I am a Ph.D. student in Computer Science and Technology at Southeast University, advised by Prof. Lei Feng. Previously, I received master’s degrees from Southeast University and Monash University through a double-degree program, with Prof. Guilin Qi as my advisor. I received my bachelor’s degree in Computer Science and Technology from Hefei University of Technology in June 2021.
My research interests include:
- Fine-tuning and reinforcement learning for LLMs
- LLM-based autonomous agent architectures
- Multi-agent collaboration
🔥 News
- 2026.09: 🎉 Our papers CITA and PhGPO were accepted to NeurIPS 2026 (Poster)!
- 2026.04: 🎉 Our paper was accepted to ICML 2026 (Poster)!
- 2025.11: 🎉 Our paper C³TG was accepted to AAAI 2026 (Poster)!
- 2025.01: 🎉 Our paper MAKGED was accepted to DASFAA 2025 (Oral)!
- 2024.12: 🎉 Our paper was accepted to AAAI 2025 (Poster)!
- 2024.03: 🎉 Our paper MATEval was accepted to DASFAA 2024 (Oral)!
- 2024.03: 🎉 Our paper DEE was accepted to DASFAA 2024 (Oral)!
- 2024.01: 🎉 Our paper was accepted to NAACL 2024!
📝 Publications
Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents (NeurIPS 2026, Poster)
Yu Li, Zheng Zhang, Xin Liu, Shengtian Yang, Guangfeng Cai, Lei Feng
PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning (NeurIPS 2026, Poster)
Yu Li, Guangfeng Cai, Shengtian Yang, Han Luo, Shuo Han, Xu He, Dong Li, Lei Feng
- Phase-Aware Mixture of Experts for Agentic Reinforcement Learning (ICML 2026, Poster)
Shengtian Yang, Yu Li, Shuo He, Yewen Li, Qingpeng Cai, Peng Jiang, Lei Feng
C³TG: Conflict-aware, Composite, and Collaborative Controlled Text Generation (AAAI 2026, Poster)
Yu Li, Zhe Yang, Yi Huang, Xin Liu, Guilin Qi
MATEval: A Multi-Agent Discussion Framework for Advancing Open-Ended Text Evaluation (DASFAA 2024, Oral)
Yu Li*, Shenyu Zhang*, Rui Wu, Xiutian Huang, Wenhao Xu, Guilin Qi, Dehai Min
-
Harnessing Diverse Perspectives: A Multi-Agent Framework for Enhanced Error Detection in Knowledge Graphs (DASFAA 2025, Oral)
Yu Li, Yi Huang, Guilin Qi, Junlan Feng, Nan Hu, Songlin Zhai, Haohan Xue, Yongrui Chen, Ruoyan Shen, Tongtong Wu
-
DEE: Dual-Stage Explainable Evaluation Method for Text Generation (DASFAA 2024, Oral)
Shenyu Zhang*, Yu Li*, Rui Wu, Xiutian Huang, Yongrui Chen, Wenhao Xu, Guilin Qi -
Hegta: Leveraging heterogeneous graph-enhanced large language models for few-shot complex table understanding (AAAI 2025)
Rihui Jin, Yu Li, Guilin Qi, Nan Hu, Yuan-Fang Li, Jiaoyan Chen, Jianan Wang, Yongrui Chen, Dehai Min, Sheng Bi -
Can ChatGPT replace traditional KBQA models? An in-depth analysis of the question answering performance of the GPT LLM family (ISWC 2023, Oral)
Yiming Tan, Dehai Min, Yu Li, Wenbo Li, Nan Hu, Yongrui Chen, Guilin Qi
Code -
Exploring the impact of table-to-text methods on augmenting LLM-based question answering with domain hybrid data (NAACL 2024, Oral)
Dehai Min, Nan Hu, Rihui Jin, Nuo Lin, Jiaoyan Chen, Yongrui Chen, Yu Li, Guilin Qi, Yun Li, Nijun Li, Qianren Wang
🎖 Honors and Awards
- 2025.06: Outstanding Graduate, Southeast University.
- 2024.10: First-Class Scholarship, Southeast University.
📖 Education
- 2025.09 – Present: Ph.D. in Computer Science and Engineering, Southeast University.
- 2022.09 – 2025.06: M.S. in Computer Science and Engineering (double-degree program), Southeast University and Monash University.
- 2017.09 – 2021.06: B.S. in Computer Science and Technology, Hefei University of Technology.
💻 Internships
- 2026.09 – Present: LLM Algorithm Intern, Large Language Model Algorithm Lab, Huawei 2012 Labs, Shanghai, China.
- 2026.03 – 2026.08: LLM Algorithm Intern, Tencent, Shenzhen, China.
- 2023.09 – 2024.03: Ant Group, Hangzhou, China.