LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning

Sangjun Bae, Yisak Park, Sanghyeon Lee, Seungyul Han
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:4985-5016, 2026.

Abstract

Communication is a key component in multi-agent reinforcement learning (MARL) for mitigating partial observability, yet prior approaches often rely on inefficient information exchange or fail to transmit sufficient state information. To address this, we propose LLM-driven Multi-Agent Communication (LMAC), which leverages an LLM’s reasoning capability to design a communication protocol that enables all agents to reconstruct the underlying state as accurately and uniformly as possible. LMAC iteratively refines the protocol using an explicit state-awareness criterion, improving state recovery while narrowing differences in agents’ knowledge. Experiments on diverse MARL benchmarks show that LMAC improves state reconstruction across agents and yields substantial performance gains over prior communication baselines.

Cite this Paper

BibTeX
@InProceedings{pmlr-v306-bae26c, title = {{LLM}-Guided Communication for Cooperative Multi-Agent Reinforcement Learning}, author = {Bae, Sangjun and Park, Yisak and Lee, Sanghyeon and Han, Seungyul}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {4985--5016}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/bae26c/bae26c.pdf}, url = {https://proceedings.mlr.press/v306/bae26c.html}, abstract = {Communication is a key component in multi-agent reinforcement learning (MARL) for mitigating partial observability, yet prior approaches often rely on inefficient information exchange or fail to transmit sufficient state information. To address this, we propose LLM-driven Multi-Agent Communication (LMAC), which leverages an LLM’s reasoning capability to design a communication protocol that enables all agents to reconstruct the underlying state as accurately and uniformly as possible. LMAC iteratively refines the protocol using an explicit state-awareness criterion, improving state recovery while narrowing differences in agents’ knowledge. Experiments on diverse MARL benchmarks show that LMAC improves state reconstruction across agents and yields substantial performance gains over prior communication baselines.} }
Endnote
%0 Conference Paper %T LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning %A Sangjun Bae %A Yisak Park %A Sanghyeon Lee %A Seungyul Han %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-bae26c %I PMLR %P 4985--5016 %U https://proceedings.mlr.press/v306/bae26c.html %V 306 %X Communication is a key component in multi-agent reinforcement learning (MARL) for mitigating partial observability, yet prior approaches often rely on inefficient information exchange or fail to transmit sufficient state information. To address this, we propose LLM-driven Multi-Agent Communication (LMAC), which leverages an LLM’s reasoning capability to design a communication protocol that enables all agents to reconstruct the underlying state as accurately and uniformly as possible. LMAC iteratively refines the protocol using an explicit state-awareness criterion, improving state recovery while narrowing differences in agents’ knowledge. Experiments on diverse MARL benchmarks show that LMAC improves state reconstruction across agents and yields substantial performance gains over prior communication baselines.
APA
Bae, S., Park, Y., Lee, S. & Han, S.. (2026). LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:4985-5016 Available from https://proceedings.mlr.press/v306/bae26c.html.

Related Material