Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
124 tokens/sec
GPT-4o
8 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Large Language Model based Multi-Agents: A Survey of Progress and Challenges (2402.01680v2)

Published 21 Jan 2024 in cs.CL, cs.AI, and cs.MA

Abstract: LLMs have achieved remarkable success across a wide array of tasks. Due to the impressive planning and reasoning abilities of LLMs, they have been used as autonomous agents to do many tasks automatically. Recently, based on the development of using one LLM as a single planning or decision-making agent, LLM-based multi-agent systems have achieved considerable progress in complex problem-solving and world simulation. To provide the community with an overview of this dynamic field, we present this survey to offer an in-depth discussion on the essential aspects of multi-agent systems based on LLMs, as well as the challenges. Our goal is for readers to gain substantial insights on the following questions: What domains and environments do LLM-based multi-agents simulate? How are these agents profiled and how do they communicate? What mechanisms contribute to the growth of agents' capacities? For those interested in delving into this field of study, we also summarize the commonly used datasets or benchmarks for them to have convenient access. To keep researchers updated on the latest studies, we maintain an open-source GitHub repository, dedicated to outlining the research on LLM-based multi-agent systems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (88)
  1. Evaluating multi-agent coordination abilities in large language models, 2023.
  2. Using large language models to simulate multiple humans and replicate human subject studies, 2023.
  3. Playing repeated games with large language models. arXiv preprint arXiv:2305.16867, 2023.
  4. Anonymous. Rethinking the buyer’s inspection paradox in information markets with language agents. In Submitted to The Twelfth International Conference on Learning Representations, 2023. under review.
  5. Chateval: Towards better llm-based evaluators through multi-agent debate, 2023.
  6. Autoagents: A framework for automatic agent generation. arXiv preprint arXiv:2309.17288, 2023.
  7. Multi-agent consensus seeking via large language models. arXiv preprint arXiv:2310.20151, 2023.
  8. Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors in agents. arXiv preprint arXiv:2308.10848, 2023.
  9. Scalable multi-robot collaboration with large language models: Centralized or decentralized systems? arXiv preprint arXiv:2309.15943, 2023.
  10. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168, 2021.
  11. Collaborating with language models for embodied reasoning. arXiv preprint arXiv:2302.00763, 2023.
  12. Victor Dibia. Multi-agent llm applications — a review of current research, tools, and challenges. https://newsletter.victordibia.com/p/multi-agent-llm-applications-a-review, 2023.
  13. A survey on in-context learning, 2023.
  14. Self-collaboration code generation via chatgpt, 2023.
  15. Improving factuality and reasoning in language models through multiagent debate, 2023.
  16. Can large language models serve as rational players in game theory? a systematic analysis. arXiv preprint arXiv:2312.05488, 2023.
  17. Agent-Based Modeling in Economics and Finance: Past, Present, and Future. INET Oxford Working Papers 2022-10, Institute for New Economic Thinking at the Oxford Martin School, University of Oxford, June 2022.
  18. S33{}^{3}start_FLOATSUPERSCRIPT 3 end_FLOATSUPERSCRIPT: Social-network simulation system with large language model-empowered agents. arXiv preprint arXiv:2307.14984, 2023.
  19. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997, 2023.
  20. Did aristotle use a laptop? a question answering benchmark with implicit reasoning strategies, 2021.
  21. Generative agent-based modeling: Unveiling social system dynamics through coupling mechanistic models with generative artificial intelligence. arXiv preprint arXiv:2309.11456, 2023.
  22. What indeed can gpt models do in chemistry? a comprehensive benchmark on eight tasks. arXiv preprint arXiv:2305.18365, 2023.
  23. Measuring massive multitask language understanding. arXiv preprint arXiv:2009.03300, 2020.
  24. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352, 2023.
  25. John J Horton. Large language models as simulated economic agents: What can we learn from homo silicus? Technical report, National Bureau of Economic Research, 2023.
  26. War and peace (waragent): Large language model-based multi-agent simulation of world wars, 2023.
  27. Agentcoder: Multi-agent-based code generation with iterative testing and optimisation, 2023.
  28. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. arXiv preprint arXiv:2311.05232, 2023.
  29. Lyfe agents: Generative agents for low-cost real-time social interactions. arXiv preprint arXiv:2310.02172, 2023.
  30. Decomposed prompting: A modular approach for solving complex tasks, 2023.
  31. The socialai school: Insights from developmental psychology towards artificial socio-cultural agents. arXiv preprint arXiv:2307.07871, 2023.
  32. Retrieval-augmented generation for knowledge-intensive nlp tasks, 2021.
  33. Psychology-informed recommender systems: A human-centric perspective on recommender systems. In Proceedings of the 2022 Conference on Human Information Interaction and Retrieval, CHIIR ’22, page 367–368, New York, NY, USA, 2022. Association for Computing Machinery.
  34. Quantifying the impact of large language models on collective opinion dynamics. arXiv preprint arXiv:2308.03313, 2023.
  35. Camel: Communicative agents for” mind” exploration of large scale language model society. arXiv preprint arXiv:2303.17760, 2023.
  36. Theory of mind for multi-agent collaboration via large language models, 2023.
  37. Api-bank: A comprehensive benchmark for tool-augmented llms, 2023.
  38. Large language model-empowered agents for simulating macroeconomic activities, 2023.
  39. Are you in a masquerade? exploring the behavior and impact of large language model driven social bots in online social networks. arXiv preprint arXiv:2307.10337, 2023.
  40. Tradinggpt: Multi-agent system with layered memory and distinct characters for enhanced financial trading performance, 2023.
  41. Metaagents: Simulating interactions of human behaviors for llm-based task-oriented coordination via collaborative generative agents. arXiv preprint arXiv:2310.06500, 2023.
  42. Let gpt be a math tutor: Teaching math word problem solvers with customized exercise generation. arXiv preprint arXiv:2305.14386, 2023.
  43. Avalonbench: Evaluating llms playing the game of avalon, 2023.
  44. From text to tactic: Evaluating llms playing the game of avalon. arXiv preprint arXiv:2310.05036, 2023.
  45. Dynamic llm-agent network: An llm-agent collaboration framework with agent team optimization. arXiv preprint arXiv:2310.02170, 2023.
  46. Understanding the benefits and challenges of using large language model-based conversational agents for mental well-being support. arXiv preprint arXiv:2307.15810, 2023.
  47. Roco: Dialectic multi-robot collaboration with large language models. arXiv preprint arXiv:2307.04738, 2023.
  48. Alympics: Language agents meet game theory. arXiv preprint arXiv:2311.03220, 2023.
  49. João Moura. Crewai. https://github.com/joaomdmoura/crewAI, 2023.
  50. Welfare diplomacy: Benchmarking language model cooperation. arXiv preprint arXiv:2310.08901, 2023.
  51. Self-adaptive large language model (llm)-based multiagent systems. In 2023 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C), pages 104–109. IEEE, 2023.
  52. Social simulacra: Creating populated prototypes for social computing systems. In Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology, pages 1–18, 2022.
  53. Generative agents: Interactive simulacra of human behavior. arXiv preprint arXiv:2304.03442, 2023.
  54. Communicative agents for software development, 2023.
  55. Tptu: Large language model-based ai agents for task planning and tool usage, 2023.
  56. Artificial Intelligence: A Modern Approach. Prentice Hall Press, USA, 3rd edition, 2009.
  57. Reflexion: Language agents with verbal reinforcement learning, 2023.
  58. Cognitive architectures for language agents. arXiv preprint arXiv:2309.02427, 2023.
  59. Medagents: Large language models as collaborators for zero-shot medical reasoning, 2023.
  60. Putting humans in the natural language processing loop: A survey, 2021.
  61. Adapting llm agents through communication, 2023.
  62. A survey on large language model based autonomous agents, 2023.
  63. Avalon’s game of thoughts: Battle against deception through recursive contemplation. arXiv preprint arXiv:2310.01320, 2023.
  64. Chain-of-thought prompting elicits reasoning in large language models. Advances in Neural Information Processing Systems, 35:24824–24837, 2022.
  65. Lilian Weng. Llm powered autonomous agents. https://lilianweng.github.io/posts/2023-06-23-agent/, 2023.
  66. Epidemic modeling with generative agents. arXiv preprint arXiv:2307.04986, 2023.
  67. Intelligent agents: theory and practice. The Knowledge Engineering Review, 10:115 – 152, 1995.
  68. Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155, 2023.
  69. Chatarena: Multi-agent language game environments for large language models. GitHub repository, 2023.
  70. The rise and potential of large language model based agents: A survey, 2023.
  71. Simulating public administration crisis: A novel generative agent-based simulation system to lower technology barriers in social science research. arXiv preprint arXiv:2311.06957, 2023.
  72. Openagents: An open platform for language agents in the wild. arXiv preprint arXiv:2310.10634, 2023.
  73. Examining inter-consistency of large language models collaboration: An in-depth analysis via debate, 2023.
  74. Magic: Investigation of large language model powered multi-agent in cognition, adaptability, rationality and collaboration, 2023.
  75. Exploring large language models for communication games: An empirical study on werewolf. arXiv preprint arXiv:2309.04658, 2023.
  76. Language agents with reinforcement learning for strategic play in the werewolf game. arXiv preprint arXiv:2310.18940, 2023.
  77. Tree of thoughts: Deliberate problem solving with large language models, 2023.
  78. Co-navgpt: Multi-robot cooperative visual semantic navigation using large language models, 2023.
  79. On generative agents in recommendation, 2023.
  80. Proagent: Building proactive cooperative ai with large language models. arXiv preprint arXiv:2308.11339, 2023.
  81. Building cooperative embodied agents modularly with large language models. arXiv preprint arXiv:2307.02485, 2023.
  82. Exploring collaboration mechanisms for llm agents: A social psychology view, 2023.
  83. Agentcf: Collaborative learning with autonomous language agents for recommender systems, 2023.
  84. Competeai: Understanding the competition behaviors in large language model-based agents, 2023.
  85. Chatgpt research group for optimizing the crystallinity of mofs and cofs. ACS Central Science, 9(11):2161–2170, 2023.
  86. Agents: An open-source framework for autonomous language agents. arXiv preprint arXiv:2309.07870, 2023.
  87. Sotopia: Interactive evaluation for social intelligence in language agents, 2023.
  88. Can large language models transform computational social science? Computational Linguistics, pages 1–53, 2023.
Citations (129)
View on Semantic Scholar

Summary

  • The paper reviews LLM-based multi-agent systems and their use in complex simulations and real-world tasks.
  • It examines components such as agent profiling, communication architectures, and dynamic capability acquisition.
  • It highlights challenges like scaling, agent hallucination, and evaluation standardization, pointing to future research directions.

LLM based Multi-Agents: A Survey of Progress and Challenges

Introduction to LLM-based Multi-Agent Systems

Recent advancements have led to the emergence of LLMs based Multi-Agent (LLM-MA) systems, showcasing notable progress in simulating complex real-world environments through multiple autonomous agents. These systems leverage the comprehensive knowledge base and generative capabilities of LLMs, enabling agents to engage in sophisticated interactions, problem-solving, and planning, akin to human group dynamics. This survey systematically reviews the current landscape of LLM-MA systems, focusing on their application domains, the mechanisms underlying agent interaction and evolution, and the challenges faced in scaling and effectively deploying these systems.

Dissecting LLM-MA Systems

To understand the intricacies of LLM-MA systems, it is imperative to examine their core components and mechanisms. This includes how agents perceive and interact with their environment, the methods for profiling agents to exhibit specific behaviors, the structure, and paradigms of agent communication, and the strategies for capability acquisition and enhancement.

  1. Agents-Environment Interface: The interface varies across applications, from sandbox environments for game simulations to physical environments for robotic tasks, impacting how agents perceive their surroundings and interact with the external world.
  2. Agent Profiling: Agents are differentiated through profiling, which defines their roles, skills, and behaviors within the system. Profiles can be predefined, derived from models, or based on dataset characteristics, aligning agents with specific tasks or scenarios.
  3. Agent Communication: Communication between agents is pivotal for collaborative problem-solving. It encompasses paradigms such as cooperative, debate, and competitive models, structures ranging from layered to decentralized networks, and the content of communication which is largely textual.
  4. Agent Capability Acquisition: Agents enhance their problem-solving abilities by learning from feedback—either from the environment, other agents, or human input—and through memory, self-evolution, and dynamic generation techniques.

Applications of LLM-MA Systems

LLM-MA systems find applications in diverse domains, each presenting unique challenges and benefiting differently from multi-agent collaborations.

  • Problem Solving: Encompasses software development, embodied agents, and scientific debates where agents work towards a common goal by leveraging their specializations.
  • World Simulation: Includes simulating societal dynamics, gaming environments, economic models, policy-making scenarios, and disease propagation, providing insights into complex behaviors and outcomes.

Implementation Frameworks and Resources

The development of LLM-MA systems is supported by various frameworks and tools designed to facilitate agent modeling, interaction, and simulation. These include MetaGPT, CAMEL, and Autogen, each offering different approaches to integrating LLMs into multi-agent settings. Ongoing efforts in the community aim to develop more comprehensive datasets and benchmarks tailored to specific applications, addressing the need for standardized evaluation metrics across diverse domains.

Challenges and Future Directions

Despite the promising developments in LLM-MA systems, significant challenges remain, including addressing agent hallucination, acquiring collective intelligence, scaling up systems to accommodate larger numbers of agents, and developing more nuanced evaluation methods. Future research is expected to explore these areas, pushing the boundaries of what LLM-MA systems can achieve and expanding their applicability across even broader spectrums of tasks and simulations. Additionally, theoretical perspectives from cognitive science, symbolic AI, and collective intelligence offer fertile grounds for enhancing our understanding and leveraging LLM-based multi-agents more effectively.

In conclusion, the exploration of LLM-based Multi-Agents stands at a fascinating juncture, with immense potential for advancing our capabilities in simulating, understanding, and solving complex problems. This survey underscores the significant progress made thus far, highlights the challenges ahead, and calls for continued interdisciplinary collaboration to unlock the full potential of LLM-MA systems.

Youtube Logo Streamline Icon: https://streamlinehq.com

YouTube