–2026). I am an M.S. student at the School of Computer Science and Technology, Huazhong University of Science and Technology (Sep. 2026–), advised by Prof. Rui Zhang.
I was an Algorithm Intern at 4Paradigm from Nov. 2025 to May 2026, working on RAG and intelligent question answering.
My research interests include AI Agents, Multimodal Learning, and Retrieval-Augmented Generation (RAG).
Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models
arXiv preprint arXiv:2506.06137, 2025
Paper ↗Recent Updates
- 2026-09M.S. study at the School of Computer Science and Technology, Huazhong University of Science and Technology, advised by Prof. Rui Zhang.
- 2026-05Completed my algorithm internship at 4Paradigm.
- 2026-04EvoThink was accepted to IJCAI-ECAI 2026.
- 2025-06Released Table-r1, a study of program-based table reasoning in small language models.
- 2024-12Received the Zhishan Student Scholarship at Southeast University.