mlsanityData to 14 Oct 2026

MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines

arXiv 2507.22606 ↗First posted 30 Jul 2025cs.AIcited by 22

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

Abstract (arXiv)

Large Language Models (LLMs) have demonstrated the ability to solve a wide range of practical tasks within multi-agent systems. However, existing human-designed multi-agent frameworks are typically limited to a small set of pre-defined scenarios, while current automated design methods suffer from several limitations, such as the lack of tool integration, dependence on external training data, and rigid communication structures. In this paper, we propose MetaAgent, a finite state machine based framework that can automatically generate a multi-agent system. Given a task description, MetaAgent will design a multi-agent system and polish it through an optimization algorithm. When the multi-agent system is deployed, the finite state machine will control the agent's actions and the state transitions. To evaluate our framework, we conduct experiments on both text-based tasks and practical tasks. The results indicate that the generated multi-agent system surpasses other auto-designed methods and can achieve a comparable performance with the human-designed multi-agent system, which is optimized for those specific tasks.

Key facts. Cited by 22 papers in the map (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 24 of its 34 references that are in the map. First posted on arXiv 30 Jul 2025.

Builds on

24 of 34 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence9 Jul
  2. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms20 Jun
  3. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  4. 2023State Machine of Thoughts: Leveraging Past Reasoning Trajectories for Enhancing Problem Solving29 Dec
  5. 2023AutoAgents: A Framework for Automatic Agent Generation29 Sep
  6. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  7. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  8. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration11 Jul

Other references · 16

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,442
  7. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  9. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  10. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  11. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  12. 2023MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedbackcited by 297
4 more
  1. 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolfcited by 241
  2. 2024How Well Can LLMs Negotiate? NegotiationArena Platform and Analysiscited by 100
  3. 2024StateFlow: Enhancing LLM Task-Solving through State-Driven Workflowscited by 65
  4. 2024Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity gamescited by 20

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 20.

22 papers.

Sort:

By area:

  1. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  2. 2025PaperArena: An Evaluation Benchmark for Tool-Augmented Agentic Reasoning on Scientific Literaturecited by 15
  3. 2025Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systemscited by 12
  4. 2026The Illusion of Multi-Agent Advantagecited by 9
  5. 2026EvoMAS: Evolutionary Generation of Multi-Agent Systemscited by 5
  6. 2026TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systemscited by 5
  7. 2026Automata from Agent Traces: Failure and Next-Step Predictioncited by 3
  8. 2026MetaAgent-X : Breaking the Ceiling of Automatic Multi-Agent Systems via End-to-End Reinforcement Learningcited by 2
  9. 2026AutoMS: Multi-Agent Evolutionary Search for Cross-Physics Inverse Microstructure Designcited by 1
  10. 2026Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Researchcited by 1
  11. 2026EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systemscited by 1
  12. 2026When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systemscited by 1
10 more
  1. 2026Structure Matters: Evaluating Multi-Agents Orchestration in Generative Therapeutic Chatbotscited by 0
  2. 2026Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Long-Horizon Workflowscited by 0
  3. 2026From Intent to Execution: Composing Agentic Workflows with Agent Recommendationcited by 0
  4. 2026The Right Lesson at the Right Step: Deriving Control Updates for Self-Evolving Agentscited by 0
  5. 2026It Takes Workflows to Evolve Better Workflowscited by 0
  6. 2026Decoupled Multi-Agent Orchestrationcited by 0
  7. 2026ST-Bench: A Spatial-Temporal Benchmark for Multi-Agent System Generation on Scientific Research Taskscited by 0
  8. 2026OOPMAS: Object-Oriented Multi-Agent Systems for Query-Level Workflow Generationcited by 0
  9. 2026WorkflowOps: Learning Agent Collaboration Priors for Multi-Agent Workflow Orchestrationcited by 0
  10. 2026CB-Orchestrator: Adaptive Workflow Optimization for LLM Agents via Contextual Banditscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review
  2. 2024A Survey on LLM-based Multi-Agent System: Recent Advances and New Frontiers in Application
  3. 2025MAS2: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems
  4. 2024Automated Design of Agentic Systems
  5. 2026Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning
  6. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  7. 2025AutoAgent: A Fully-Automated and Zero-Code Framework for LLM Agents
  8. 2025Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies