Woojung Song

I'm an integrated M.S.–Ph.D. student in Data Science at Seoul National University, advised by Yohan Jo in the HOLI Lab (Human-Oriented Language Intelligence).

AI agents can already solve many real-world problems. I believe making them better takes more than improving task performance: we also need to understand how they behave, what guides their decisions, and how they respond to people. My goal is to use that understanding to build agents that better align with human needs and values.

opusdeisong@snu.ac.kr

Woojung Song

Research Interests

  1. [Agent Behavior] How agents work, decide, and interact

    I examine how agents make decisions, use tools, and interact with users, and how to make these behaviors more reliable.

  2. [Human-like Agents] How agents model people and fictional characters

    I'm also interested in agents that capture the values and personalities of people and fictional characters, including how their behavior changes across situations and over time.

My research asks: How can we understand and shape agent behavior to better align it with human needs and values?

I'm currently seeking a summer research internship in agents, alignment, or social simulation, and I'm always open to collaboration. Feel free to reach out at opusdeisong@snu.ac.kr.

News

Earlier news