发表机构
Edith Cowan University; The University of Queensland; Victoria University（埃迪斯科文大学; 昆士兰大学; 维多利亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对异质图结构，提出多智能体图学习框架MAAGL，通过社区划分、置换不变结构签名与辩论协作，在四个基准上超越现有AGL方法。
AI 中文摘要
智能体图学习（AGL）近期在图推理任务上取得了有前景的成果，其中由大语言模型（LLM）驱动的智能体顺序采样图作为证据以支持其最终预测。现有方法要么采用单一智能体，要么编排多个基于角色的智能体在整个图上进行推理和学习，但两者本质上都依赖于跨不同图区域的共享推理策略，这对于具有异质结构和语义模式的图而言可能不是最优的。受多智能体协作在复杂推理任务上取得进展的启发，一个自然的补救措施是让多个智能体拥有不同的记忆并进行协作；然而，将此范式直接应用于图面临两个挑战。首先，现有AGL方法通常将图结构转化为自然语言描述以供LLM智能体使用，这使得推理过程对结构信息的顺序敏感，从而破坏了图的置换不变性。其次，纳入不断增大的采样邻域导致上下文迅速增长。为解决这些挑战，本文引入了一个多智能体智能体图学习（即MAAGL）框架。MAAGL将图划分为社区，并为每个社区分配一个独立智能体以实现区域特定专业化。MAAGL分别表示结构和语义证据。结构证据由动态更新的结构签名概括，该签名具有置换不变性且大小固定，而语义证据则被过滤为按相关性排序的前k个节点。基于具有相似签名的历史轨迹，智能体估计其置信度，并在需要时触发辩论式协作。在四个基准数据集上的大量实验表明，MAAGL优于最先进的AGL方法。
英文摘要
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.
CommentsUnder review
