mlsanityData to 14 Oct 2026

LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning

arXiv 2605.18077 ↗First posted 18 May 2026cs.AI cs.LG cs.MAcited by 2

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 55 of its 69 references that are in the map. First posted on arXiv 18 May 2026.

Builds on

55 of 69 references.

Closest ancestors · 2

Same direction, newest first

  1. 2023LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models5 Oct
  2. 2023ExpeL: LLM Agents Are Experiential Learners20 Aug

Other references · 53

  1. 2017Attention Is All You Needcited by 60,361
  2. 2023GPT-4 Technical Reportcited by 18,396
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  7. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  8. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  9. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  10. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  11. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  12. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,407
38 more
  1. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
  2. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 694
  3. 2019The StarCraft Multi-Agent Challengecited by 597
  4. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 575
  5. 2023Eureka: Human-Level Reward Design via Coding Large Language Modelscited by 571
  6. 2017Value-Decomposition Networks For Cooperative Multi-Agent Learningcited by 503
  7. 2020Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learningcited by 485
  8. 2016Learning Multiagent Communication with Backpropagationcited by 366
  9. 2020QPLEX: Duplex Dueling Multi-Agent Q-Learningcited by 270
  10. 2019Google Research Football: A Novel Reinforcement Learning Environmentcited by 260
  11. 2022Pre-Trained Language Models for Interactive Decision-Makingcited by 221
  12. 2020Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Taskscited by 212
  13. 2018TarMAC: Targeted Multi-Agent Communicationcited by 208
  14. 2023Text2Reward: Reward Shaping with Language Models for Reinforcement Learningcited by 160
  15. 2022SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learningcited by 122
  16. 2018Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Taskscited by 121
  17. 2023Retroformer: Retrospective Large Language Agents with Policy Gradient Optimizationcited by 112
  18. 2022A Survey of Multi-Agent Deep Reinforcement Learning with Communicationcited by 104
  19. 2023Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Modelscited by 92
  20. 2024Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Modelscited by 91
  21. 2019Learning Nearly Decomposable Value Functions Via Communication Minimizationcited by 86
  22. 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
  23. 2023Language Instructed Reinforcement Learning for Human-AI Coordinationcited by 63
  24. 2020Learning Individually Inferred Communication for Multi-Agent Cooperationcited by 55
  25. 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learningcited by 49
  26. 2024Learning Multi-Agent Communication from Graph Modeling Perspectivecited by 48
  27. 2023Language Reward Modulation for Pretraining Reinforcement Learningcited by 43
  28. 2023Skill Reinforcement Learning and Planning for Open-World Long-Horizon Taskscited by 36
  29. 2023Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learningcited by 36
  30. 2020Succinct and Robust Multi-Agent Communication With Temporal Message Controlcited by 29
  31. 2024LLM-Empowered State Representation for Reinforcement Learningcited by 28
  32. 2023Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learningcited by 24
  33. 2023Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Modelscited by 22
  34. 2023LLM-State: Open World State Representation for Long-horizon Task Planning with Large Language Modelcited by 15
  35. 2025CTRL-O: Language-Controllable Object-Centric Visual Representation Learningcited by 12
  36. 2024T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integrationcited by 10
  37. 2022Consensus Learning for Cooperative Multi-Agent Reinforcement Learningcited by 8
  38. 2023Embodied Executable Policy Learning with Language-based Scene Summarizationcited by 6

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026A MARL Centered Reference Architecture for Large Language Model Augmentation in Smart Manufacturingcited by 0
  2. 2026Reinforcement Learning of Communication in a Mesh of Small Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-ALSO: LLM-Driven Adaptive Learning-Signal Optimization for Multi-Agent Reinforcement Learning
  2. 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs
  3. 2026Robust and Efficient Communication for Multi-Agent Learning
  4. 2024Generalising Multi-Agent Cooperation through Task-Agnostic Communication
  5. 2023Adapting LLM Agents with Universal Feedback in Communication
  6. 2024DCMAC: Demand-aware Customized Multi-Agent Communication via Upper Bound Training
  7. 2025Multi-Agent Reinforcement Learning with Communication-Constrained Priors
  8. 2026HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning