I recently defended my PhD at the Language Technologies Institute at CMU, where I was advised by Maarten Sap, and received a Microsoft PhD Fellowship.

I am interested in socially intelligent AI. More specifically:

📢How do we build socially intelligent AI systems? e.g., Sotopia, Social World Models
🧱How do we create AI agents that effectively help humans? e.g., WebArena, TOM-SWE
🛡️How do we ensure AI systems behave safely and align with human values? e.g., HAICOSYSTEM, OpenAgentSafety

Aug 12, 2026	I defended my PhD! [Slides]
Jul 8, 2026	Excited that five papers were accepted to COLM 2026: Mind the Sim2Real Gap in User Simulation for Agentic Tasks, SOTOPIA-TOM, Social World Models, GoodPoint, and Training Proactive and Personalized LLM Agents.
Apr 18, 2026	Gave a talk on "User-Effective AI Agents" at Scale AI. [Slides]
Apr 9, 2026	I received a Microsoft PhD Fellowship!
Mar 6, 2025	Excited to give a guest lecture on "Safety, bias, ethics in LLMs" for Data Bias and Fairness Series

Feel free to contact me at xuhuiz@cs.cmu.edu