mlsanityData to 14 Oct 2026

A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives

arXiv 2503.13415 ↗First posted 17 Mar 2025cs.MA cs.AIcited by 27

On the map: LLM agents and tool use → Reinforcement learning for LLM agents

Abstract (arXiv)

With the rapid development of artificial intelligence, intelligent decision-making techniques have gradually surpassed human levels in various human-machine competitions, especially in complex multi-agent cooperative task scenarios. Multi-agent cooperative decision-making involves multiple agents working together to complete established tasks and achieve specific objectives. These techniques are widely applicable in real-world scenarios such as autonomous driving, drone navigation, disaster rescue, and simulated military confrontations. This paper begins with a comprehensive survey of the leading simulation environments and platforms used for multi-agent cooperative decision-making. Specifically, we provide an in-depth analysis for these simulation environments from various perspectives, including task formats, reward allocation, and the underlying technologies employed. Subsequently, we provide a comprehensive overview of the mainstream intelligent decision-making approaches, algorithms and models for multi-agent systems (MAS). Theseapproaches can be broadly categorized into five types: rule-based (primarily fuzzy logic), game theory-based, evolutionary algorithms-based, deep multi-agent reinforcement learning (MARL)-based, and large language models(LLMs)reasoning-based. Given the significant advantages of MARL andLLMs-baseddecision-making methods over the traditional rule, game theory, and evolutionary algorithms, this paper focuses on these multi-agent methods utilizing MARL and LLMs-based techniques. We provide an in-depth discussion of these approaches, highlighting their methodology taxonomies, advantages, and drawbacks. Further, several prominent research directions in the future and potential challenges of multi-agent cooperative decision-making are also detailed.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use. Builds on 99 of its 341 references that are in the map. First posted on arXiv 17 Mar 2025.

Builds on

99 of 341 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025DVM: Towards Controllable LLM Agents in Social Deduction Games12 Jan
  2. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory25 May

Other references · 97

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  7. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  8. 2016OpenAI Gymcited by 1,736
  9. 2023Gemini: A Family of Highly Capable Multimodal Modelscited by 872
  10. 2016Learning to Communicate with Deep Multi-Agent Reinforcement Learningcited by 575
  11. 2015Deep Recurrent Q-Learning for Partially Observable MDPscited by 465
  12. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 431
38 more
  1. 2023Multi-Agent Collaboration: Harnessing the Power of Intelligent LLM Agentscited by 333
  2. 2023Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Taskscited by 327
  3. 2023Language to Rewards for Robotic Skill Synthesiscited by 312
  4. 2020Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?cited by 294
  5. 2017StarCraft II: A New Challenge for Reinforcement Learningcited by 274
  6. 2017Emergence of Grounded Compositional Language in Multi-Agent Populationscited by 263
  7. 2018Unity: A General Platform for Intelligent Agentscited by 236
  8. 2021Trust Region Policy Optimisation in Multi-Agent Reinforcement Learningcited by 186
  9. 2020FACMAC: Factored Multi-Agent Centralised Policy Gradientscited by 178
  10. 2017Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learningcited by 150
  11. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 121
  12. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithmscited by 113
  13. 2021Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Potcited by 99
  14. 2017Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Gamescited by 96
  15. 2017A Survey of Learning in Multiagent Environments: Dealing with Non-Stationaritycited by 94
  16. 2024Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunitiescited by 83
  17. 2024MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learningcited by 69
  18. 2023Learning to Model the World with Languagecited by 68
  19. 2023Automating Customer Service using LangChain: Building custom open-source GPT Chatbot for organizationscited by 61
  20. 2023Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraftcited by 61
  21. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Applicationcited by 55
  22. 2024An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learningcited by 50
  23. 2025Distilling Multi-modal Large Language Models for Autonomous Drivingcited by 46
  24. 2023AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agentscited by 41
  25. 2024SciAssess: Benchmarking LLM Proficiency in Scientific Literature Analysiscited by 41
  26. 2024PlanAgent: A Multi-modal Large Language Agent for Closed-loop Vehicle Motion Planningcited by 38
  27. 2023Self-Refined Large Language Model as Automated Reward Function Designer for Deep Reinforcement Learning in Roboticscited by 36
  28. 2024Exploration of LLM Multi-Agent Application Implementation Based on LangGraph+CrewAIcited by 35
  29. 2024Multi-Agent Reinforcement Learning for Autonomous Driving: A Surveycited by 32
  30. 2024Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Modelscited by 28
  31. 2024A Survey on Context-Aware Multi-Agent Systems: Techniques, Challenges and Future Directionscited by 27
  32. 2024Agents4PLC: Automating Closed-loop PLC Code Generation and Verification in Industrial Control Systems using LLM-based Agentscited by 26
  33. 2025Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directionscited by 23
  34. 2016Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networkscited by 21
  35. 2024The emergence of Large Language Models (LLM) as a tool in literature reviews: an LLM automated systematic reviewcited by 21
  36. 2024AutoGen Studio: A No-Code Developer Tool for Building and Debugging Multi-Agent Systemscited by 20
  37. 2023Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?cited by 18
  38. 2024GAMEBoT: Transparent Assessment of LLM Reasoning in Gamescited by 17

50 most cited of 97 All 97 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 12; 2026: 15.

27 papers.

Sort:

By area:

  1. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 205
  2. 2025Internet of Agents: Fundamentals, Applications, and Challengescited by 31
  3. 2026One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligencecited by 7
  4. 2025One Step is Enough: Multi-Agent Reinforcement Learning based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platformscited by 5
  5. 2026Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decompositioncited by 5
  6. 2025Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?cited by 4
  7. 2025Agent-as-a-Service based on Agent Networkcited by 3
  8. 2025Can LLM Agents Solve Collaborative Tasks? A Study on Urgency-Aware Planning and Coordinationcited by 3
  9. 2026Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimizationcited by 3
  10. 2025Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learningcited by 2
  11. 2025DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaborationcited by 2
  12. 2026Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensuscited by 2
15 more
  1. 2026Towards Next-Generation Healthcare: A Survey of Medical Embodied AI for Perception, Decision-Making, and Actioncited by 2
  2. 2025Overcoming Environmental Meta-Stationarity in MARL via Adaptive Curriculum and Counterfactual Group Advantagecited by 1
  3. 2025What Would an LLM Do? Evaluating Large Language Models for Policymaking to Alleviate Homelessnesscited by 1
  4. 2025Can Agents Judge Systematic Reviews Like Humans? Evaluating SLRs with LLM-based Multi-Agent Systemcited by 1
  5. 2026MARO: Learning Stronger Reasoning from Social Interactioncited by 1
  6. 2026Self-Evolving Multi-Agent Network for Industrial IoT Predictive Maintenancecited by 1
  7. 2026Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modelingcited by 1
  8. 2025ToMPO: Training LLM Strategic Decision Making from a Multi-Agent Perspectivecited by 0
  9. 2026A self-evolving multi-role collaborative framework with fine-grained difficulty guidance for innovative mathematical problem generationcited by 0
  10. 2026DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoningcited by 0
  11. 2026Story2Proposal: A Scaffold for Structured Scientific Paper Writingcited by 0
  12. 2026Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learningcited by 0
  13. 2026Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futurescited by 0
  14. 2026Aggregate in the Advantage, Not the Ratio: A Canonical-Form Analysis of Cooperative Multi-Agent Policy Optimizationcited by 0
  15. 2026RideSkill: A Hierarchical Algorithm for Generalized Ride Sharing with LLM-Driven Automatic Evolutioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025An Extended Benchmarking of Multi-Agent Reinforcement Learning Algorithms in Complex Fully Cooperative Tasks
  2. 2024Fully Decentralized Cooperative Multi-Agent Reinforcement Learning: A Survey
  3. 2025CTC: The Composite Task Challenge for Cooperative Multi-Agent Reinforcement Learning
  4. 2024Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmas
  5. 2024Multi-Agent Reinforcement Learning with a Hierarchy of Reward Machines
  6. 2024Language-Driven Policy Distillation for Cooperative Driving in Multi-Agent Reinforcement Learning
  7. 2025A Survey of Multi Agent Reinforcement Learning: Federated Learning and Cooperative and Noncooperative Decentralized Regimes
  8. 2025Goal-Oriented Multi-Agent Reinforcement Learning for Decentralized Agent Teams