Kwangwook Seo

I’m a Ph.D. student in the Data & Language Intelligence (DLI) Lab at Yonsei University, advised by Prof. Dongha Lee.

If you're interested in collaborating on research or exploring new ideas together, please feel free to connect with me anytime! I welcome the opportunity to discuss potential projects and innovative approaches, and I'm always open to hearing from fellow researchers and enthusiasts.

🔎 Research Interest

My research lies at the intersection of natural language processing (NLP) and machine learning (ML) at scale. My current interests include:

Personalized Agents and User Simulation in diverse real environments
Agent Self-Evolving with Procedural Memory Learning and Scalable Environment Synthesis
Designing and Optimizing Interfaces for Agent–Environment Alignment

✨ I’m currently working on personalized harnesses that help agents learn how to work with individual users over time. My focus is on organizing memories of users’ preferences, past decisions, and ongoing tasks within persistent workspaces, so agents can use this knowledge to guide tool use and actions on users’ behalf.

📚 Publications

*: denotes equal contribution.

	ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis Kwangwook Seo, Dongha Lee arXiv, 2026 Paper / Code
	BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedback Hyunseo Kim, Sangam Lee, Kwangwook Seo, Dongha Lee ICML, 2026 Paper / Code
	P-Check: Advancing Personalized Reward Model via Learning to Generate Dynamic Checklist Kwangwook Seo, Dongha Lee ACL, 2026 Paper / Code / Blog Post
	In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners Jaehoon Kim, Kwangwook Seo, Dongha Lee arXiv, 2025 Paper / Code
	Stop Playing the Guessing Game! Target-free User Simulation for Evaluating Conversational Recommender Systems Sunghwan Kim, Kwangwook Seo, Tongyoung Kim, Jinyoung Yeo, Dongha Lee EMNLP Findings*, 2025 Paper / Code / Presentation / Poster
	MT-RAIG: Novel Benchmark and Evaluation Framework for Retrieval-Augmented Insight Generation over Multiple Tables Kwangwook Seo, Donguk Kwon, Dongha Lee ACL, 2025 Paper / Code / Presentation / Poster
	Unveiling Implicit Table Knowledge with Question-Then-Pinpoint Reasoner for Insightful Table Summarization Kwangwook Seo, Jinyoung Yeo, Dongha Lee EMNLP Findings, 2024 Paper / Code / Presentation / Poster
	VerifiNER: Verification-augmented NER via Knowledge-grounded Reasoning with Large Language Models Seoyeon Kim, Kwangwook Seo, Hyungjoo Chae, Jinyoung Yeo Dongha Lee ACL, 2024 Paper / Code / Presentation / Poster

📁 Industry Experience

Research Scientist Intern,
EXAONE Lab, 2026.11 -

Research Project,
Naver Place, Team AirSPACE, 2025.06 - 2026.06
Advancing Personalized Place Search and Recommendation with User Simulation and Profiling

Research Engineer Intern,
Sol Project 3rd Internship Program, 2022.09 - 2022.11
Enhancing Korean STS benchmark via scoring silver-label inconsistency

🏆 Honors and Awards

1st Prize – Bigcontest 2022 Data Analysis Champion League, MSIT and NIA
Minister of Science and ICT Award
Optimal Location Selection of EV Slow Charger
Presentation / Blog Post

📖 Teaching

[AI Expert] Agent basics, Conversational Recommender Systems (2025), Samsung Electronics SNU R&D Center
Teaching Assistant

[AI Expert] Information Retrieval and Recommender Systems (2024), Samsung Electronics SNU R&D Center
Teaching Assistant, Project Mentorship

[AAI3120,CAS3120] Machine Learning (2024S, 2025S), Yonsei University
Teaching Assistant

[AIC2110] Introduction to Data Science (2024S), Yonsei University
Teaching Assistant

📝 Academic Service

Conference Reviewer and Program Committee

EMNLP (2024, 2025)
ACL (2025)
AAAI (2024, 2025, 2026)
KDD (2024)
WWW (2024, 2025)
CIKM (2025)
COLM (2025)
ICLR (2026, 2027)
ICML (2026)
NeurIPS (2026)

World map of website visitors — view visitor statistics