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

2024-08-15

arXiv.org

AI Summary

To address the challenges of low-fidelity natural language intent parsing and high cognitive load in BIM modeling for the AEC industry, this paper proposes the first multi-LLM agent-based collaborative modeling framework tailored to AEC. The method employs domain-knowledge-guided multi-agent reasoning to parse natural language instructions into executable Vectorworks API calls, integrated with a rule-engine-driven closed-loop verification and iterative refinement mechanism to achieve end-to-end generation of structurally sound and semantically complete BIM models. The framework synergistically leverages LLaMA-3, Qwen, and GPT-4 to support layout design, building envelope modeling, and IFC semantic annotation. Experimental results demonstrate significant improvements in structural validity and intent alignment of generated models. An interactive prototype has been deployed within Vectorworks, enabling real-time user feedback and model refinement.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

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.

Problem

• Simplifying BIM modeling with natural language input
• Reducing cognitive load in BIM design process
• Automating 3D model generation from text instructions

Innovation

• LLM-based multi-agent framework for BIM generation
• Natural language to imperative code conversion
• Rule-based model checker for quality improvement