CV
Download my CV (PDF) (Transcripts)
Education
- Ph.D. in Computer Science, University of Waterloo, advised by Professor Victor Zhong, 09.2025 - Now (expected 06.2028)
- M.S. in Computer Science and Technology, Nanjing University, advised by Professor Yuzhong Qu, 09.2021 - 06.2024
- B.E. in Software Engineering, University of Electronic Science and Technology of China, advised by Professor Yi Ding, GPA 3.98 / 4.00 (Top 3), 09.2017 - 06.2021
Work experience
- 08.2026 - Now : Research Intern
- Samaya AI, Mountain View, USA
- Advisor: Yuhao Zhang
- 09.2025 - Now : Ph.D. student
- R2L Lab, University of Waterloo
- Supervisor: Professor Victor Zhong
- 07.2024 - 06.2025 : Visiting Research Scholar
- NLP Group, University of California, Santa Barbara
- Supervisor: Professor William Wang
- 10.2023 - 06.2024 : Research Intern and Mentor of Junior Interns
- DKI (Data, Knowledge, Intelligence) Group, Microsoft Research Asia
- Advisors: Yong Xu, Fangkai Yang, Chaoyun Zhang
- 06.2023 - 09.2023 : Research Intern
- Data Management Intelligence Department, Ant Group
- 09.2021 - 06.2024 : Student Researcher
- Websoft Lab, Nanjing University
- Supervisor: Professor Yuzhong Qu
Preprints
- X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization
Sitao Cheng, Xunjian Yin, Zhiyuan Sun, Yuxuan Li, Ruiwen Zhou, Xiangru Jian, Victor Zhong
[paper] [homepage]
Publications
From Atomic to Composite: Reinforcement Learning Enables Generalization in Complementary Reasoning
Sitao Cheng, Xunjian Yin, Ruiwen Zhou, Yuxuan Li, Xinyi Wang, Liangming Pan, William Yang Wang, Victor Zhong
[paper] [code] [data] [homepage]Dual-Evolving Reinforcement Learning for Automated Reward Design
Sitao Cheng*, Tianle Li*, Xuhan Huang*, Xunjian Yin, Difan Zou
[paper] [code] [model] [homepage]Understanding the Interplay between Parametric and Contextual Knowledge for Large Language Models
Sitao Cheng, Liangming Pan, Xunjian Yin, Xinyi Wang, William Yang Wang
[paper] [code] [homepage]Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments
Sitao Cheng, Ziyuan Zhuang, Yong Xu, Fangkai Yang, Chaoyun Zhang, Xiaoting Qin, Xiang Huang, Ling Chen, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang
[paper] [code]QueryAgent: A Reliable and Efficient Reasoning Framework with Environmental Feedback based Self-Correction
Xiang Huang*, Sitao Cheng*, Shanshan Huang, Jiayu Shen, Yong Xu, Chaoyun Zhang, Yuzhong Qu
[paper] [code]LEDOM: Reverse Language Model
Xunjian Yin, Sitao Cheng, Yuxi Xie, Xinyu Hu, Li Lin, Xinyi Wang, Liangming Pan, William Yang Wang, Xiaojun Wan
[paper] [code] [model]Dynamic Evaluation for Oversensitivity in LLMs
Sophia Xiao Pu, Sitao Cheng, Xin Eric Wang, William Yang Wang
[paper] [data]EfficientRAG: Efficient Retriever for Multi-Hop Question Answering
Ziyuan Zhuang*, Zhiyang Zhang*, Sitao Cheng, Fangkai Yang, Jia Liu, Shujian Huang, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang
[paper] [code]MarkQA: A Large Scale KBQA Dataset with Numerical Reasoning
Xiang Huang, Sitao Cheng, Yuheng Bao, Shanshan Huang, Yuzhong Qu
[paper] [code] [homepage]Disentangling Memory and Reasoning Ability in Large Language Models
Mingyu Jin, Weidi Luo, Sitao Cheng, Xinyi Wang, Wenyue Hua, Ruixiang Tang, William Yang Wang, Yongfeng Zhang
[paper] [code]RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios
Ruiwen Zhou, Wenyue Hua, Liangming Pan, Sitao Cheng, Xiaobao Wu, En Yu, William Yang Wang
[paper] [code]Question Decomposition Tree for Answering Complex Questions over Knowledge Bases
Xiang Huang, Sitao Cheng, Yiheng Shu, Yuheng Bao, Yuzhong Qu
[paper] [code]TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Data
Xiang Huang*, Jiayu Shen*, Shanshan Huang, Sitao Cheng, Xiaxia Wang, Yuzhong Qu
[paper]Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation
Kaikai An, Fangkai Yang, Liqun Li, Junting Lu, Sitao Cheng, Shuzheng Si, Lu Wang, Pu Zhao, Lele Cao, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, Qi Zhang, Baobao Chang
[paper]
* equal contribution
Honors and Awards
- Layer 6 - TD Graduate Scholarship in Data & AI, University of Waterloo, Fall 2025
- MCM/ICM H Prize
- Outstanding Graduating Student, Nanjing University, 2024
- Outstanding Graduating Student of Sichuan Province, 2021
- Outstanding Graduating Student, UESTC, 2021
Services
- ICML 2026 Silver Reviewer
- ACL 2024 Volunteer
- ARR, ICLR, NeurIPS Reviewer