arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.08054cs.AIcs.CLcs.SE
收藏

Text2BIM：使用基于大型语言模型的多智能体框架生成建筑模型

Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework

Chair of Computing in Civil and Building Engineering, Technical University of Munich, Munich, Germany（土木与建筑工程计算系，慕尼黑技术大学，德国慕尼黑）；TUM Georg Nemetschek Institute, Munich, Germany（慕尼黑技术大学格奥尔·奈梅克研究所，德国慕尼黑）

Changyu Du, Sebastian Esser, Stavros Nousias, André Borrmann

备注：
Journal of Computing in Civil Engineering
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出Text2BIM，一个基于LLM的多智能体框架，通过将自然语言指令转换为调用BIM工具API的代码生成可编辑3D建筑模型，结合规则检查器迭代提升质量，实现直观的聊天式建模。

摘要：

传统的BIM创作过程通常要求设计师掌握复杂且繁琐的建模命令，以便在BIM创作工具中实现其设计意图。这种额外的认知负担使设计过程复杂化，并阻碍了BIM和基于模型的设计在AEC（建筑、工程和施工）行业的采用。为了更直观地表达设计意图，我们提出了Text2BIM，这是一个基于LLM的多智能体框架，能够根据自然语言指令生成3D建筑模型。该框架协调多个LLM智能体进行协作和推理，将文本用户输入转换为调用BIM创作工具API的命令式代码，从而直接在软件中生成具有内部布局、外部围护结构和语义信息的可编辑BIM模型。此外，智能体工作流中引入了基于规则的模型检查器，利用预定义的领域知识指导LLM智能体解决生成模型中的问题，并迭代地提高模型质量。我们进行了大量实验，比较和分析了三种不同LLM在所提出框架下的性能。评估结果表明，我们的方法能够有效地生成高质量、结构合理的建筑模型，且与用户输入指定的抽象概念相一致。最后，开发了一个交互式软件原型，将框架集成到BIM创作软件Vectorworks中，展示了通过聊天进行建模的潜力。代码可在以下地址获取：https://github.com/dcy0577/Text2BIM

英文摘要：

The conventional BIM authoring process typically requires designers to master complex and tedious modeling commands in order to materialize their design intentions within BIM authoring tools. This additional cognitive burden complicates the design process and hinders the adoption of BIM and model-based design in the AEC (Architecture, Engineering, and Construction) industry. To facilitate the expression of design intentions more intuitively, we propose Text2BIM, an LLM-based multi-agent framework that can generate 3D building models from natural language instructions. This framework orchestrates multiple LLM agents to collaborate and reason, transforming textual user input into imperative code that invokes the BIM authoring tool's APIs, thereby generating editable BIM models with internal layouts, external envelopes, and semantic information directly in the software. Furthermore, a rule-based model checker is introduced into the agentic workflow, utilizing predefined domain knowledge to guide the LLM agents in resolving issues within the generated models and iteratively improving model quality. Extensive experiments were conducted to compare and analyze the performance of three different LLMs under the proposed framework. The evaluation results demonstrate that our approach can effectively generate high-quality, structurally rational building models that are aligned with the abstract concepts specified by user input. Finally, an interactive software prototype was developed to integrate the framework into the BIM authoring software Vectorworks, showcasing the potential of modeling by chatting. The code is available at: https://github.com/dcy0577/Text2BIM

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑