The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs

TL;DR

This survey explores the evolution of multi-agent communication from early reinforcement learning methods to emergent languages and large language models, highlighting design choices, challenges, and future directions for scalable, interpretable collaboration.

Contribution

It provides a unified framework using the Five Ws to connect diverse research on multi-agent communication and discusses practical design patterns and open challenges.

Findings

End-to-end learned protocols are task-specific and hard to interpret.

Emergent Language enables structured communication but faces grounding and scalability issues.

Large Language Models bring natural language priors, improving reasoning and collaboration.

Abstract

Multi-agent sequential decision-making powers many real-world systems, from autonomous vehicles and robotics to collaborative AI assistants. In dynamic, partially observable environments, communication is often what reduces uncertainty and makes collaboration possible. This survey reviews multi-agent communication (MA-Comm) through the Five Ws: who communicates with whom, what is communicated, when communication occurs, and why communication is beneficial. This framing offers a clean way to connect ideas across otherwise separate research threads. We trace how communication approaches have evolved across three major paradigms. In Multi-Agent Reinforcement Learning (MARL), early methods used hand-designed or implicit protocols, followed by end-to-end learned communication optimized for reward and control. While successful, these protocols are frequently task-specific and hard to interpret, motivating work on Emergent Language (EL), where agents can develop more structured or symbolic communication through interaction. EL methods, however, still struggle with grounding, generalization, and scalability, which has fueled recent interest in large language models (LLMs) that bring natural language priors for reasoning, planning, and collaboration in more open-ended settings. Across MARL, EL, and LLM-based systems, we highlight how different choices shape communication design, where the main trade-offs lie, and what remains unsolved. We distill practical design patterns and open challenges to support future hybrid systems that combine learning, language, and control for scalable and interpretable multi-agent collaboration.