Sangeun Park, Minhae Kwon,"Multi^2: Hierarchical Multi-Agent Decision-Making with LLM-Based Agents in Interactive Environments," International Conference on Machine Learning (ICML), July 2026. (BK21+ IF: 4, Acceptance rate: 26.6%) [Project Page]
Sangeun Park, Chanin Eom, Minhae Kwon, "Offline-to-Online Reinforcement Learning for Driving Style-aware Policy Adaptation in Mixed Traffic," IEEE Transactions on Intelligent Transportation Systems, under review. (Rating: Q1, IF 8.4, Rank: 5/183, Top 2.5%)
Sangeun Park*, Guhyeon Kang*, Minhae Kwon, Anonymous submission–multi-agent LLM, Top AI Conference, under review. (*equal contribution) (BK21+ IF: 4)
Sangeun Park, Hyunggon Park*, Minhae Kwon*, "Autonomous Vehicle Leadership as Networked AI: A Stackelberg Game-Theoretic Analysis in Mixed Traffic," under review. (*co-corresponding authors) (Rating: Q1, IF: 13.7, Rank: 3/122, Top 2.5%)
Hongki Kim, Sangeun Park, Minhae Kwon, “Adaptive Action Chunking Strategy from World Feedback in Mixed Traffic,” International Conference on Machine Learning (ICML) RLxF: Reinforcement Learning from World Feedback Workshop, July 2026.
Sangeun Park, Minhae Kwon, “Drift-Aware Coordination for Long-Horizon LLM-Based Multi-Agent Systems,” International Conference on Machine Learning (ICML) WiML Workshop, July 2026.
Hongki Kim, Sangeun Park, Minhae Kwon, “UA2C: Uncertainty-Aware Adaptive Action Chunking for Offline-to-Online Decision-Making in Mixed Traffic,” International Conference on Machine Learning (ICML) Workshop on Decision-Making from Offline Datasets to Online Adaptation: Black-Box Optimization to Reinforcement Learning, July 2026.
Sangeun Park*, Guhyeon Kang*, Minhae Kwon, Improving Multi-Agent Coordination with a Drift-Aware RL Objective, International Conference on Machine Learning (ICML) Workshop on Decision-Making from Offline Datasets to Online Adaptation: Black-Box Optimization to Reinforcement Learning, July 2026. (*equal contribution)
Sangeun Park, Minhae Kwon, "Multi-Agent LLMs with Offline Reinforcement Learning for Hierarchical Multi-turn Decision-Making," Conference on Neural Information Processing Systems (NeurIPS) Efficient Reasoning Workshop, December 2025.
Sangeun Park, Minhae Kwon, "Hierarchical Decision-making via Multi-turn Reinforcement Learning," Conference on Neural Information Processing Systems (NeurIPS) Women in Machine Learning Workshop, December 2025. (Contributed Talk) [Video]
Sangeun Park, Chanin Eom, Jaehwi Lee, Dongsu Lee, Minhae Kwon, "Enhancing Traffic Flow in On-ramp Merging Through Autonomous Vehicles Based on Deep Reinforcement Learning," IEEE International Conference on Robotics and Automation (IEEE ICRA) HRI Workshop, May 2024. (Spotlight Talk) [Video] [Media]
Sangeun Park, Chanin Eom, Minhae Kwon, "xLSTM-based Noise-robust Driving Characteristic Inference Network for V2I Systems," Transactions of the Korean Society of Automotive Engineers (T-KSAE), vol.33, no.07, pp.487-502, July 2025. [Media]
Sangeun Park, Chanin Eom, Minhae Kwon, "Inference on Driving Characteristic Based on Time-series Partial Observation of Vehicle," The Journal of Korean Institute of Communications and Information Sciences (J-KICS), vol.50, no.06, pp.858-874, June 2025. (Best Paper Award) [Media]
Hongki Kim, Sangeun Park, Minhae Kwon, "Decision-Making Based on Decision Transformer in Space Reward Environment," Joint Conference on Communications and Information (JCCI), April 2026.
Sangeun Park, Chanin Eom, Minhae Kwon, "V2I-Based Driving Characteristics Inference Model," Korean Society of Automotive Engineers (KSAE) Fall Conference, November 2024. (Best Paper Award) [Media]
Sangeun Park, Chanin Eom, Minhae Kwon, "Inference on Driving Characteristics with Partially Observed Trajectory Datasets," Korean Society of Automotive Engineers (KSAE) Fall Conference, November 2024. [Video]
Sangeun Park, Chanin Eom, Dongsu Lee, Minhae Kwon, "Enhancing Traffic Flow in On-ramp Merging Through DDPG-based Autonomous Vehicle," Joint Conference on Communications and Information (JCCI), April 2024. [Video]