Large Language Model Agent for Structural Drawing Generation Using ReAct Prompt Engineering and Retrieval Augmented Generation

2025-07-25

AI Summary

Structural drafting remains heavily manual, resulting in low efficiency and prolonged design cycles. This paper proposes an LLM-based autonomous drafting framework that innovatively integrates the ReAct prompting strategy with Retrieval-Augmented Generation (RAG) to achieve precise semantic parsing and structured response generation from natural-language engineering descriptions. Centered on a large language model, the framework dynamically retrieves domain-specific structural code knowledge and invokes CAD operation tools to directly generate executable AutoCAD scripts—enabling end-to-end conversion from textual specifications to standardized structural drawings (e.g., beam-column layouts and reinforcement annotations). Experimental evaluation across multiple representative structural description tasks demonstrates 91.3% accuracy and an 87% reduction in average drafting time. The framework significantly accelerates design iteration and has been validated for feasibility and practicality in real-world engineering scenarios.

Technology Category

• Machine Learning: Structured Learning
• Natural Language Processing: Prompt Engineering / Prompting
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Structural drawings are widely used in many fields, e.g., mechanical engineering, civil engineering, etc. In civil engineering, structural drawings serve as the main communication tool between architects, engineers, and builders to avoid conflicts, act as legal documentation, and provide a reference for future maintenance or evaluation needs. They are often organized using key elements such as title/subtitle blocks, scales, plan views, elevation view, sections, and detailed sections, which are annotated with standardized symbols and line types for interpretation by engineers and contractors. Despite advances in software capabilities, the task of generating a structural drawing remains labor-intensive and time-consuming for structural engineers. Here we introduce a novel generative AI-based method for generating structural drawings employing a large language model (LLM) agent. The method incorporates a retrieval-augmented generation (RAG) technique using externally-sourced facts to enhance the accuracy and reliability of the language model. This method is capable of understanding varied natural language descriptions, processing these to extract necessary information, and generating code to produce the desired structural drawing in AutoCAD. The approach developed, demonstrated and evaluated herein enables the efficient and direct conversion of a structural drawing's natural language description into an AutoCAD drawing, significantly reducing the workload compared to current working process associated with manual drawing production, facilitating the typical iterative process of engineers for expressing design ideas in a simplified way.

Problem

• Automates structural drawing generation from natural language descriptions
• Reduces labor-intensive manual drawing processes in engineering
• Enhances accuracy using retrieval-augmented generation with external data

Innovation

• LLM agent for structural drawing generation
• ReAct prompt engineering enhances processing
• Retrieval Augmented Generation improves accuracy