Saved in:
Bibliographic Details
Main Authors: Han, Shuo, Cao, Yukun, Ding, Zezhong, Gao, Zengyi, Zhou, S Kevin, Xie, Xike
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.16769
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917191216005120
author Han, Shuo
Cao, Yukun
Ding, Zezhong
Gao, Zengyi
Zhou, S Kevin
Xie, Xike
author_facet Han, Shuo
Cao, Yukun
Ding, Zezhong
Gao, Zengyi
Zhou, S Kevin
Xie, Xike
contents Vision-language models (VLMs) have shown promise in graph structure 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 structure 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 decomposes and routes tasks to the most suitable modality-using the text modality for direct access to explicit graph properties and the visual modality for local graph structure 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16769
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle See or Say Graphs: Agent-Driven Scalable Graph Structure Understanding with Vision-Language Models
Han, Shuo
Cao, Yukun
Ding, Zezhong
Gao, Zengyi
Zhou, S Kevin
Xie, Xike
Artificial Intelligence
Computation and Language
Vision-language models (VLMs) have shown promise in graph structure 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 structure 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 decomposes and routes tasks to the most suitable modality-using the text modality for direct access to explicit graph properties and the visual modality for local graph structure 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.
title See or Say Graphs: Agent-Driven Scalable Graph Structure Understanding with Vision-Language Models
topic Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2510.16769