mlsanityData to 7 Oct 2026

AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems

arXiv 2504.00587 ↗First posted 1 Apr 2025cs.MA cs.CLcited by 86

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

Abstract (arXiv)

The rapid advancement of large language models (LLMs) has enabled the development of multi-agent systems where multiple LLM-based agents collaborate on complex tasks. However, existing systems often rely on centralized coordination, leading to scalability bottlenecks, reduced adaptability, and single points of failure. Privacy and proprietary knowledge concerns further hinder cross-organizational collaboration, resulting in siloed expertise. We propose AgentNet, a decentralized, Retrieval-Augmented Generation (RAG)-based framework that enables LLM-based agents to specialize, evolve, and collaborate autonomously in a dynamically structured Directed Acyclic Graph (DAG). Unlike prior approaches with static roles or centralized control, AgentNet allows agents to adjust connectivity and route tasks based on local expertise and context. AgentNet introduces three key innovations: (1) a fully decentralized coordination mechanism that eliminates the need for a central orchestrator, enhancing robustness and emergent intelligence; (2) dynamic agent graph topology that adapts in real time to task demands, ensuring scalability and resilience; and (3) a retrieval-based memory system for agents that supports continual skill refinement and specialization. By minimizing centralized control and data exchange, AgentNet enables fault-tolerant, privacy-preserving collaboration across organizations. Experiments show that AgentNet achieves higher task accuracy than both single-agent and centralized multi-agent baselines.

Key facts. Cited by 86 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 25 of its 36 references that are in the map. First posted on arXiv 1 Apr 2025.

Builds on

25 of 36 references.

Closest ancestors · 9

Same direction, newest first

  1. 2024MorphAgent: Empowering Agents through Self-Evolving Profiles and Decentralized Collaboration19 Oct
  2. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks15 Oct
  3. 2024AgentSquare: Automatic LLM Agent Search in Modular Design Space8 Oct
  4. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems3 Oct
  5. 2024TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned Decision10 Mar
  6. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges21 Jan
  7. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration3 Oct
  8. 2023AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors21 Aug
  9. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug

Other references · 16

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  5. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  6. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
  7. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,767
  8. 2021Measuring Coding Challenge Competence With APPScited by 879
  9. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 803
  10. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  11. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  12. 2024AFlow: Automating Agentic Workflow Generationcited by 395
4 more
  1. 2024Self-Evolving Multi-Agent Collaboration Networks for Software Developmentcited by 73
  2. 2024LLM-based Multi-Agent Reinforcement Learning: Current and Future Directionscited by 67
  3. 2025Understanding and Optimizing Agentic Workflows via Shapley valuecited by 9
  4. 2025Privacy-Enhancing Paradigms within Federated Multi-Agent Systemscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 24; 2026: 62.

86 papers.

Sort:

By area:

  1. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automationcited by 129
  2. 2025Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agentscited by 52
  3. 2025MARFT: Multi-Agent Reinforcement Fine-Tuningcited by 51
  4. 2025Agentic Web: Weaving the Next Web with AI Agentscited by 43
  5. 2026Multi-Agent Teams Hold Experts Backcited by 16
  6. 2025Survey of LLM Agent Communication with MCP: A Software Design Pattern Centric Reviewcited by 14
  7. 2025Maestro: Learning to Collaborate via Conditional Listwise Policy Optimization for Multi-Agent LLMscited by 14
  8. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systemscited by 12
  9. 2025SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generationcited by 11
  10. 2025How to Train a Leader: Hierarchical Reasoning in Multi-Agent LLMscited by 11
  11. 2026Toward Efficient Agents: Memory, Tool learning, and Planningcited by 11
  12. 2026Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systemscited by 11
38 more
  1. 2025Stochastic Self-Organization in Multi-Agent Systemscited by 9
  2. 2025Distributional AGI Safetycited by 8
  3. 2026Information-Theoretic Privacy Control for Sequential Multi-Agent LLM Systemscited by 8
  4. 2026Learning Decentralized LLM Collaboration with Multi-Agent Actor Criticcited by 7
  5. 2026DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviorscited by 7
  6. 2025Agentic Services Computingcited by 6
  7. 2026Self-Evolving Multi-Agent Systems via Decentralized Memorycited by 6
  8. 2026LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systemscited by 6
  9. 2026MonoScale: Scaling Multi-Agent System with Monotonic Improvementcited by 5
  10. 2026SMMBench: A Benchmark for Source-Distributed Multimodal Agent Memorycited by 5
  11. 2026Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveriescited by 5
  12. 2025PhenoAssistant: A Conversational Multi-Agent AI System for Automated Plant Phenotypingcited by 4
  13. 2025Multi-level Value Alignment in Agentic AI Systems: Survey and Perspectivescited by 4
  14. 2025Generalizing Test-time Compute-optimal Scaling as an Optimizable Graphcited by 4
  15. 2025Optimizing PyTorch Inference with LLM-Based Multi-Agent Systemscited by 4
  16. 2026Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspectivecited by 4
  17. 2026AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Taskscited by 3
  18. 2026EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scalescited by 3
  19. 2026Characterization of Multi-Model Agentic AI Systems on General Tasks via Trace-Driven Simulationcited by 3
  20. 2026Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactionscited by 3
  21. 2026Distributed General-Purpose Agent Networks: Architecture, Key Mechanisms, and Prototypescited by 3
  22. 2025Structuring the Unstructured: A Multi-Agent System for Extracting and Querying Financial KPIs and Guidancecited by 2
  23. 2025An Auditable Agent Platform For Automated Molecular Optimisationcited by 2
  24. 2025SEVADE: Self-Evolving Multi-Agent Analysis with Decoupled Evaluation for Hallucination-Resistant Irony Detectioncited by 2
  25. 2025Hierarchical Decentralized Multi-Agent Coordination with Privacy-Preserving Knowledge Sharing: Extending AgentNet for Scalable Autonomous Systemscited by 2
  26. 2026Cost and Accuracy of Long-Term Memory in Distributed Multi-Agent Systems Based on Large Language Modelscited by 2
  27. 2026Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrievalcited by 2
  28. 2026AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Webcited by 2
  29. 2026Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systemscited by 2
  30. 2025From Large AI Models to Agentic AI: A Tutorial on Future Intelligent Communicationscited by 1
  31. 2025A Decentralized Retrieval Augmented Generation System with Source Reliabilities Secured on Blockchaincited by 1
  32. 2026Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agentscited by 1
  33. 2026SUN: Shared Use of Next-token Prediction for Efficient Multi-LLM Disaggregated Servingcited by 1
  34. 2026Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generationcited by 1
  35. 2026Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systemscited by 1
  36. 2026Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM Agentscited by 1
  37. 2026SGTO-MAS: Secure Gorilla Troops Optimization for Multi-Agent LLM Systemscited by 1
  38. 2026How Task Structure Limits Multi-Agent Success: An Information-Theoretic Analysiscited by 1

50 most cited of 86 All 86 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025AgentsNet: Coordination and Collaborative Reasoning in Multi-Agent LLMs
  2. 2025LLMs Working in Harmony: A Survey on the Technological Aspects of Building Effective LLM-Based Multi Agent Systems
  3. 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
  4. 2026Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
  5. 2025AMAS: Adaptively Determining Communication Topology for LLM-based Multi-Agent System
  6. 2024AgentCoord: Visually Exploring Coordination Strategy for LLM-based Multi-Agent Collaboration
  7. 2025Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems
  8. 2026AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation