Joonkee Kim

I'm an LLM research engineer at Upstage, where I work on the Solar LLM series. Before that, I was at LG AI Research (2024–2026), where I contributed to the EXAONE models, from EXAONE 3.0 to EXAONE 4.5 and K-EXAONE.

I received my M.S. from the Graduate School of AI at KAIST, advised by Prof. Se-Young Yun, and my B.S. in Computer Science and Bio-Mechatronics from Sungkyunkwan University. My research focuses on LLM post-training and reinforcement learning.

Experience

Upstage
LLM Research Engineer · Solar LLM
Apr 2026 – Present
LG AI Research
LLM Research Engineer · EXAONE
Feb 2024 – Apr 2026
KAIST
M.S., Graduate School of AI · Advisor: Prof. Se-Young Yun
Mar 2022 – Feb 2024
Sungkyunkwan University
B.S., Computer Science and Bio-Mechatronics · Summa Cum Laude
Mar 2015 – Feb 2022

Publications

* equal contribution.

Learning to Comply: Workflow-Grounded Environment Generation for Training Procedurally Compliant Agents
Seungwon Lim*, Minu Kim*, Seokhee Hong, Jinyoung Yeo, Se-Young Yun, Joonkee Kim
COLM 2026
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
Yujin Kim*, Namgyu Ho*, Sangmin Hwang*, Joonkee Kim, Yongjin Yang, Sangmin Bae, Seungone Kim, Jaehun Jung, Se-Young Yun, Hwanjun Song
NeurIPS 2026
AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
Woosung Koh, Wonbeen Oh, Jaein Jang, MinHyung Lee, Hyeongjin Kim, Ah Yeon Kim, Joonkee Kim, Junghyun Lee, Taehyeon Kim, Se-Young Yun
NeurIPS 2025
Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions
Taehyeon Kim*, Joonkee Kim*, Gihun Lee*, Se-Young Yun
ICLR 2024  Spotlight
Re3val: Reinforced and Reranked Generative Retrieval
EuiYul Song, Sangryul Kim, Haeju Lee, Joonkee Kim, James Thorne
Findings of EACL 2024
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning
Hojoon Lee*, Hanseul Cho*, Hyunseung Kim*, Daehoon Gwak, Joonkee Kim, Jaegul Choo, Se-Young Yun, Chulhee Yun
NeurIPS 2023
HARE: Explainable Hate Speech Detection with Step-by-Step Reasoning
Yongjin Yang*, Joonkee Kim*, Yunjin Kim*, Namgyu Ho, James Thorne, Se-Young Yun
Findings of EMNLP 2023
Toward Risk-Based Optimistic Exploration for Cooperative Multi-Agent Reinforcement Learning
Jihwan Oh*, Joonkee Kim*, Minchan Jeong, Se-Young Yun
AAMAS 2023
The Multimodality Cell Segmentation Challenge: Toward Universal Solutions
Jun Ma, Ronald Xie, Shamini Ayyadhury, Cheng Ge, Anubha Gupta, Ritu Gupta, Song Gu, Yao Zhang, Gihun Lee, Joonkee Kim, et al.
Nature Methods 2024
The StarCraft Multi-Agent Exploration Challenges: Learning Multi-Stage Tasks and Environmental Factors Without Precise Reward Functions
Mingyu Kim*, Jihwan Oh*, Yongsik Lee, Joonkee Kim, Seonghwan Kim, Song Chong, Se-Young Yun
IEEE Access 2023
MEDIAR: Harmony of Data-Centric and Model-Centric for Multi-Modality Microscopy
Gihun Lee*, SangMook Kim*, Joonkee Kim*, Se-Young Yun
NeurIPS 2022 Competition  1st Place

Technical Reports

As a contributor.

Solar Open 2 Technical Report · Upstage, 2026
EXAONE 4.5 Technical Report · LG AI Research, 2026
K-EXAONE Technical Report · LG AI Research, 2026
EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes · LG AI Research, 2025
EXAONE Deep: Reasoning Enhanced Language Models · LG AI Research, 2025
EXAONE 3.5: Series of Large Language Models for Real-world Use Cases · LG AI Research, 2024
EXAONE 3.0 7.8B Instruction Tuned Language Model · LG AI Research, 2024