Metraipolis › archive › dc_450f237d8bc5

TopoAgent: A Structure-Aware Perception-to-Reasoning Framework for Diagram-to-Graph Topology Extraction with Large Vision-Language Models — arXiv:2608.28701

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28701
License (as archived)
CC0-1.0
Archived
2026-10-17T09:53:17.412Z
SHA-256 of the archived text
9de14a13973b11d2a4e53d46a73cf1cca8b789f656c22fe15b853d2986db4af8
Stable URL of this page
https://metraipolis.com/documento/dc_450f237d8bc5

How to cite

TopoAgent: A Structure-Aware Perception-to-Reasoning Framework for Diagram-to-Graph Topology Extraction with Large Vision-Language Models — arXiv:2608.28701 — arXiv (en), https://arxiv.org/abs/2608.28701 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_450f237d8bc5 (Metraipolis archive dc_450f237d8bc5, sha256 9de14a13973b11d2a4e53d46a73cf1cca8b789f656c22fe15b853d2986db4af8)
BibTeX
@misc{dc450f237d8bc5,
  title = {TopoAgent: A Structure-Aware Perception-to-Reasoning Framework for Diagram-to-Graph Topology Extraction with Large Vision-Language Models — arXiv:2608.28701},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28701},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_450f237d8bc5; sha256 9de14a13973b11d2a4e53d46a73cf1cca8b789f656c22fe15b853d2986db4af8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28701. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diagram-to-graph topology extraction aims to extract a graph of entities and their connections from a structural diagram. This task remains challenging for current vision-language models because it requires both fine-grained perceptual grounding and topology-aware reasoning with global consistency. We present TopoBench-180, a human-verified benchmark for diagram-to-graph topology extraction, and TopoAgent, a structure-aware perception-to-reasoning framework for reliable topology extraction using large vision-language models. TopoBench-180 contains 180 structural diagrams spanning Web-style and Network-style categories, paired with canonical graph annotations. TopoAgent progressively extracts the target graph by combining grounded perception, global structural priors, canonical node inventory construction, node-centric local-to-global relation reasoning, and topological consistency enforcement. Experiments on TopoBench-180 show that TopoAgent outperforms strong vision-language model baselines and recent visual reasoning frameworks, especially on edge extraction. More broadly, this work fills an important gap in multimodal structured understanding by establishing a benchmark and framework for diagram-to-graph topology extraction. The benchmark and associated resources will be publicly released at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-01 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.28701 — 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 2026-10-17T09:28:47.944Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).