用可自适应探索的LLM代理从异构BIM模型中提取信息
BIM Information Extraction Through LLM-based Adaptive Exploration
- LLM代理动态执行代码，实时发现BIM结构，不依赖预设格式
- 在ifc-bench v2上达到92.3%准确率，显著优于静态查询方法
- 适合建筑信息模型、智能设计等领域的研究人员与工程师
BIM模型提供了建筑几何、语义和拓扑的结构化表示，但从中提取特定信息仍极为困难。现有方法通过将自然语言转化为结构化查询，假设数据组织是固定的（静态方法），而BIM的异构性最终使该假设失效。本文提出一种新范式——自适应探索：基于LLM的智能体通过迭代执行代码，动态发现BIM模型的运行时结构，而非预先假设。我们在ifc-bench v2上评估该方法，这是一个随本文发布的开源BIM问答基准，涵盖来自21个项目的37个IFC模型中的1,027个任务。通过双因素消融实验（两种LLM能力水平与四种增强策略），结果表明自适应探索在所有配置下均显著优于静态查询生成，无论采用何种增强策略。这表明，应对BIM异构性的最佳方式在于范式革新，而非优化静态方法。
原文摘要 · Abstract (English)
BIM models provide structured representations of building geometry, semantics, and topology, yet extracting specific information from them remains remarkably difficult. Current approaches translate natural language into structured queries by assuming a fixed data organization (static approach), which BIM heterogeneity eventually invalidates. We address this with a new paradigm, adaptive exploration, where an LLM-based agent iteratively executes code to extract information from a BIM model, discovering its structure at runtime instead of assuming it. We evaluate this approach on ifc-bench v2, an open-source BIM question-answering benchmark introduced alongside this work, comprising 1,027 tasks across 37 IFC models from 21 projects. A factorial ablation across two LLM capability levels and four augmentation strategies shows that adaptive exploration significantly outperforms static query generation across all configurations, regardless of the augmentation strategy. These results indicate that BIM heterogeneity is best addressed at the paradigm level, not by further optimizing static approaches.
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。