用约束触发重检，自动从扫描图纸提取可直接用于仿真的结构模型。
BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints
- 以工程约束为触发器，局部重检MLLM输出，确保结构合理性。
- 在300张真实图纸上，梁的F1达0.994，远超基线模型的0.301。
- 适合需要高精度结构建模的工程安全评估与抗震改造场景。
将服役中的钢筋混凝土建筑图纸转换为支持确定性有限元分析导出和工程师审查的仿真可用模型，是开展安全评估与抗震加固的关键，但目前仍依赖人工操作。直接对扫描图纸使用多模态大模型进行提示不可靠：输出常违反梁柱支撑、跨度数量或三维连续性等工程约束。本文提出BlueprintAgent（BPA），一种基于约束触发的多模态代理系统，用于从扫描蓝图中提取仿真可用的结构框架。BPA将多模态大模型作为主要读取与决策者，结合OCR和计算机视觉提供局部证据。其核心机制将工程约束实现为可调用的验证器，当实体级冲突被检测到时，触发对局部区域的针对性重检——这是一种不同于固定流水线和自由反思的推理期控制。我们在20个匿名钢筋混凝土框架项目的300张真实扫描图纸上评估BPA，对比五种基线和六种消融实验。BPA在宏平均梁F1上达到0.994，而单个MLLM零样本方法仅为0.301，固定流水线为0.820；移除由MLLM主导的轴线仲裁机制后，在复杂多页项目中梁与柱的F1显著下降。对于密集技术图纸，工程约束应作为实体级目标重检的触发条件，而非事后输出过滤。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。