用分治多智能体系统提升大图算法推理能力
GraphDC: A Divide-and-Conquer Multi-Agent System for Scalable Graph Algorithm Reasoning
- 将大图拆成子图，分工处理再整合结果
- 在大规模图上准确率显著优于传统方法
- 适合需要复杂推理的图算法任务
大型语言模型在数学问题上表现强劲，但在图算法任务中仍不理想，因图结构拓扑复杂且常需系统性多步推理，尤其在大图上更明显。为此，我们提出GraphDC，一种基于分治思想的多智能体框架，用于可扩展的图算法推理。具体而言，该框架将输入图分解为若干子图，分配给专用智能体进行局部推理，并由主智能体结合子图间信息整合局部输出，生成最终解。这种分层设计减轻了单个智能体的推理负担，缓解计算瓶颈，并在大图实例上提升鲁棒性。大量实验表明，GraphDC在多种图算法推理任务和不同规模下均持续优于现有方法，尤其在大图上，其性能远超端到端直接推理。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated strong potential for many mathematical problems. However, their performance on graph algorithmic tasks is still unsatisfying, since graphs are naturally more complex in topology and often require systematic multi-step reasoning, especially on larger graphs. Motivated by this gap, we propose GraphDC, a Divide-and-Conquer multi-agent framework for scalable graph algorithm reasoning. Specifically, inspired by Divide-and-Conquer design, GraphDC decomposes an input graph into smaller subgraphs, assigns each subgraph to a specialized agent for local reasoning, and uses a master agent to integrate the local outputs with inter-subgraph information to produce the final solution. This hierarchical design reduces the reasoning burden on individual agents, alleviates computational bottlenecks, and improves robustness on large graph instances. Extensive experiments show that GraphDC consistently outperforms existing methods on graph algorithm reasoning across diverse tasks and scales, especially on larger instances where direct end-to-end reasoning is less reliable.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。