# Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation

arXiv: https://arxiv.org/abs/2507.18224 · HTML: https://mlsanity.com/paper/2507.18224/

## Key facts

- Cited by 58 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 26 of its 43 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 26 of 26)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Are NLP Models really able to Solve Simple Math Word Problems?](https://mlsanity.com/paper/2103.07191/) (2021)
- [Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems](https://mlsanity.com/paper/1705.04146/) (2017)
- [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models](https://mlsanity.com/paper/1802.08773/) (2018)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [Efficient Graph Generation with Graph Recurrent Attention Networks](https://mlsanity.com/paper/1910.00760/) (2019)
- [Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding](https://mlsanity.com/paper/2401.04398/) (2024)
- [Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step](https://mlsanity.com/paper/2402.16906/) (2024)
- [Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies](https://mlsanity.com/paper/2502.02533/) (2025)
- [Autoregressive Diffusion Model for Graph Generation](https://mlsanity.com/paper/2307.08849/) (2023)
- [Exchange-of-Thought: Enhancing Large Language Model Capabilities through Cross-Model Communication](https://mlsanity.com/paper/2312.01823/) (2023)
- [GraphGen: A Scalable Approach to Domain-agnostic Labeled Graph Generation](https://mlsanity.com/paper/2001.08184/) (2020)
- [Scalable Deep Generative Modeling for Sparse Graphs](https://mlsanity.com/paper/2006.15502/) (2020)
- [Are Large Language Models Good Statisticians?](https://mlsanity.com/paper/2406.07815/) (2024)
- [A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detection](https://mlsanity.com/paper/2502.13308/) (2025)
- [A Simple and Scalable Representation for Graph Generation](https://mlsanity.com/paper/2312.02230/) (2023)
- [Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approach](https://mlsanity.com/paper/2506.13083/) (2025)
- [Bisecle: Binding and Separation in Continual Learning for Video Language Understanding](https://mlsanity.com/paper/2507.00469/) (2025)
- [Noise-Resilient Unsupervised Graph Representation Learning via Multi-Hop Feature Quality Estimation](https://mlsanity.com/paper/2407.19944/) (2024)
- [CCGG: A Deep Autoregressive Model for Class-Conditional Graph Generation](https://mlsanity.com/paper/2110.03800/) (2021)

## Built on by (most cited first, 30 of 58)

- [BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks](https://mlsanity.com/paper/2508.08127/) (2025)
- [From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents](https://mlsanity.com/paper/2603.22386/) (2026)
- [DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning](https://mlsanity.com/paper/2603.16459/) (2026)
- [Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects](https://mlsanity.com/paper/2507.21407/) (2025)
- [A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models](https://mlsanity.com/paper/2509.06609/) (2025)
- [OFA-MAS: One-for-All Multi-Agent System Topology Design based on Mixture-of-Experts Graph Generative Models](https://mlsanity.com/paper/2601.12996/) (2026)
- [Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems](https://mlsanity.com/paper/2510.26585/) (2025)
- [Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time](https://mlsanity.com/paper/2511.07023/) (2025)
- [Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models](https://mlsanity.com/paper/2510.07799/) (2025)
- [Hollywood Town: Long-Video Generation via Cross-Modal Multi-Agent Orchestration](https://mlsanity.com/paper/2510.22431/) (2025)
- [Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection](https://mlsanity.com/paper/2512.18733/) (2025)
- [MetaGen: Self-Evolving Roles and Topologies for Multi-Agent LLM Reasoning](https://mlsanity.com/paper/2601.19290/) (2026)
- [Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AI](https://mlsanity.com/paper/2510.16720/) (2025)
- [Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction](https://mlsanity.com/paper/2510.14319/) (2025)
- [Towards One-for-All Anomaly Detection for Tabular Data](https://mlsanity.com/paper/2603.14407/) (2026)
- [EvoMAS: Evolutionary Generation of Multi-Agent Systems](https://mlsanity.com/paper/2602.06511/) (2026)
- [GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2603.19677/) (2026)
- [Self-Improvement of Large Language Models: A Technical Overview and Future Outlook](https://mlsanity.com/paper/2603.25681/) (2026)
- [TacoMAS: Test-Time Co-Evolution of Topology and Capability in LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.09539/) (2026)
- [RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation](https://mlsanity.com/paper/2605.09907/) (2026)
- [Towards Anomaly Detection on Relational Data](https://mlsanity.com/paper/2606.18621/) (2026)
- [Generalizing Test-time Compute-optimal Scaling as an Optimizable Graph](https://mlsanity.com/paper/2511.00086/) (2025)
- [Holos: A Web-Scale LLM-Based Multi-Agent System for the Agentic Web](https://mlsanity.com/paper/2604.02334/) (2026)
- [Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems](https://mlsanity.com/paper/2605.29790/) (2026)
- [Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective](https://mlsanity.com/paper/2608.18104/) (2026)
- [TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems](https://mlsanity.com/paper/2601.10120/) (2026)
- [Beyond a Single Perspective: Text Anomaly Detection with Multi-View Language Representations](https://mlsanity.com/paper/2601.17786/) (2026)
- [Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning](https://mlsanity.com/paper/2604.00344/) (2026)
- [HyperAgent: Leveraging Hypergraphs for Topology Optimization in Multi-Agent Communication](https://mlsanity.com/paper/2510.10611/) (2025)
- [EMS: Multi-Agent Voting via Efficient Majority-then-Stopping](https://mlsanity.com/paper/2604.02863/) (2026)

## Abstract (arXiv)

Multi-agent systems (MAS) based on large language models (LLMs) have emerged as a powerful solution for dealing with complex problems across diverse domains. The effectiveness of MAS is critically dependent on its collaboration topology, which has become a focal point for automated design research. However, existing approaches are fundamentally constrained by their reliance on a template graph modification paradigm with a predefined set of agents and hard-coded interaction structures, significantly limiting their adaptability to task-specific requirements. To address these limitations, we reframe MAS design as a conditional autoregressive graph generation task, where both the system composition and structure are designed jointly. We propose ARG-Designer, a novel autoregressive model that operationalizes this paradigm by constructing the collaboration graph from scratch. Conditioned on a natural language task query, ARG-Designer sequentially and dynamically determines the required number of agents, selects their appropriate roles from an extensible pool, and establishes the optimal communication links between them. This generative approach creates a customized topology in a flexible and extensible manner, precisely tailored to the unique demands of different tasks. Extensive experiments across six diverse benchmarks demonstrate that ARG-Designer not only achieves state-of-the-art performance but also enjoys significantly greater token efficiency and enhanced extensibility. The source code of ARG-Designer is available at https://github.com/Shiy-Li/ARG-Designer.