A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectives
cs.MA, cs.AI
Submitted: 2025-03-17
Updated: 2026-08-28
Comments: 54 pages, 24 figures
Code: https://github.com/vision-mini/MazeSolverLLM
Project page: https://mindagent.github.io
License: http://creativecommons.org/licenses/by/4.0/
The gist: With the rapid development of artificial intelligence, intelligent decision-making techniques have gradually surpassed human levels in various human-machine competitions, especially in complex
Terminology
Abstract
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.
Sources
- Playing Atari with Deep Reinforcement Learning
- Learning to Model Diverse Driving Behaviors in Highly Interactive Autonomous Driving Scenarios with Multi-Agent Reinforcement Learning
- Energy-Aware Ergodic Search: Continuous Exploration for Multi-Agent Systems with Battery Constraints
- Optimizing Search and Rescue UAV Connectivity in Challenging Terrain through Multi Q-Learning
- Utility Theory based Cognitive Modeling in the Application of Robotics: A Survey
- A Survey of Learning in Multiagent Environments: Dealing with Non-Stationarity
- A Game-Theoretic Learning Framework for Multi-Agent Intelligent Wireless Networks
- EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms
- Challenges Faced by Large Language Models in Solving Multi-Agent Flocking
- Emergence of Grounded Compositional Language in Multi-Agent Populations
- Measuring Policy Distance for Multi-Agent Reinforcement Learning
- Multi-Target Pursuit by a Decentralized Heterogeneous UAV Swarm using Deep Multi-Agent Reinforcement Learning
- Efficient Distributed Framework for Collaborative Multi-Agent Reinforcement Learning
- CoAct: A Global-Local Hierarchy for Autonomous Agent Collaboration
- AgentScope: A Flexible yet Robust Multi-Agent Platform
- MLLM-Tool: A Multimodal Large Language Model For Tool Agent Learning
- Data Interpreter: An LLM Agent For Data Science
- Intelligent Spark Agents: A Modular LangGraph Framework for Scalable, Visualized, and Enhanced Big Data Machine Learning Workflows
- Agent AI with LangGraph: A Modular Framework for Enhancing Machine Translation Using Large Language Models
- PlanAgent: A Multi-modal Large Language Agent for Closed-loop Vehicle Motion Planning
Related papers
- Highway Congestion Reduction through Reinforcement Learning Based Eulerian Headway Control
- You Only Align Once: Propagating Cooperative Behaviors in Multi-Agent Systems through Seed Agents
- Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems
- MA-SAPO: Multi-Agent Reasoning for Score-Aware Prompt Optimization
- PeroMAS: A Multi-agent System of Perovskite Material Discovery
- StitchCUDA: An Automated Multi-Agents End-to-End GPU Programing Framework with Rubric-based Agentic Reinforcement Learning