Hello!

I am a Software Engineer at Google, USA, developing AI/ML models to optimize user satisfaction in search ads. I hold a Ph.D. in Computer Science from Rice University, USA, where I was advised by Dr. Vaibhav Unhelkar. Prior to my Ph.D., I worked as a research engineer at Coreline Soft - a medical AI startup - and the Agency for Defense Development - a national research institute - in South Korea. I received my M.S. and B.S. degrees from Seoul National University, South Korea.

My research centers on Human Behavior Modeling, Human-Agent Collaboration, Theory of Mind and AI-Assisted Decision Making. During my PhD, I developed imitation and reinforcement learning algorithms for modeling multimodal human behaviors, as well as an AI-driven team coaching system that automatically analyzes and improves human teamwork in real time.

Selected Publications

Zhiqin Qian, Ryan Diaz, Sangwon Seo and Vaibhav V. Unhelkar, “Hierarchical Reward Design from Language: Enhancing Alignment of Agent Behavior with Human Specifications ,” AAMAS 2026

Sangwon Seo, Bing Han, Rayan E. Harari, Roger D. Dias, Marco A. Zenati, Eduardo Salas, and Vaibhav V. Unhelkar, “Socratic: Enhancing Human Teamwork via AI-enabled Coaching,” AAMAS 2025

Sangwon Seo and Vaibhav V. Unhelkar, “IDIL: Imitation Learning of Intent-Driven Expert Behavior,” AAMAS 2024

Sangwon Seo and Vaibhav V. Unhelkar, “Semi-Supervised Imitation Learning of Team Policies from Suboptimal Demonstrations,” IJCAI 2022

Sangwon Seo, Lauren R. Kennedy-Metz, Marco A. Zenati, Julie A. Shah, Roger D. Dias, and Vaibhav V. Unhelkar, “Towards an AI coach to infer team mental model alignment in healthcare,” CogSIMA 2021