# BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints

arXiv: https://arxiv.org/abs/2609.07362 · HTML: https://mlsanity.com/paper/2609.07362/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 32 references that are in the map.
- First posted on arXiv 7 Sep 2026.

## Builds on (most cited first, 25 of 25)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding](https://mlsanity.com/paper/2210.03347/) (2022)
- [Lexically Constrained Decoding for Sequence Generation Using Grid Beam Search](https://mlsanity.com/paper/1704.07138/) (2017)
- [Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning](https://mlsanity.com/paper/2305.13971/) (2023)
- [MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations](https://mlsanity.com/paper/2407.01523/) (2024)
- [Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translation](https://mlsanity.com/paper/1804.06609/) (2018)
- [NeuroLogic A*esque Decoding: Constrained Text Generation with Lookahead Heuristics](https://mlsanity.com/paper/2112.08726/) (2021)
- [DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysis](https://mlsanity.com/paper/2206.01062/) (2022)
- [SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories](https://mlsanity.com/paper/2409.07440/) (2024)
- [CubiCasa5K: A Dataset and an Improved Multi-Task Model for Floorplan Image Analysis](https://mlsanity.com/paper/1904.01920/) (2019)
- [RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning](https://mlsanity.com/paper/2401.08326/) (2024)
- [FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting](https://mlsanity.com/paper/2105.07147/) (2021)
- [Fine-Tuning Vision-Language Model for Automated Engineering Drawing Information Extraction](https://mlsanity.com/paper/2411.03707/) (2024)
- [DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding](https://mlsanity.com/paper/2511.11552/) (2025)
- [From Drawings to Decisions: A Hybrid Vision-Language Framework for Parsing 2D Engineering Drawings into Structured Manufacturing Knowledge](https://mlsanity.com/paper/2506.17374/) (2025)
- [A Multi-Stage Hybrid Framework for Automated Interpretation of Multi-View Engineering Drawings Using Vision Language Model](https://mlsanity.com/paper/2510.21862/) (2025)
- [SlideAgent: Hierarchical Agentic Framework for Multi-Page Visual Document Understanding](https://mlsanity.com/paper/2510.26615/) (2025)
- [EngiAI: Capability-Based Evaluation of Tool-Connected LLM Agents for Engineering Design](https://mlsanity.com/paper/2605.19743/) (2026)
- [Seg2Act: Global Context-aware Action Generation for Document Logical Structuring](https://mlsanity.com/paper/2410.06802/) (2024)
- [How to Build AI Agents by Augmenting LLMs with Codified Human Expert Domain Knowledge? A Software Engineering Framework](https://mlsanity.com/paper/2601.15153/) (2026)
- [Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans](https://mlsanity.com/paper/2603.11640/) (2026)
- [Image-Based Structural Analysis Using Computer Vision and LLMs: PhotoBeamSolver](https://mlsanity.com/paper/2603.21432/) (2026)

## Abstract (arXiv)

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.