发表机构
New York University Shanghai; New York University; Northwestern University（上海纽约大学; 纽约大学; 西北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对图学习中多智能体协调缺乏系统研究的问题，提出GraphMAS基准，统一评估七种协调方法，发现专家分解与实例自适应选择能显著提升性能与效率。
AI 中文摘要
基于大语言模型的多智能体系统通过聚合、交互和自适应控制来协调专门化的推理，但其在图学习方面的潜力尚未得到探索。图学习是此类系统的天然应用场景，因为有用的证据可能来自异构的局部、长程、全局结构和语义视角，而这些视角的相关性因实例而异。现有的基于大语言模型的图学习方法主要依赖单智能体推理，而多智能体协调主要在通用推理场景中研究。因此，尚不清楚多个专门化智能体能否改进图学习，以及应如何设计和评估协调策略。为填补这一空白，我们提出了GraphMAS，一个面向图学习的多智能体协调系统化基准。GraphMAS构建了一个共享的图推理专家池，并沿两个维度组织协调：智能体间交互和运行时自适应性，从而产生四种范式和七种代表性协调方法。在统一协议下，我们在七个文本属性图、三个领域和两个图学习任务上评估了这些方法。我们发现异构图视角是互补的，协调专家优于单个专家和单智能体图推理，其收益来自于将推理分解到多个专家，而非仅仅更广泛的证据访问。然而，更丰富的智能体间交互并不总是可靠地带来帮助，而实例自适应的专家选择在准确性和效率之间取得了最强的权衡。我们进一步表明，协调可以在固定的专家池上学习，并迁移到未见过的图。因此，GraphMAS提供了一个受控评估框架和经验原则，用于理解多智能体协调何时以及如何有益于图学习。
英文摘要
LLM-based multi-agent systems coordinate specialized reasoning through aggregation, interaction, and adaptive control, yet their potential for graph learning remains unexplored. Graph learning is a natural setting for such systems because useful evidence may arise from heterogeneous local, long-range, global structural, and semantic perspectives whose relevance varies across instances. Existing LLM-based graph learning approaches primarily rely on single-agent reasoning, while multi-agent coordination has been studied mainly in general reasoning settings. Consequently, it remains unclear whether multiple specialized agents can improve graph learning and how coordination strategies should be designed and evaluated. To address this gap, we introduce GraphMAS, a systematic benchmark of multi-agent coordination for graph learning. GraphMAS builds a shared pool of graph reasoning specialists and organizes coordination along two dimensions, inter-agent interaction and runtime adaptivity, yielding four paradigms and seven representative coordination methods. Under a unified protocol, we evaluate these methods across seven text-attributed graphs, three domains, and two graph learning tasks. We find that heterogeneous graph perspectives are complementary, and that coordinating specialists improves over individual specialists and single-agent graph reasoning, with gains from decomposing reasoning across specialists rather than from broader evidence access alone. However, richer inter-agent interaction does not reliably help, whereas instance-adaptive specialist selection yields the strongest accuracy-efficiency trade-off. We further show that coordination can be learned over a fixed specialist pool and transfers to held-out graphs. GraphMAS therefore provides a controlled evaluation framework and empirical principles for understanding when and how multi-agent coordination benefits graph learning.
