Research Areas
Retrieval, agents, and memory
Research Statement
My research focuses on information retrieval, retrieval-augmented generation, LLM-based agents, and agentic memory. I am particularly interested in building robust information-seeking agents that can adapt to unseen domains through feedback-driven alignment and long-term experience accumulation.
My broader goal is to develop self-improving retrieval agents that remain reliable, efficient, and grounded in external evidence while accumulating useful experience over time.
Information Retrieval
Retrieval-Augmented Generation
LLM Agents
Agentic Memory
Domain Adaptation
Test-time Reasoning
Robust Information-Seeking Agents
I study agents that use retrieval, retrieval-state feedback, and reasoning-time decision making to search, refine queries, and stay grounded in external evidence across unseen domains.
Agentic Retrieval
Query Refinement
Grounded Reasoning
Hybrid Retrieval and RAG
I build retrieval systems that use corpus-level statistics, retrieval evidence, and complementary dense-sparse signals to improve data generation, hybrid retrieval, and retrieval-augmented generation.
Dense and Sparse Retrieval
Hybrid Retrieval
RAG
Feedback-Driven Adaptation
I am interested in feedback-driven alignment for retrieval agents that adapt to new domains through retrieval-state feedback, evidence use, and zero-shot or test-time reasoning signals.
Domain Adaptation
Zero-shot Retrieval
Retrieval Feedback
Agentic Memory
I study how memories should be generated from past trajectories, retrieved for future tasks, updated as evidence changes, and managed efficiently under practical inference constraints.
Long-term Memory
Memory-augmented Agents
Experience Accumulation
Publications
Selected peer-reviewed work
ACL 2026
Beyond Markovian Forgetfulness: Episodic Memory for Reasoning-Intensive Retrieval
Dohyeon Lee, Yeonseok Jeong, and Seung-won Hwang.
EACL 2026
D3: Dynamic Docid Decoding for Multi-Intent Generative Retrieval
Jaeyoung Kim*, Dohyeon Lee*, Soona Hong*, and Seung-won Hwang.
Industry Track.
Findings of EMNLP 2025
From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval
Dohyeon Lee, Yeonseok Jeong, and Seung-won Hwang.
Findings of ACL 2025
ECoRAG: Evidentiality-guided Compression for Long Context RAG
Yeonseok Jeong, Jinsu Kim, Dohyeon Lee, and Seung-won Hwang.
NAACL 2025
Query-focused Referentiability Learning for Zero-shot Retrieval
Jaeyoung Kim, Dohyeon Lee, and Seung-won Hwang.
NAACL 2025
tRAG: Term-level Retrieval-Augmented Generation for Zero-shot Retrieval
Dohyeon Lee, Jongyoon Kim, Jihyuk Kim, Seung-won Hwang, and Joonsuk Park.
EMNLP 2024
Interventional Speech Noise Injection for ASR Generalizable Spoken Language Understanding
YeonJoon Jung, Jaeseong Lee, Seungtaek Choi, Dohyeon Lee, Minsoo Kim, and Seung-won Hwang.
Findings of ACL 2024
DADA: Distribution-Aware Domain Adaptation of PLMs for Information Retrieval
Dohyeon Lee*, Jongyoon Kim*, Seung-won Hwang, and Joonsuk Park.
NAACL 2024
HIL: Hybrid Isotropy Learning for Zero-shot Performance in Dense Retrieval
Jaeyoung Kim, Dohyeon Lee, and Seung-won Hwang.
NAACL 2024
Script-mix: Mixing Scripts for Low-resource Language Parsing
Jaeseong Lee, Dohyeon Lee, and Seung-won Hwang.
EACL 2024
Chaining Event Spans for Temporal Relation Grounding
Jongho Kim, Dohyeon Lee, Minsoo Kim, and Seung-won Hwang.
ACL 2023
On Complementarity Objectives for Hybrid Retrieval
Dohyeon Lee, Seung-won Hwang, Kyungjae Lee, Seungtaek Choi, and Sunghyun Park.
ECIR 2023
C2LIR: Continual Cross-lingual Transfer for Low-Resource Information Retrieval
Jaeseong Lee*, Dohyeon Lee*, Jongho Kim, and Seung-won Hwang.
Short paper.
AAAI 2023
Script, Language, Labels: Overcoming Three Discrepancies for Low-Resource Language Specialization
Jaeseong Lee, Dohyeon Lee, and Seung-won Hwang.
EMNLP 2022
PLM-based World Models for Text-based Games
Minsoo Kim, Yeonjoon Jung, Dohyeon Lee, and Seung-won Hwang.
ACL/IJCNLP 2021
Robustifying Multi-hop QA through Pseudo-Evidentiality Training
Kyungjae Lee, Seung-won Hwang, Sang-eun Han, and Dohyeon Lee.
CIKM 2021
SCOPA: Soft Code-Switching, Pairwise Alignment for Zero-Shot Cross-lingual Transfer
Dohyeon Lee*, Jaeseong Lee*, Gyewon Lee, Byung-Gon Chun, and Seung-won Hwang.
Short paper.
Experience
KAIST - Postdoctoral Researcher
March 2026 - present
Research on information retrieval, retrieval-augmented generation, LLM-based agents, and agentic memory.
NAVER Corp. - Research Intern
March 2020 - June 2020
Research title: Sparse-Dense Hybrid Retrieval. Mentor: Sunghyun Park, Ph.D.
