mlsanityData to 14 Oct 2026

G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks

arXiv 2410.11782 ↗First posted 15 Oct 2024cs.MA cs.LGcited by 119

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

Abstract (arXiv)

Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, primarily due to well-crafted inter-agent communication topologies. Despite the diverse and high-performing designs available, practitioners often face confusion when selecting the most effective pipeline for their specific task: textitWhich topology is the best choice for my task, avoiding unnecessary communication token overhead while ensuring high-quality solution? In response to this dilemma, we introduce G-Designer, an adaptive, efficient, and robust solution for multi-agent deployment, which dynamically designs task-aware, customized communication topologies. Specifically, G-Designer models the multi-agent system as a multi-agent network, leveraging a variational graph auto-encoder to encode both the nodes (agents) and a task-specific virtual node, and decodes a task-adaptive and high-performing communication topology. Extensive experiments on six benchmarks showcase that G-Designer is: (1) high-performing, achieving superior results on MMLU with accuracy at 84.50% and on HumanEval with pass@1 at 89.90%; (2) task-adaptive, architecting communication protocols tailored to task difficulty, reducing token consumption by up to 95.33% on HumanEval; and (3) adversarially robust, defending against agent adversarial attacks with merely 0.3% accuracy drop.

Key facts. Cited by 119 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 59 of its 85 references that are in the map. First posted on arXiv 15 Oct 2024.

Builds on

59 of 85 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems3 Oct
  2. 2024Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence9 Jul
  3. 2024Scaling Large Language Model-based Multi-Agent Collaboration11 Jun
  4. 2024More Agents Is All You Need3 Feb
  5. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects7 Jan
  6. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives19 Dec
  7. 2023The Rise and Potential of Large Language Model Based Agents: A Survey14 Sep
  8. 2023A Survey on Large Language Model based Autonomous Agents22 Aug
  9. 2023ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate14 Aug
  10. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework1 Aug
  11. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society31 Mar

Other references · 48

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  5. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  6. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  7. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  8. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  9. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  10. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  11. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  12. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
36 more
  1. 2020MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformerscited by 1,463
  2. 2016Variational Graph Auto-Encoderscited by 1,382
  3. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  4. 2021Are NLP Models really able to Solve Simple Math Word Problems?cited by 878
  5. 2023DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelinescited by 832
  6. 2019Graph Neural Networks for Social Recommendationcited by 714
  7. 2017Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problemscited by 650
  8. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 591
  9. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  10. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 388
  11. 2016Solving General Arithmetic Word Problemscited by 360
  12. 2019KGAT: Knowledge Graph Attention Network for Recommendationcited by 343
  13. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 312
  14. 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repaircited by 232
  15. 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology Viewcited by 222
  16. 2023Exphormer: Sparse Transformers for Graphscited by 170
  17. 2023LM vs LM: Detecting Factual Errors via Cross Examinationcited by 156
  18. 2023Self-Taught Optimizer (STOP): Recursively Self-Improving Code Generationcited by 148
  19. 2023Progressive-Hint Prompting Improves Reasoning in Large Language Modelscited by 147
  20. 2023War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Warscited by 145
  21. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 105
  22. 2024Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimizationcited by 84
  23. 2023Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communicationcited by 82
  24. 2023Corex: Pushing the Boundaries of Complex Reasoning through Multi-Model Collaborationcited by 70
  25. 2023LASER: LLM Agent with State-Space Exploration for Web Navigationcited by 66
  26. 2024Learning Multi-Agent Communication from Graph Modeling Perspectivecited by 48
  27. 2023Virtual Node Tuning for Few-shot Node Classificationcited by 46
  28. 2023GameGPT: Multi-agent Collaborative Framework for Game Developmentcited by 43
  29. 2023ChatLLM Network: More brains, More intelligencecited by 37
  30. 2023L2MAC: Large Language Model Automatic Computer for Extensive Code Generationcited by 30
  31. 2023Large Language Model as a Policy Teacher for Training Reinforcement Learning Agentscited by 30
  32. 2022Self-supervised Hypergraph Representation Learning for Sociological Analysiscited by 27
  33. 2024Depending on yourself when you should: Mentoring LLM with RL agents to become the master in cybersecurity gamescited by 20
  34. 2024Distinguished In Uniform: Self Attention Vs. Virtual Nodescited by 20
  35. 2024Computational Experiments Meet Large Language Model Based Agents: A Survey and Perspectivecited by 11
  36. 2020Learning Multi-Agent Coordination through Connectivity-driven Communicationcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 42; 2026: 76.

119 papers.

Sort:

By area:

  1. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  2. 2025Multi-agent Architecture Search via Agentic Supernetcited by 179
  3. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 122
  4. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 116
  5. 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systemscited by 90
  6. 2025FlowReasoner: Reinforcing Query-Level Meta-Agentscited by 63
  7. 2025ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimizationcited by 56
  8. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agentscited by 51
  9. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 50
  10. 2025ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Taskscited by 31
  11. 2025Internet of Agents: Fundamentals, Applications, and Challengescited by 31
  12. 2025Thought Communication in Multiagent Collaborationcited by 30
38 more
  1. 2025Adaptive Graph Pruning for Multi-Agent Communicationcited by 29
  2. 2025CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewardscited by 29
  3. 2025MAS-ZERO: Designing Multi-Agent Systems with Zero Supervisioncited by 28
  4. 2025We Should Identify and Mitigate Third-Party Safety Risks in MCP-Powered Agent Systemscited by 27
  5. 2026From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agentscited by 24
  6. 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systemscited by 23
  7. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  8. 2024FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preferencecited by 16
  9. 2025MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programmingcited by 16
  10. 2025AgentSwift: Efficient LLM Agent Design via Value-guided Hierarchical Searchcited by 15
  11. 2025SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agentscited by 15
  12. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systemscited by 15
  13. 2026EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answeringcited by 15
  14. 2025MASLab: A Unified and Comprehensive Codebase for LLM-based Multi-Agent Systemscited by 14
  15. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectscited by 14
  16. 2025Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flowcited by 13
  17. 2025Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Modelscited by 11
  18. 2025Stochastic Self-Organization in Multi-Agent Systemscited by 9
  19. 2026MetaGen: Self-Evolving Roles and Topologies for Multi-Agent LLM Reasoningcited by 9
  20. 2026CARD: Towards Conditional Design of Multi-agent Topological Structurescited by 9
  21. 2026SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topologycited by 9
  22. 2025Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AIcited by 8
  23. 2026Workflow-R1: Group Sub-sequence Policy Optimization for Multi-turn Workflow Constructioncited by 8
  24. 2026DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matchingcited by 8
  25. 2025Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstructioncited by 7
  26. 2026Scaling Discovery through Test-Time Communicationcited by 7
  27. 2025Agentic Services Computingcited by 6
  28. 2025On the Importance of Task Complexity in Evaluating LLM-Based Multi-Agent Systemscited by 6
  29. 2025VideoChat-M1: Collaborative Policy Planning for Video Understanding via Multi-Agent Reinforcement Learningcited by 6
  30. 2026ABSTRAL: Automatic Design of Multi-Agent Systems Through Iterative Refinement and Topology Optimizationcited by 6
  31. 2026Why Search When You Can Transfer? Amortized Agentic Workflow Design from Structural Priorscited by 6
  32. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 6
  33. 2025Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systemscited by 5
  34. 2026TodyComm: Task-Oriented Dynamic Communication for Multi-Round LLM-based Multi-Agent Systemcited by 5
  35. 2025The Society of HiveMind: Multi-Agent Optimization of Foundation Model Swarms to Unlock the Potential of Collective Intelligencecited by 4
  36. 2025Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaborationcited by 4
  37. 2026Learning Latency-Aware Orchestration for Multi-Agent Systemscited by 4
  38. 2026Phase Transition for Budgeted Multi-Agent Synergycited by 4

50 most cited of 119 All 119 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation
  2. 2026OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative Models
  3. 2026GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
  4. 2026PRISM: PRIvileged Sibling-guided Multi-Agent Topology Design
  5. 2026AgentConductor: Topology Evolution for Multi-Agent Competition-Level Code Generation
  6. 2025AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction
  7. 2026Graph-GRPO: Stabilizing Multi-Agent Topology Learning via Group Relative Policy Optimization
  8. 2026A Survey of Multi-Agent Deep Reinforcement Learning with Graph Neural Network-Based Communication