Beanie

👋 Hello, I'm Beanie

Jeonghye Kim

KAIST Graduate school of Electrical Engineering

I'm a Ph.D. student at KAIST, advised by Prof. Youngchul Sung. My research focuses on developing automated agents with high applicability in real-world contexts. To achieve this goal, I am actively involved in the integration of reinforcement learning and LLMs, as well as LLM-based agents.

News

May. 2025

Three papers, including one spotlight poster, have been accepted to ICML 2025!

Sep. 2024

QCS has been accepted to NeurIPS 2024 and will be presented in Vancouver, Canada 🇨🇦

Jan. 2024

DC has been accepted to ICLR 2024 as a spotlight presentation! See you in Vienna, Austria 🇦🇹

Mar. 2024

I’ve started as a research intern at LG AI Research!

Apr. 2023

My first paper, LESSON, has been accepted to ICML 2023! I hope to see you in Hawaii, USA 🇺🇸

Publications

(*: equal contribution, †: equal corresponding)

ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflection

Jeonghye Kim*, Sojeong Rhee* , Minbeom Kim, Dohyung Kim, Sangmook Lee, Youngchul Sung† , and Kyomin Jung†

Under-review

Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data

Jeonghye Kim, Yongjae Shin, Whiyoung Jung, Sunghoon Hong, Deunsol Yoon, Youngchul Sung, Kanghoon Lee, Woohyung Lim

*Work done during the LG AI Internship

ICML 2025

Spotlight (Top 2.6%)

Online Pre-Training for Offline-to-Online Reinforcement Learning

Yongjae Shin, Jeonghye Kim, Whiyoung Jung, Sunghoon Hong, Deunsol Yoon, Youngsoo Jang, Geon-Hyeong Kim, Jongseong Chae, Youngchul Sung, Kanghoon Lee, Woohyung Lim

*Work done during the LG AI Internship

ICML 2025