Multi-Agent Communication

Follow this topic Ask about this topic

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

380 papers65 papers in the last four weeks, up 59% on the four weeks before. 0.4% of all new papers.

SVR-MAD: A Bayesian-Inspired Framework for Posterior-Guided Multi-Agent Debate
May 21, 2026Weifan Jiang, Rana Shahout, Minghao Li +4Multi-Agent LLM Systems Multi-Agent Debate
Harvard University
LACO: Adaptive Latent Communication for Collaborative Driving
May 21, 2026Tianhao Chen, Yuheng Wu, Dongman LeeAutonomous Driving Multi-Agent Collaboration
Korea Advanced Institute of Science & Technology
ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
May 21, 2026Woomin Song, Beomjun Kim, Daewon Choi +4Test-Time Scaling Multi-Agent Systems
1KAIST · 2Amazon AGI · 3Together AI
Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints
May 20, 2026Alexi Canesse, Benoît Goupil, Jesse Read +1Decentralized MARL Multi-Agent Communication
École polytechnique (LIX), CNRS, Institut Polytechnique de Paris, Palaiseau, France
What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems
May 19, 2026Yong Jin Chun, Iftekhar AhmedMulti-Agent Collaboration Multi-Agent Systems
Department of Informatics University of California, Irvine Irvine, CA, 92618
Conflict-Aware Multi-Agent Reasoning via Signed Graph Modeling
May 19, 2026Longgang He, Longzhu He, Shihao Peng +2Multi-Agent LLM Systems Multi-Agent Systems
Harbin Institute of Technology (Shenzhen) · Beijing University of Posts and Telecommunications
LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning
May 18, 2026Sangjun Bae, Yisak Park, Sanghyeon Lee +1LLM-Guided RL Multi-Agent Systems
Graduate School of Artificial Intelligence, UNIST, Ulsan, South Korea.
Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Learning
May 17, 2026Wei Duan, Junyu Xuan, En Yu +2Graph Structure Learning Information Bottleneck
Australian Artificial Intelligence Institute (AAII), University of Technology Sydney
NeuroMAS: Multi-Agent Systems as Neural Networks with Joint Reinforcement Learning
May 16, 2026Haoran Lu, Luyang Fang, Wenxuan Zhong +1Multi-Agent LLM Systems Multi-Agent Coordination
Department of Statistics, University of Georgia, Athens, GA 30602
Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems
May 15, 2026Nurbek Tastan, Alex Iacob, Lorenzo Sani +4Multi-Agent System Optimization Multi-Agent Orchestration
1MBZUAI, UAE · University of Cambridge, UK · 3Flower Labs, UK +1
Trustworthy Multi-Agent Systems: Mitigating Semantic Drift with the Argent Signaling Protocol
May 14, 2026Anantha SharmaAI Agent Reliability Multi-Agent LLM Systems
Synechron Inc · Charlotte, NC, USA
Good Agentic Friends Do Not Just Give Verbal Advice: They Can Update Your Weights
May 13, 2026Wenrui Bao, Huan Wang, Jian Wang +3LLM Inference Efficiency Multi-Agent LLM Systems
University of Central Florida · Westlake University · Snap Inc. +2
Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning
May 13, 2026Hao Zhou, Tiru Wu, Yan Jiang +3Multimodal Robustness Adversarial Attacks
Finding the Weakest Link: Adversarial Attack against Multi-Agent Communications
May 13, 2026Maxwell Standen, Junae Kim, Claudia SzaboAdversarial Attacks Adversarial Perturbations
The University of Adelaide · DST Group
Embodied Multi-Agent Coordination by Aligning World Models Through Dialogue
May 13, 2026Vardhan Dongre, Dilek Hakkani-TürMulti-Agent Coordination AI Agent Benchmarks
Siebel School of Computing & Data Science University of Illinois Urbana-Champaign
Beyond Inefficiency: Systemic Costs of Incivility in Multi-Agent Monte Carlo Simulations
May 12, 2026Alison Moldovan-Mauer, Benedikt MangoldMulti-Agent Debate Multi-Agent Communication
Technische Hochschule Nürnberg Georg Simon Ohm 90489 Nuremberg, Germany
Emergent Communication between Heterogeneous Visual Agents through Decentralized Learning
May 12, 2026Mikako Ochiai, Masatoshi Nagano, Tadahiro TaniguchiMulti-Agent Systems Vision-Language Alignment
Graduate School of Informatics, Kyoto University, Kyoto 606-8501, Japan
Predictive Maps of Multi-Agent Reasoning: A Successor-Representation Spectrum for LLM Communication Topologies
May 12, 2026Ethan Parks, Dalal AlharthiMulti-Agent Systems Multi-Agent Communication Topology
University of Arizona
LLM-X: A Scalable Negotiation-Oriented Exchange for Communication Among Personal LLM Agents
May 12, 2026Giuliano Lorenzoni, Paulo Alencar, Donald CowanMulti-Agent LLM Systems Multi-Agent Coordination
University of Waterloo · University of Waterloo Waterloo, ON, Canada
Information and Contract Design for Repeated Interactions between Agents with Misaligned Incentives
May 11, 2026Nanda Kishore Sreenivas, Kate LarsonImperfect-Information Games Multi-Agent Communication
University of Waterloo
Priority-Driven Control and Communication in Decentralized Multi-Agent Systems via Reinforcement Learning
May 11, 2026Qingyun Guo, Junyi Shi, Tomasz Piotr Kucner +1Agent Communication Protocols Feedback Control
Department of Electrical Engineering and Automation, Aalto University, Espoo, Finland · Center for Artificial Intelligence, Helsinki, Finland
RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation
May 11, 2026Zhen Zhang, Wanjing Zhou, Juncheng Li +3Multi-Agent LLM Systems Multi-Agent System Optimization
National Key Laboratory for Novel Software Technology, Nanjing University, China · Zhejiang University · University of Oxford +1
TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems
May 10, 2026Chen Xu, Yicheng Hu, Ruizi Wang +4Multi-Agent LLM Systems Multi-Agent System Optimization
1Carnegie Mellon University · University of Science and Technology of China · 3National University of Singapore +1
Emergent Communication for Co-constructed Emotion Between Embodied Agents via Collective Predictive Coding
May 10, 2026Zehang Zhang, Nguyen Le Hoang, Tadahiro Taniguchi +1Computational Cognitive Modeling Predictive Coding
Graduate School of Engineering Science, The University of Osaka, Toyonaka 560-8531, Japan · Graduate School of Informatics, Kyoto University, Kyoto 606-8501, Japan
Robust Multi-Agent LLMs under Byzantine Faults
May 9, 2026Haejoon Lee, Vincent-Daniel Yun, Dimitra Panagou +1Multi-Agent LLM Systems Multi-Agent Coordination
Department of Robotics, University of Michigan, Ann Arbor, USA · Thomas Lord Department of Computer Science, University of Southern California, USA
AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators
May 9, 2026Aritra Mazumder, Shubhashis Roy Dipta, Nusrat Jahan Lia +10AI Agent Reliability Multi-Agent Collaboration
University of Utah · University of Maryland, Baltimore County · University of Dhaka +7
Generalization Bounds of Emergent Communications for Agentic AI Networking
May 9, 2026Yong Xiao, Jingxuan Chai, Guangming Shi +16G Networks Information Bottleneck
School of Elect. Inform. & Commun., Huazhong Univ. of Science & Technology, China · School of Artificial Intelligence, Xidian University, Xi’an, China · Peng Cheng Laboratory, Shenzhen, China +1
Too Many Specialists: Emergent Inefficiencies and Bottlenecks for Multi-agent Ad-hoc Collaboration
May 8, 2026Benjamin Panny, Shashank Mehrotra, Zahra Zahedi +2Multi-Agent Coordination Multi-Agent Collaboration
University of Pittsburgh Pittsburgh, PA, United States · Honda Research Institute USA, Inc. San Jose, CA, United States
What Software Engineering Looks Like to AI Agents? -- An Empirical Study of AI-Only Technical Discourse on MoltBook
May 8, 2026Junyu Huo, Ziqi Mao, Zihao Wan +1Software Engineering Agents Multi-Agent Communication
University of Calgary, Calgary, Alberta, Canada · Phanvic, Calgary, Alberta, Canada
The Reciprocity Gradient
May 8, 2026Yue Lin, Pascal Poupart, Shuhui Zhu +5Credit Assignment in RL Policy Gradient Methods
The Chinese University of Hong Kong, Shenzhen · LIGHTSPEED · University of Waterloo +2

May 21, 2026J/K move · Enter open · S save

SVR-MAD: A Bayesian-Inspired Framework for Posterior-Guided Multi-Agent Debate

Weifan Jiang, Rana Shahout, Minghao Li, Zhenting Qi+3

Harvard University

Multi-Agent LLM Systems Multi-Agent Debate Multi-Agent Communication

Open paper AskPDF arXiv

Multi-Agent Debate (MAD) improves LLM-agent accuracy but suffers from rapid context growth, limiting scalability in larger multi-agent settings. Existing methods prune low-utility communications using prior signals, such as token-level log-likelihoods or LLM self-reported confidence. However, these signals become unreliable under hallucination, degrading the accuracy of MAD methods that rely on them. We propose SVR-MAD, a Bayesian-inspired MAD framework that treats pre-debate signals as priors and debate outcomes as posterior-style evidence for estimating agent correctness. SVR-MAD uses this evidence to incrementally construct the communication graph, prioritizing agents whose answers survive peer challenges. Experiments across multiple LLMs and benchmarks show that SVR-MAD reduces token cost by up to 61% while matching or improving accuracy relative to the most accurate competing MAD baseline.