Publications: 'Web-Shepherd: Advancing PRMs for Reinforcing Web Agents' (NeurIPS 2025 Spotlight); 'ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactions' (EMNLP 2025 Findings); 'Evaluating Robustness of Reward Models for Mathematical Reasoning' (ACL 2025). Awards: 'The BiGGen Bench' selected for Best Paper Award at NAACL 2025.
Research Experience
Worked as a research intern at LG AI Research and Tutoring, Market Designers Inc.
Education
2025 - Present: Ph.D. in Computer Science at Georgia Institute of Technology, Advisor: Alan Ritter; 2023 - 2025: M.S. in Computer Science at Yonsei University, Advisor: Jinyoung Yeo; 2019 - 2022: B.S. in Computer Science at Yonsei University.
Background
Research interests: GUI agents, digital agents, reinforcement learning (especially for long-horizon tasks), and code generation models. Bio: Focuses on developing GUI and digital agents that can interact with complex environments, particularly in web navigation and code generation. Passionate about building agents that can understand and interact with the digital world meaningfully.
Miscellany
Open to collaboration and discussion about research projects. Interested in GUI agents, web navigation, or code generation? Feel free to reach out!