让大模型直接操作建筑数据，用自然语言设计房屋
MCP4IFC: IFC-Based Building Design Using Large Language Models
- 通过MCP协议让大模型直接操控IFC建筑数据
- 能完成建房、查询、修改等复杂任务，准确率高
- 适合建筑设计师和AI研究者快速上手智能建模
将生成式AI引入建筑、工程与施工（AEC）领域，需要能够将自然语言指令转化为对标准化数据模型的操作系统。我们提出MCP4IFC，一个开源框架，使大型语言模型（LLMs）可通过模型上下文协议（MCP）直接操作行业基础类（IFC）数据。该框架提供一系列BIM工具，包括用于信息检索的场景查询工具、创建和修改常见建筑构件的预设函数，以及结合上下文学习与检索增强生成（RAG）的动态代码生成系统，可处理超出预设工具集的任务。实验表明，使用本框架的大模型能成功执行从建造简单房屋到查询与编辑现有IFC数据等复杂任务。框架已开源，旨在推动大模型驱动的BIM设计研究，并为AI辅助建模工作流提供基础。代码地址：https://show2instruct.github.io/mcp4ifc/
原文摘要 · Abstract (English)
Bringing generative AI into the architecture, engineering and construction (AEC) field requires systems that can translate natural language instructions into actions on standardized data models. We present MCP4IFC, a comprehensive open-source framework that enables Large Language Models (LLMs) to directly manipulate Industry Foundation Classes (IFC) data through the Model Context Protocol (MCP). The framework provides a set of BIM tools, including scene querying tools for information retrieval, predefined functions for creating and modifying common building elements, and a dynamic code-generation system that combines in-context learning with retrieval-augmented generation (RAG) to handle tasks beyond the predefined toolset. Experiments demonstrate that an LLM using our framework can successfully perform complex tasks, from building a simple house to querying and editing existing IFC data. Our framework is released as open-source to encourage research in LLM-driven BIM design and provide a foundation for AI-assisted modeling workflows. Our code is available at https://show2instruct.github.io/mcp4ifc/.
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。