mlsanityData to 7 Oct 2026

EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms

arXiv 2406.14228 ↗First posted 20 Jun 2024cs.AIcited by 109

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

Abstract (arXiv)

The rise of powerful large language models (LLMs) has spurred a new trend in building LLM-based autonomous agents for solving complex tasks, especially multi-agent systems. Despite the remarkable progress, we notice that existing works are heavily dependent on human-designed frameworks, which greatly limits the functional scope and scalability of agent systems. How to automatically extend the specialized agent to multi-agent systems to improve task-solving capability still remains a significant challenge. In this paper, we introduce EvoAgent, a generic method to automatically extend specialized agents to multi-agent systems via the evolutionary algorithm, thereby improving the effectiveness of LLM-based agents in solving tasks. Specifically, we consider the existing agent frameworks as the initial individual and then apply a series of evolutionary operators (e.g., mutation, crossover, selection, etc.) to generate multiple agents with diverse settings. Experimental results across various tasks show that EvoAgent can significantly enhance the task-solving capability of LLM-based agents, and can be generalized to any LLM-based agent framework to extend them into multi-agent systems. Resources are available at https://evo-agent.github.io/.

Key facts. Cited by 109 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 28 of its 53 references that are in the map. First posted on arXiv 20 Jun 2024.

Builds on

28 of 53 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation8 Feb
  2. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agents2 Feb
  3. 2023AutoAgents: A Framework for Automatic Agent Generation29 Sep
  4. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors21 Aug
  5. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  6. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks27 May
  7. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 21

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  6. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  7. 2023MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGIcited by 2,044
  8. 2023The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)cited by 677
  9. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  10. 2014Memory Networkscited by 354
  11. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 298
  12. 2024From Persona to Personalization: A Survey on Role-Playing Language Agentscited by 206
9 more
  1. 2023EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizerscited by 189
  2. 2023InCharacter: Evaluating Personality Fidelity in Role-Playing Agents through Psychological Interviewscited by 177
  3. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instructioncited by 153
  4. 2023ExpertPrompting: Instructing Large Language Models to be Distinguished Expertscited by 140
  5. 2023TaskBench: Benchmarking Large Language Models for Task Automationcited by 138
  6. 2023EvoPrompting: Language Models for Code-Level Neural Architecture Searchcited by 129
  7. 2023MetaAgents: Large Language Model Based Agents for Decision-Making on Teamingcited by 85
  8. 2023Put Your Money Where Your Mouth Is: Evaluating Strategic Planning and Execution of LLM Agents in an Auction Arenacited by 78
  9. 2023Distilling Script Knowledge from Large Language Models for Constrained Language Planningcited by 45

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 53; 2026: 52.

109 papers.

Sort:

By area:

  1. 2024Automated Design of Agentic Systemscited by 360
  2. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 294
  3. 2025Multi-agent Architecture Search via Agentic Supernetcited by 164
  4. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  5. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Spacecited by 141
  6. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 112
  7. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  8. 2025A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systemscited by 108
  9. 2025Multi-Agent Collaboration via Evolving Orchestrationcited by 102
  10. 2025Agent-R: Training Language Model Agents to Reflect via Iterative Self-Trainingcited by 74
  11. 2025Evolving Deeper LLM Thinkingcited by 58
  12. 2025FlowReasoner: Reinforcing Query-Level Meta-Agentscited by 56
38 more
  1. 2025EvoFlow: Evolving Diverse Agentic Workflows On The Flycited by 49
  2. 2025EvoAgentX: An Automated Framework for Evolving Agentic Workflowscited by 43
  3. 2025EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systemscited by 34
  4. 2025Generative to Agentic AI: Survey, Conceptualization, and Challengescited by 32
  5. 2025Adaptive Graph Pruning for Multi-Agent Communicationcited by 28
  6. 2025A Comprehensive Survey on Multi-Agent Cooperative Decision-Making: Scenarios, Approaches, Challenges and Perspectivescited by 27
  7. 2025AutoPDL: Automatic Prompt Optimization for LLM Agentscited by 27
  8. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 27
  9. 2025MAS-ZERO: Designing Multi-Agent Systems with Zero Supervisioncited by 26
  10. 2025From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibriumcited by 24
  11. 2025Difficulty-Aware Agentic Orchestration for Query-Specific Multi-Agent Workflowscited by 23
  12. 2025SEW: Self-Evolving Agentic Workflows for Automated Code Generationcited by 18
  13. 2025SwarmAgentic: Towards Fully Automated Agentic System Generation via Swarm Intelligencecited by 17
  14. 2025MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machinescited by 17
  15. 2025Agent Exchange: Shaping the Future of AI Agent Economicscited by 15
  16. 2025Nature-Inspired Population-Based Evolution of Large Language Modelscited by 14
  17. 2025AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Searchcited by 14
  18. 2025AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvementcited by 13
  19. 2025TP-RAG: Benchmarking Retrieval-Augmented Large Language Model Agents for Spatiotemporal-Aware Travel Planningcited by 12
  20. 2025AdsQA: Towards Advertisement Video Understandingcited by 12
  21. 2025Blueprint First, Model Second: A Framework for Deterministic LLM Workflowcited by 11
  22. 2025AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaborationcited by 10
  23. 2025Alita-G: Self-Evolving Generative Agent for Agent Generationcited by 10
  24. 2026Mem2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillationcited by 10
  25. 2026JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolutioncited by 10
  26. 2025RETAIL: Towards Real-world Travel Planning for Large Language Modelscited by 9
  27. 2024ReDel: A Toolkit for LLM-Powered Recursive Multi-Agent Systemscited by 8
  28. 2025EvoEmo: Towards Evolved Emotional Policies for Adversarial LLM Agents in Multi-Turn Price Negotiationcited by 8
  29. 2025AgentArch: A Comprehensive Benchmark to Evaluate Agent Architectures in Enterprisecited by 8
  30. 2024LLM-Virus: Evolutionary Jailbreak Attack on Large Language Modelscited by 7
  31. 2025BOAD: Discovering Hierarchical Software Engineering Agents via Bandit Optimizationcited by 7
  32. 2026ABSTRAL: Automatic Design of Multi-Agent Systems Through Iterative Refinement and Topology Optimizationcited by 6
  33. 2025Tournament of Prompts: Evolving LLM Instructions Through Structured Debates and Elo Ratingscited by 5
  34. 2025Toward Autonomous Engineering Design: A Knowledge-Guided Multi-Agent Frameworkcited by 5
  35. 2026A-MapReduce: Executing Wide Search via Agentic MapReducecited by 5
  36. 2026RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generationcited by 5
  37. 2025Cross-Task Experiential Learning on LLM-based Multi-Agent Collaborationcited by 4
  38. 2025InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarioscited by 4

50 most cited of 109 All 109 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026EvoAgent: An Evolvable Agent Framework with Skill Learning and Multi-Agent Delegation
  2. 2024AgentGym: Evolving Large Language Model-based Agents across Diverse Environments
  3. 2024LLM2TEA: An Agentic AI Designer for Discovery with Generative Evolutionary Multitasking
  4. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challenges
  5. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges
  6. 2025SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
  7. 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
  8. 2025Multi-Agent Evolve: LLM Self-Improve through Co-evolution