Overview

Multi-agent communication examines how agents share information, form common beliefs, and coordinate actions when each may have only a partial view of a task. Approaches include learned signaling in decentralized reinforcement learning, graph-based routing and debate among language-model agents, and compact symbolic or latent messages designed to reduce bandwidth and latency. Researchers evaluate these methods in settings such as cooperative navigation, StarCraft, reasoning and coding tasks, and embodied collaboration with limited or unreliable communication. A central tension is that messages can reveal information teammates need, but added communication can also create overhead, spread errors, reduce diversity, or expose systems to attacks.

Latest papers

CardsList

399 papers29 papers in the last four weeks, down 61% on the four weeks before. 0.2% of all new papers.

  1. Enabling Agents to Communicate Entirely in Latent Space

    Nov 12, 2025Zhuoyun Du, Runze Wang, Huiyu Bai +6Multi-Agent CommunicationMulti-Agent LLMs

  2. An Explanation-oriented Inquiry Dialogue Game for Expert Collaborative Recommendations

    Nov 3, 2025Qurat-ul-ain Shaheen, Katarzyna Budzynska, Carles SierraExplainable Artificial IntelligenceHealthcare

  3. Communication and Verification in LLM Agents towards Collaboration under Information Asymmetry

    Oct 29, 2025Run Peng, Ziqiao Ma, Amy Pang +5Multi-Agent LLM SystemsLLM Agent Verification

  4. When and Why Does Multi-Agent Debate Fail and Does It Really Underperform?

    Oct 23, 2025Yongqiang Chen, Gang Niu, James Cheng +2Multi-Agent DebateMulti-Agent Collaboration

  5. Fetch.ai: An Architecture for Modern Multi-Agent Systems

    Oct 21, 2025Michael J. Wooldridge, Attila Bagoly, Jonathan J. Ward +2Multi-Agent OrchestrationMulti-Agent Systems

  6. Benefits and Limitations of Communication in Multi-Agent Reasoning

    Oct 14, 2025Michael Rizvi-Martel, Satwik Bhattamishra, Neil Rathi +2Multi-Agent ReasoningCommunication Complexity

  7. Axiomatisation for an asynchronous epistemic logic with sending and receiving messages

    Oct 3, 2025Philippe Balbiani, Hans van Ditmarsch, Clara LerouvilloisLogical ReasoningDynamic Epistemic Logic

  8. Policy Gradient with Self-Attention for Model-Free Distributed Nonlinear Multi-Agent Games

    Sep 22, 2025Eduardo Sebastián, Maitrayee Keskar, Eeman Iqbal +3Policy GradientSelf-Attention

  9. Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning

    Jul 31, 2025Tommaso Marzi, Cesare Alippi, Andrea CiniMulti-Agent CoordinationHierarchical MARL