Yuxuan Li 李宇轩

I'm a second-year PhD student in the Human-Computer Interaction Institute (HCII) within Carnegie Mellon University (CMU)'s School of Computer Science, advised by Hirokazu Shirado and Sauvik Das.

As humans increasingly delegate social agency to AI, social intelligence becomes essential to useful and trustworthy agents. My research asks how we can build socially intelligent agents for the world ahead—and use agent societies today to understand and improve the human world.

I pursue this agenda through two lenses:

Build for an agent-native future: Evaluating and improving the social intelligence of AI agents
EMNLP'25 Oral FAccT'25 ICML'26 Submission
Use that future today: Using multi-agent simulations to model social dynamics and inform real-world practice
TOCHI Submission UIST'26 Submission USENIX Security'26 Submission PoliSim@CHI'26

I hold a BS in Computer Science from Tsinghua University, advised by Chun Yu and Yuanchun Shi. I was also a research intern at UC Berkeley, advised by Coye Cheshire. My research has received extensive media coverage and led to invited talks at institutions such as CMU, Georgia Tech, Tsinghua, HKU and Microsoft.

Yuxuan Li profile photo

I will be joining Microsoft Research AI Frontiers this summer as a Research Intern, working on social reasoning in LLM agents.