@inproceedings{han-etal-2026-see,
    title = "See or Say Graphs: Agent-Driven Scalable Graph Understanding with Vision-Language Models",
    author = "Han, Shuo  and
      Cao, Yukun  and
      Ding, Zezhong  and
      Gao, Zengyi  and
      Zhou, S Kevin  and
      Xie, Xike",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.2066/",
    pages = "41565--41589",
    ISBN = "979-8-89176-395-1",
    abstract = "Vision-language models (VLMs) have shown promise in graph understanding, but remain limited by input-token constraints, facing scalability bottlenecks and lacking effective mechanisms to coordinate textual and visual modalities. To address these challenges, we propose GraphVista, a unified framework that enhances both scalability and modality coordination in graph understanding. For scalability, GraphVista organizes graph information hierarchically into a lightweight GraphRAG base, which retrieves only task-relevant textual descriptions and high-resolution visual subgraphs, compressing redundant context while preserving key reasoning elements. For modality coordination, GraphVista introduces a planning agent that routes tasks to the most suitable modality{---}using the text modality for simple property reasoning and the visual modality for local and structurally complex reasoning grounded in explicit topology. Extensive experiments demonstrate that GraphVista scales to large graphs, up to $200{\times}$ larger than those used in existing benchmarks, and consistently outperforms existing textual, visual, and fusion-based methods, achieving up to $4.4{\times}$ quality improvement over the state-of-the-art baselines by fully exploiting the complementary strengths of both modalities."
}