GEMS-RAG: Graph-grounded Engineering Multimodal Standards Retrieval-Augmented Generation

A new arXiv paper, arXiv:2610.33277v1, proposes GEMS-RAG, a graph-grounded multimodal retrieval-augmented generation framework that decomposes figures in engineering standards into visual entities linked to textual provisions, engineering concepts and regulatory rules. Evaluated on the Manual on Uniform Traffic Control Devices (MUTCD), GEMS-RAG's combination of dense, sparse and visual retrieval with graph expansion improved retrieval effectiveness and question-answering performance over text-only, multimodal and graph-based RAG baselines. The authors present GEMS-RAG as a general framework for reasoning over engineering codes, technical manuals, regulatory documents and scientific standards in safety-critical applications.

arXiv:2610.33277v1 Announce Type: new Abstract: Engineering standards are challenging knowledge sources for large language models LLMs because they are hierarchical, multimodal, and densely connected through figures, tables, cross-references, and normative rules. Existing retrieval-augmented generation RAG methods often rely on unstructured text retrieval and struggle with questions requiring joint reasoning over textual provisions, visual specifications, and document structure. We propose GEMS-RAG Graph-grounded Engineering Multimodal Standards Retrieval-Augmented Generation , a framework for grounded reasoning over engineering standards. GEMS-RAG combines hierarchical parsing, fine-grained visual entity extraction, multimodal knowledge graph construction, and graph-grounded hybrid retrieval. Instead of treating figures as monolithic images, it decomposes them into meaningful visual entities linked to textual provisions, engineering concepts, and regulatory rules. During inference, dense, sparse, and visual retrieval are combined with graph expansion to identify relevant evidence across text, figures, and document structure. We evaluate GEMS-RAG on the Manual on Uniform Traffic Control Devices MUTCD , a large engineering standard containing egulations, technical drawings, and standardized traffic-control devices. Results show that graph-grounded multimodal retrieval improves retrieval effectiveness and question-answering performance over text-only, multimodal, and graph-based RAG baselines. Beyond MUTCD, GEMS-RAG offers a general framework for reasoning over engineering codes, technical manuals, regulatory documents, and scientific standards in safety-critical applications.