Sunghwan Kim

prof_pic.jpg

MS Student at Yonsei University

kimsh8564[at]yonsei.ac.kr

Hi! I am a first year M.S. student at Language and AGI Lab advised by Jinyoung Yeo. Previously, I received B.S. in Materials Science & Engineering from Yonsei University in Aug. 2024.

I aim to build human-like intelligent systems that can autonomously learn, reason, and adapt to diverse environments. My recent research interests include: (i) Reinforcement Learning (RL) to solve long-horizon tasks and (ii) Developing intelligent systems that learn through interaction with the environment. Additionally, I focus on analyzing language models to identify limitations and room for improvement.

News

May 23, 2025 Our “Web-Shepherd” and “Embodied Agents Meet Personalization” papers are released!
May 17, 2025 🎉 Our “Reward Model Evaluation” and “LLM Meets Scene Graph” got accepted to ACL 2025!
Mar 11, 2025 I will join Microsoft Research Asia (MSRA) as a research intern!
Jan 23, 2025 🎉 Our work “World Model for Web Agent” got accepted to ICLR 2025!
Sep 21, 2024 🎉 Our work “Think-and-Execute” got accepted to EMNLP 2024 and “Cactus” got accepted to EMNLP 2024 Findings!
Aug 14, 2024 🏆 Our paper has been selected as an outstanding paper at ACL 2024! 🏆
May 15, 2024 🎉 Our work “Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation” got accepted to ACL 2024!

Selected Publications

† indicates equal contribution.
  1. Reward Model
    WebShepherd.png
    Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
    Hyungjoo Chae Sunghwan Kim ,  Junhee Cho,  Seungone Kim,  Seungjun Moon,  Gyeom Hwangbo,  Dongha Lim,  Minjin Kim,  Yeonjun Hwang,  Minju Gwak,  Dongwook Choi,  Minseok Kang,  Gwanhoon Im,  ByeongUng Cho,  Hyojun Kim,  Jun Hee Han,  Taeyoon Kwon,  Minju Kim,  Beong-woo Kwak,  Dongjin Kang, and 1 more author
    Arxiv preprint
  2. Reward Model
    Reward_Model.png
    Rethinking Reward Model Evaluation Through the Lens of Reward Overoptimization
    Sunghwan Kim ,  Dongjin Kang,  Taeyoon Kwon,  Hyungjoo Chae,  Dongha Lee, and  Jinyoung Yeo
    ACL 2025
  3. Interaction
    worldmodel_web.png
    Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigation
    Hyungjoo Chae,  Namyoung Kim,  Kai Tzu-iunn Ong,  Minju Gwak,  Gwanwoo Song,  Jihoon Kim,  Sunghwan Kim ,  Dongha Lee, and  Jinyoung Yeo
    ICLR 2025
  4. Dialogue
    ESC.png
    Can Large Language Models be Good Emotional Supporter? Mitigating Preference Bias on Emotional Support Conversation
    Dongjin Kang Sunghwan Kim ,  Taeyoon Kwon,  Seungjun Moon,  Hyunsouk Cho,  Youngjae Yu,  Dongha Lee, and  Jinyoung Yeo
    ACL 2024
    🏆 Outstanding Paper Award 🏆