Curriculum Vitae
I am a Ph.D. student at the School of Information Science and Technology, University of Science and Technology of China (USTC). My research focuses on LLM post-training, agents, reinforcement learning, and world models.
Education
- Ph.D., School of Information Science and Technology, University of Science and Technology of China, 2026 - 2029 (Expected)
- M.S., School of Information Science and Technology, University of Science and Technology of China, 2024 - 2026
- B.S., School of the Gifted Young, University of Science and Technology of China, 2020 - 2024
Research Experience
-
Tencent Hunyuan, Qingyun Program Intern, May 2026 – Present -
Shanghai AI Laboratory, Research Intern, Sept. 2025 – Apr. 2026 -
Noah's Ark Lab, Huawei, Research Collaboration, Dec. 2024 – Aug. 2025 -
Alibaba Cloud, Research Intern, May 2024 – Aug. 2024
Selected Publications
- Runquan Gui, Hanzhu Chen, Zehao Wang, Hanxin Zhu, Xin Li, Zhibo Chen†. VAMR: Multi-Question Agentic Reasoning for Efficient Long-Form Video Understanding. [Paper]
- Haoran Zhang*, Luxin Xu*, Zhilin Wang*, Runquan Gui*, Shunkai Zhang, Haodi Lei, Zihao He, Bingsu He, Chicheng Qin, Tong Zhu, Xiaoye Qu, Yang Yang†, Yu Cheng†, Yafu Li†. Pi-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows. NeurIPS 2026. [Website][Paper][Code]
- Runquan Gui, Yafu Li†, Xiaoye Qu, Ziyan Liu, Yeqiu Chen, Yu Cheng. Learning to Reason Faithfully through Step-Level Faithfulness Maximization. EMNLP 2026. [Paper][Code]
- Runquan Gui, Jie Wang†, Zhihai Wang, Chi Ma, Jianye Hao, Feng Wu. Short Chains, Deep Thoughts: Balancing Reasoning Efficiency and Intra-Segment Capability via Split-Merge Optimization. ICML 2026. [Paper][Code]
- Yeqiu Chen, Ziyan Liu, Zhenxin Huang, Runquan Gui, Hong Wang, Lei Liu†. ArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM Reasoning. ICML 2026. [Paper]
- Runquan Gui, Zhihai Wang, Jie Wang†, Chi Ma, Huiling Zhen, Mingxuan Yuan, Jianye Hao, Defu Lian, Enhong Chen, Feng Wu. HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking. ICML 2025. [Paper][Code]
* denotes equal contribution. † denotes corresponding author.
Honors and Awards
- "Qiangwei" Scholarship, 2021 & 2023
- Outstanding Student Scholarship, 2021 & 2022 & 2023