Metraipolis › archive › dc_1ef4e7f0aae9
GraphMAS: A Systematic Benchmark of Multi-Agent Coordination for Graph Learning — arXiv:2609.39777
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39777
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T13:46:35.506Z
- SHA-256 of the archived text
8866d3f7031ea9155380f90a8c1deeb7f809c5f7ce6067d2e3f46c76fc06dbba- Stable URL of this page
https://metraipolis.com/documento/dc_1ef4e7f0aae9
How to cite
GraphMAS: A Systematic Benchmark of Multi-Agent Coordination for Graph Learning — arXiv:2609.39777 — arXiv (en), https://arxiv.org/abs/2609.39777 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1ef4e7f0aae9 (Metraipolis archive dc_1ef4e7f0aae9, sha256 8866d3f7031ea9155380f90a8c1deeb7f809c5f7ce6067d2e3f46c76fc06dbba)
BibTeX
@misc{dc1ef4e7f0aae9,
title = {GraphMAS: A Systematic Benchmark of Multi-Agent Coordination for Graph Learning — arXiv:2609.39777},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39777},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1ef4e7f0aae9; sha256 8866d3f7031ea9155380f90a8c1deeb7f809c5f7ce6067d2e3f46c76fc06dbba},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39777. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.39777 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T13:18:10.449Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).