Metraipolis › archive › dc_96ef3105f8de

BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints — arXiv:2609.07362

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.07362
License (as archived)
CC0-1.0
Archived
2026-10-16T12:45:34.570Z
SHA-256 of the archived text
54140531d129d3b6715edc2237782e88ab7e9e6f97fbbd692edcbbffb9b946d5
Stable URL of this page
https://metraipolis.com/documento/dc_96ef3105f8de

How to cite

BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints — arXiv:2609.07362 — arXiv (en), https://arxiv.org/abs/2609.07362 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96ef3105f8de (Metraipolis archive dc_96ef3105f8de, sha256 54140531d129d3b6715edc2237782e88ab7e9e6f97fbbd692edcbbffb9b946d5)
BibTeX
@misc{dc96ef3105f8de,
  title = {BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints — arXiv:2609.07362},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07362},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96ef3105f8de; sha256 54140531d129d3b6715edc2237782e88ab7e9e6f97fbbd692edcbbffb9b946d5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07362. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Converting in-service reinforced-concrete (RC) building blueprints into simulation-ready models---structured frame representations that support deterministic FEM export and qualified-engineer review---underpins safety assessment and seismic retrofit, but the process remains manual. Direct prompting of a multimodal large language model (MLLM) over a scanned sheet is unreliable: outputs often violate engineering constraints on beam--column support, span count, or 3D continuity. We present BlueprintAgent (BPA), a constraint-triggered multimodal agent for simulation-ready frame extraction from scanned blueprints. BPA treats the MLLM as the primary reader and decision maker, with OCR and computer vision supplying localized evidence. Its central mechanism realizes engineering constraints as callable validators whose entity-level conflict reports trigger targeted MLLM revisits over the local region---an inference-time control distinct from fixed pipelines and free-form self-reflection. We evaluate BPA on 300 real scanned blueprint sheets from 20 anonymized RC frame projects, against five baselines and six ablations. BPA reaches a macro-averaged Beam F1 of 0.994, against 0.301 for single-MLLM zero-shot and 0.820 for a fixed pipeline; removing MLLM-led axis adjudication collapses Beam and Column F1 on complex multi-sheet projects. For dense technical drawings, engineering constraints are best deployed as triggers for entity-level targeted revisits rather than as post-hoc output filters.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.07362 — 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 2026-10-16T12:30:25.114Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).