Yibo He

Member of Technical Staff · RL Team @ Moonshot AI (Kimi)
Ph.D. student · School of Computer Science @ Peking University

I am a Member of Technical Staff at Moonshot AI (Kimi) and a Ph.D. student in Computer Science at Peking University, advised by Prof. Tao Xie. Prior to my Ph.D., I received my B.Sc. in Computer Science, also from Peking University. My current work focuses on post-training LLMs for coding agents, targeting challenging, long-horizon agentic tasks in real-world software engineering. This involves RL environments, synthetic data generation, trajectory filtering, SFT/RL, and evaluation across diverse coding domains. My research also spans compiler fuzzing, benchmarking code LLMs, and test generation.