mlsanityData to 14 Oct 2026

Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures

arXiv 2604.18133 ↗First posted 20 Apr 2026cs.AIcited by 0

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

Abstract (arXiv)

With the rapid advancement of artificial intelligence, multi-agent systems (MASs) are evolving from classical paradigms toward architectures built upon large foundation models (LFMs). This survey provides a systematic review and comparative analysis of classical MASs (CMASs) and LFM-based MASs (LMASs). First, within a closed-loop coordination framework, CMASs are reviewed across four fundamental dimensions: perception, communication, decision-making, and control. Beyond this framework, LMASs integrate LFMs to lift collaboration from low-level state exchanges to semantic-level reasoning, enabling more flexible coordination and improved adaptability across diverse scenarios. Then, a comparative analysis is conducted to contrast CMASs and LMASs across architecture, operating mechanism, adaptability, and application. Finally, future perspectives on MASs are presented, summarizing open challenges and potential research opportunities.

Key facts. No citing papers in the map yet (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 98 of its 151 references that are in the map. First posted on arXiv 20 Apr 2026.

Builds on

98 of 151 references.

Closest ancestors · 30

Same direction, newest first

  1. 2025Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions29 Oct
  2. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards9 Oct
  3. 2025Stochastic Self-Organization in Multi-Agent Systems1 Oct
  4. 2025Contemporary Agent Technology: LLM-Driven Advancements vs Classic Multi-Agent Systems2 Sep
  5. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios25 Aug
  6. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users24 Aug
  7. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review28 Apr
  8. 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems1 Apr
  9. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems31 Mar
  10. 2025A Survey on the Optimization of Large Language Model-based Agents16 Mar
  11. 2025ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks4 Mar
  12. 2025Multi-Agent Coordination across Diverse Applications: A Survey20 Feb
18 more
  1. 2025Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems20 Feb
  2. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMs10 Jan
  3. 2024Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration20 Dec
  4. 2024Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance16 Oct
  5. 2024AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML3 Oct
  6. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems3 Oct
  7. 2024Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface30 Sep
  8. 2024Automated Design of Agentic Systems15 Aug
  9. 2024AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation1 Aug
  10. 2024Scaling Large Language Model-based Multi-Agent Collaboration11 Jun
  11. 2024Mixture-of-Agents Enhances Large Language Model Capabilities7 Jun
  12. 2024Agent Planning with World Knowledge Model23 May
  13. 2024A Survey on Context-Aware Multi-Agent Systems: Techniques, Challenges and Future Directions3 Feb
  14. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  15. 2023Theory of Mind for Multi-Agent Collaboration via Large Language Models16 Oct
  16. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors21 Aug
  17. 2023ExpeL: LLM Agents Are Experiential Learners20 Aug
  18. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug

Other references · 68

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  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. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  7. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  8. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  9. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  10. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  11. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  12. 2023ChatDev: Communicative Agents for Software Developmentcited by 919
38 more
  1. 2023Large Language Modelscited by 780
  2. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 634
  3. 2023Instruction Tuning for Large Language Models: A Surveycited by 623
  4. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 386
  5. 2022DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 273
  6. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  7. 2024TradingAgents: Multi-Agents LLM Financial Trading Frameworkcited by 188
  8. 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 172
  9. 2019Cooper: Cooperative Perception for Connected Autonomous Vehicles based on 3D Point Cloudscited by 165
  10. 2024OASIS: Open Agent Social Interaction Simulations with One Million Agentscited by 132
  11. 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendationscited by 131
  12. 2024Web Agents with World Models: Learning and Leveraging Environment Dynamics in Web Navigationcited by 126
  13. 2025Agent Lightning: Train ANY AI Agents with Reinforcement Learningcited by 109
  14. 2025A Survey of LLM-based Agents in Medicine: How far are we from Baymax?cited by 85
  15. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 83
  16. 2024World Models for Autonomous Driving: An Initial Surveycited by 80
  17. 2023ISR-LLM: Iterative Self-Refined Large Language Model for Long-Horizon Sequential Task Planningcited by 77
  18. 2024Self-Evolving Multi-Agent Collaboration Networks for Software Developmentcited by 74
  19. 2025AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learningcited by 72
  20. 2024LLM-based Multi-Agent Reinforcement Learning: Current and Future Directionscited by 67
  21. 2025SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Userscited by 55
  22. 2023Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perceptioncited by 52
  23. 2024COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Modelscited by 45
  24. 2023CGMI: Configurable General Multi-Agent Interaction Frameworkcited by 42
  25. 2023A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environmentcited by 39
  26. 2025Multi-agent Embodied AI: Advances and Future Directionscited by 36
  27. 2021Applications of Multi-Agent Reinforcement Learning in Future Internet: A Comprehensive Surveycited by 34
  28. 2023Multi-agent Reinforcement Learning: A Comprehensive Surveycited by 33
  29. 2025Removal of Hallucination on Hallucination: Debate-Augmented RAGcited by 29
  30. 2025RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaborationcited by 28
  31. 2025A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectivescited by 27
  32. 2024Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trendscited by 26
  33. 2024CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaborationcited by 25
  34. 2025OS-Kairos: Adaptive Interaction for MLLM-Powered GUI Agentscited by 25
  35. 2025Monte Carlo Planning with Large Language Model for Text-Based Game Agentscited by 22
  36. 2022Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-worldcited by 17
  37. 2025PolyTouch: A Robust Multi-Modal Tactile Sensor for Contact-rich Manipulation Using Tactile-Diffusion Policiescited by 14
  38. 2025Edge-Cloud Collaborative Computing on Distributed Intelligence and Model Optimization: A Surveycited by 14

50 most cited of 68 All 68 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Scaling LLM-Driven Multi-Agent Systems: Design Principles and Architectural Scalability Analysis
  2. 2026LLM-Enabled Multi-Agent Systems: Empirical Evaluation and Insights into Emerging Design Patterns & Paradigms
  3. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  4. 2025X-MAS: Towards Building Multi-Agent Systems with Heterogeneous LLMs
  5. 2025Advancing Multi-Agent Systems Through Model Context Protocol: Architecture, Implementation, and Applications
  6. 2026Scaling Behavior of Single LLM-Driven Multi-Agent Systems
  7. 2025Designing LLM-based Multi-Agent Systems for Software Engineering Tasks: Quality Attributes, Design Patterns and Rationale
  8. 2025Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems