I am a second-year master's student at Seoul National University, working with Prof. Gunhee Kim. I am also a visiting researcher at Stanford University, hosted by Prof. Chelsea Finn. Previously, I received my Bachelor's degree with honors in Computer Science and Engineering from POSTECH.

Throughout my life, I’ve been thinking about what I want, what I know, and how to explore what I do not know. This curiosity has grown into the research question I want to pursue: how can models use external knowledge to solve increasingly challenging problems? I believe we already have plenty of knowledge to draw on, especially the knowledge that keeps evolving and accumulating after training. The bottleneck is a memory system that models can manage on their own: reusing prior knowledge instead of reasoning from scratch, and not repeating past failures. Yet such knowledge is hard to retrieve, since it is rarely similar on the surface and recognizing that it is useful takes deeper reasoning. I want to push into this unexplored direction: retrieving knowledge for better decision making in open-ended, long-horizon problems (e.g., scientific discovery, robotics).

In parallel, I enjoy abstracting thoughts and mapping their relationships into my own language. For me, conversation serves as a medium for interpreting others’ mental models and discovering new axes of thinking. You can find more of these reflections on my Blog.

Publication

ScholarCatalyst: A Benchmark for Retrieving Papers that Inspire New Research

Sohyeon Kim^*, Yoonho Lee^*, Bo Liu, Dayoon Ko, Rulin Shao, Seungone Kim, Graham Neubig, Pang Wei Koh, Aakanksha Chowdhery, Akari Asai, Omar Khattab, Yejin Choi, Gunhee Kim, Chelsea Finn
Preprint 2026  Website  Paper  Code  Data  *equal contribution

MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information Retrieval

Seokwon Song, Sohyeon Kim, Gunhee Kim
EMNLP 2026  Paper

When Is Enough Not Enough? Illusory Completion in Search Agents

Dayoon Ko, Jihyuk Kim, Sohyeon Kim, Haeju Park, Dahyun Lee, Gunhee Kim, Moontae Lee, Kyungjae Lee
COLM 2026 Workshop on Agent Behavior  Paper

Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning

Dayoon Ko, Jihyuk Kim, Haeju Park, Sohyeon Kim, Dahyun Lee, Yongrae Jo, Gunhee Kim, Moontae Lee, Kyungjae Lee
ICLR 2026  Paper  Website

When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using GradNormIR

Dayoon Ko, Jinyoung Kim, Sohyeon Kim, Jinhyuk Kim, Jaehoon Lee, Seonghak Song, Minyoung Lee, Gunhee Kim
ACL 2025 Findings  Paper