Structural Plan-to-Model Conversion with Deterministic Geometry and Guarded Agentic Vision-Language Refinement

Researchers introduced the first agentic vision-language framework for converting structural framing plans into editable finite-element model drafts without task-specific detector training, achieving scale estimation within 0.1% of the reference and recall/precision scores up to 1.000/1.000 for walls and braces on a held-out benchmark of 100 plans. The framework combines a deterministic stage for primitive extraction and entity recognition with a guarded agentic stage that applies typed corrections, admission tests, and fail-closed transactions. The study, published on arXiv (2608.17237v1), used an author-generated benchmark and reported end-to-end results on a seed-disjoint held-out half.

arXiv:2608.17237v1 Announce Type: new Abstract: Converting structural framing plans into editable finite-element model drafts remains labor-intensive and prone to transcription error. Existing drawing-understanding systems for building components rely on task-specific trained neural detectors, and language-model agents in structural engineering operate on text or model data rather than the drawing itself. This paper presents, to the authors' knowledge, the first framework applying an agentic vision-language layer to structural component detection and model drafting from framing-plan PDFs, without task-specific detector training or fine-tuning. A deterministic stage extracts primitives, estimates scale by dimension-ratio consensus, recognizes five entity classes with a drafting grammar, and assembles an editable layout. The agentic stage proposes typed corrections constrained by deterministic candidates, operation-specific admission tests, change-level review, and fail-closed transactions. Evaluation used an author-generated benchmark of 100 plans: a development half that informed every rule revision, and a seed-disjoint held-out half generated after the rules froze, evaluated once. All reported scores are end-to-end results of the complete framework on the held-out half. Scale was estimated within 0.1% of the generator reference for every drawing. Recall and precision were 0.922/0.997 for columns, 0.886/0.990 for beams, 1.000/1.000 for walls, 1.000/1.000 for braces, and 1.000/0.964 for openings. A controlled study repeated two corruptions three times on three development drawings. Calibration passed all nine trials; member repair met every strict end-state predicate in five of nine. Guarded review corrected missed framing and false marks within explicit bounds. The held-out half shares the development generator, so the study excludes independently drafted plans, raster evaluation, analytical connectivity, and solver validation.