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

2025-03-17

AI Summary

This paper addresses key challenges in multi-agent collaborative decision-making for complex real-world applications—including autonomous driving, drone swarm coordination, and disaster response. To this end, it establishes a tripartite analytical framework integrating simulation environments, algorithmic models, and evaluation dimensions. It pioneers the classification of large language model (LLM)-based multi-step collaborative reasoning and deep multi-agent reinforcement learning (MARL) as two complementary frontier paradigms, proposing a unified methodology taxonomy and a technical comparison matrix. Through bibliometric analysis, cross-platform simulation (MPE, PettingZoo, MAgent), MARL lineage modeling, and LLM case decomposition, the work synthesizes five evolutionary methodological trajectories and identifies six open challenges: scalability, credit assignment, human-AI alignment, among others. The study delivers both a theoretical foundation and a practical roadmap for next-generation collaborative intelligent systems.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Intelligent Robots: Multi-Robot Systems
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

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.

Problem

• Survey multi-agent cooperative decision-making scenarios and approaches.
• Analyze simulation environments for task formats and reward allocation.
• Focus on MARL and LLMs-based methods, discussing their advantages and challenges.

Innovation

• Deep multi-agent reinforcement learning (MARL) techniques
• Large language models (LLMs) reasoning-based methods
• Comprehensive analysis of simulation environments and platforms