Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
8-2025
Abstract
Multi-agent reinforcement learning (MARL) has demonstrated remarkable success in collaborative tasks, yet faces significant challenges in scaling to complex scenarios requiring sustained planning and coordination across long horizons. While hierarchical approaches help decompose these tasks, they typically rely on hand-crafted subtasks and domain-specific knowledge, limiting their generalizability. We present L2M2, a novel hierarchical framework that leverages large language models (LLMs) for high-level strategic planning and MARL for low-level execution. L2M2 enables zero-shot planning that supports both end-to-end training and direct integration with pre-trained MARL models. Experiments in the VMAS environment demonstrate that L2M2's LLM-guided MARL achieves superior performance while requiring less than 20% of the training samples compared to baseline methods. In the MOSMAC environment, L2M2 demonstrates strong performance with pre-defined subgoals and maintains substantial effectiveness without subgoals - scenarios where baseline methods consistently fail. Analysis through kernel density estimation reveals L2M2's ability to automatically generate appropriate navigation plans, demonstrating its potential for addressing complex multi-agent coordination tasks.
Keywords
Agent-based and multi-agent systems, coordination and cooperation, machine learning, multi-agent reinforcement learning (MARL)
Discipline
Artificial Intelligence and Robotics
Research Areas
Intelligent Systems and Optimization
Areas of Excellence
Sustainability
Publication
IJCAI '25: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, Montreal, Canada, August 16-22
First Page
99
Last Page
107
Identifier
10.24963/ijcai.2025/12
Publisher
International Joint Conferences on Artifical Intelligence (IJCAI) Organization
City or Country
Montreal, Canada
Citation
GENG, Minghong; PATERIA, Shubham; SUBAGDJA, Budhitama; LI, Lin; ZHAO, Xin; and TAN, Ah-hwee.
L2M2: A hierarchical framework integrating large language model and multi‑agent reinforcement learning. (2025). IJCAI '25: Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, Montreal, Canada, August 16-22. 99-107.
Available at: https://ink.library.smu.edu.sg/sis_research/10852
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.24963/ijcai.2025/12