Liaoyaqi Wang

I am a PhD student in Computer Science at the University of Texas at Austin, advised by Prof. Elias Stengel-Eskin. Before that, I completed my M.S. at Johns Hopkins University, where I was fortunate to work with Prof. Anqi Liu and Prof. Benjamin Van Durme on calibrated and trustworthy reasoning in large language models.

My research centers on uncertainty quantification and reasoning in LLMs, and I’m currently interested in multi-agent systems — particularly how to calibrate agents’ confidence and enable them to communicate and collaborate more effectively.

Feel free to reach out if you’d like to chat about calibration, LLM reasoning, or multi-agent systems.