Sunghwan Kim

Hi! I am a second year M.S. student at Yonsei University advised by Jinyoung Yeo. Previously, I received my B.S. in Materials Science & Engineering from Yonsei University in August 2024.

My research aims to build self-improving AI systems: agents that continue to learn after deployment while remaining controllable by and interpretable to humans. I study this goal through three coupled axes: shaping the environments that determine both the data agents learn from and the rewards that guide them, developing agents that use adaptive and meta-cognitive policies, and analyzing the learning dynamics that make self-improvement reliable rather than accidental. My broader goal is to move beyond static, once-trained models toward agents that safely learn to improve themselves over a lifetime, with personalization and scientific discovery as the primary settings.