I am a Ph.D. student in Computer Science at the University of Houston, advised by Prof. Feng Yan. I received my M.S. in Computer Science from Georgia Tech and my B.Eng. from the University of Electronic Science and Technology of China (UESTC).

My research focuses on LLM agents for complex tasks in data science and software engineering. I study how agents learn through reinforcement learning, use tools effectively, and follow instructions throughout multi-step workflows.

My recent work spans training long-horizon coding agents, building data-science agents that adapt their workflows to task characteristics, and developing benchmarks for modeling performance and instruction fidelity. Across these projects, I aim to connect agent training, system design, and evaluation to make agents more capable and reliable in practice.

Feel free to reach out if you are interested in collaboration.