Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual understanding, yet they suffer from a critical limitation: structural blindness. Even state-of-the-art models fail to capture topology and symbolic logic in engineering schematics, as their pixel-driven paradigm discards the explicit vector-defined relations needed for reasoning. To overcome this, we propose a Vector-to-Graph (V2G) pipeline that converts CAD diagrams into property graphs where nodes represent components and edges encode connectivity, making structural dependencies explicit and machine-auditable. On a diagnostic benchmark of electrical compliance checks, V2G yields large accuracy gains across all error categories, while leading MLLMs remain near chance level. These results highlight the systemic inadequacy of pixel-based methods and demonstrate that structure-aware representations provide a reliable path toward practical deployment of multimodal AI in engineering domains. To facilitate further research, we release our benchmark and implementation at https://github.com/gm-embodied/V2G-Audit.
@article{arxiv.2602.11678,
title = {Beyond Pixels: Vector-to-Graph Transformation for Reliable Schematic Auditing},
author = {Chengwei Ma and Zhen Tian and Zhou Zhou and Zhixian Xu and Xiaowei Zhu and Xia Hua and Si Shi and F. Richard Yu},
journal= {arXiv preprint arXiv:2602.11678},
year = {2026}
}