Yuxiao Qu

Yuxiao Qu is a PhD student in the Machine Learning Department at Carnegie Mellon University, advised by Prof. Aviral Kumar and Prof. Ruslan Salakhutdinov, and a part-time student researcher at NVIDIA Research. He is an Amazon AI Ph.D. Fellow whose research focuses on the intersection of reinforcement learning and foundation models for reasoning and agentic tasks. He is best known for developing Recursive Introspection (RISE), a method for teaching language model agents to self-improve through iterative internal feedback, and Meta Reinforcement Fine-Tuning (MRT) for optimizing test-time compute in LLMs.