Jiongxiao Wang

I am a fourth-year PhD student at the Information School, University of Wisconsin–Madison, where I’m fortunately advised by Professor Chaoqun Ni. I got my bachelor degree at School of Mathematical Sciences, Fudan University in June 2022.

My research centers on AI safety and Reinforcement Learning for AI Agents. I am dedicated to designing methods that better evaluate and safeguard AI systems against unexpected vulnerabilities. Concurrently, I explore using RL to push the boundaries of agentic capabilities, with a distinct focus on self-improving AI agents.

I am actively looking for new grad job opportunities for Fall 2027. If you are interested in my work or want to chat about trustworthy, agentic AI, I would love to connect!