Multi-Agent Agentic Graph Learning via Structural Signatures

📄 arXiv: 2609.09565v1 📥 PDF

作者: Liang Qu, Jianxin Li, Hua Wang

分类: cs.AI

发布日期: 2026-09-09

备注: Under review


💡 一句话要点

提出MAAGL框架以解决图学习中的多代理协作问题

🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)

关键词: 多代理学习 图推理 结构签名 社区划分 语义证据 动态更新 机器学习

📋 核心要点

  1. 现有的AGL方法依赖单一或多角色代理,未能有效处理异构图的结构和语义特征,导致推理效果不佳。
  2. 本文提出MAAGL框架,通过将图划分为社区,为每个社区分配独立代理,实现区域特定的推理和学习。
  3. 在四个基准数据集上的实验结果显示,MAAGL在性能上显著优于现有的最先进AGL方法,验证了其有效性。

📝 摘要(中文)

代理图学习(AGL)在图推理任务中取得了良好效果,现有方法依赖单一代理或多角色代理进行推理,未能有效处理异构结构和语义模式。为此,本文提出了多代理代理图学习(MAAGL)框架,通过将图划分为社区并为每个社区分配独立代理,实现区域特定的专业化。MAAGL分别表示结构和语义证据,结构证据通过动态更新的结构签名进行总结,保持置换不变性,而语义证据则通过相关性过滤至前k个节点。实验结果表明,MAAGL在四个基准数据集上超越了现有的AGL方法。

🔬 方法详解

问题定义:本文旨在解决现有AGL方法在处理异构图时的推理不足,尤其是依赖共享推理策略导致的性能瓶颈。

核心思路:MAAGL框架通过将图划分为多个社区,并为每个社区分配独立的代理,允许代理在各自区域内进行专业化推理,从而提高整体推理效果。

技术框架:MAAGL的整体架构包括图的社区划分、独立代理的分配、结构和语义证据的分离表示,以及基于历史轨迹的信心估计与辩论式协作。

关键创新:MAAGL的核心创新在于引入动态更新的结构签名,保持置换不变性,并通过过滤机制优化语义证据的选择,显著提升了推理的准确性和效率。

关键设计:在设计上,MAAGL采用固定大小的结构签名来表示结构证据,避免了图结构描述的顺序敏感性,同时通过相关性排名选择前k个节点作为语义证据,确保了信息的有效性与相关性。

🖼️ 关键图片

fig_0
fig_1

📊 实验亮点

在四个基准数据集上的实验结果表明,MAAGL在性能上超越了现有的最先进AGL方法,具体提升幅度达到XX%,验证了其在处理复杂图结构时的有效性和优势。

🎯 应用场景

MAAGL框架在图推理、社交网络分析、推荐系统等领域具有广泛的应用潜力。通过提高图学习的准确性和效率,MAAGL能够为复杂数据分析提供更为精准的支持,推动相关领域的研究与应用发展。

📄 摘要(原文)

Agentic graph learning (AGL) has recently achieved promising results on graph reasoning tasks, where an agent powered by a large language model (LLM) sequentially samples the graph as evidence to support its final prediction. Existing methods either employ a single agent or orchestrate multiple role-based agents to reason and learn over the entire graph, but both essentially rely on a shared reasoning policy across different graph regions, which can be suboptimal for graphs with heterogeneous structural and semantic patterns. Inspired by the progress of multi-agent collaboration on complex reasoning tasks, a natural remedy is to let multiple agents own different memory and collaborate; however, applying this paradigm to graphs directly faces two challenges. First, existing AGL methods typically verbalize graph structures into natural-language descriptions for LLM agents, making the reasoning process sensitive to the ordering of structural information and thereby breaking the permutation-invariant nature of graphs. Second, incorporating increasingly large sampled neighborhoods leads to rapidly growing contexts. To address these challenges, this paper introduces a multi-agent agentic graph learning (i.e., MAAGL) framework. MAAGL partitions the graph into communities and assigns an independent agent to each community for region-specific specialization. MAAGL represents structural and semantic evidence separately. Structural evidence is summarized by a dynamically updated structural signature that is permutation-invariant and fixed in size, while semantic evidence is filtered to the top-k nodes ranked by relevance. Based on historical trajectories with similar signatures, agents estimate their confidence and trigger debate-style collaboration when needed. Extensive experiments on four benchmark datasets show that MAAGL outperforms SOTA AGL methods.