Tianhao Wu

I’m a 3rd-year Ph.D. student advised by Jiantao Jiao and Kannan Ramchandran at UC Berkeley. During my undergrad, I worked with Liwei Wang and majored in Mathematics

My research focuses on improving LLMs’ instruction following and reasoning capabilities via (Self-Play) RL. My ambition is to construct large-scale models that can solve complex tasks requiring multi-step reasoning.

I’m also working on AI Society, a group of agents that can link together in a modular fashion to form a more capable collective intelligence. This decentralized paradigm could mitigate the computing demands that limit centralized AI systems today.