SOURCE-LINKED INTELLIGENCE

PlanSightRAG: A Visual-First Multimodal RAG for Automating Question Answering and Compliance Checking for Civil Standard Plans

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Civil infrastructure compliance checking has long relied on engineers manually reading legacy 2D plans; however, OCR-based automation strips away the geometry and layout essential for interpreting these plans. We present a Visual-First Multimodal Retrieval-Augmented Generation (RAG) framework called PlanSightRAG. It indexes and reasons directly over plan imagery, integrates a ColNomic-3B multi-vector retrieval, an agentic Planner-Retriever-Auditor-Synthesizer, and MaxSim heatmaps as an evidence trail. We introduce a 4,056-pair benchmark from five state Departments of Transportation (DOT) stand

Read original source ↗ Open in workspace

recordType

paper

region

Global