Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs

2025-08-30

AI Summary

This study addresses the challenge of automating early-stage architectural design by enabling direct generation of BIM-compatible floor plans from natural language prompts. Methodologically, it integrates prompt engineering, furniture layout optimization algorithms, and Python-based automation to semantically drive the placement of walls, doors, windows, and furniture—while preserving native Revit parametric properties. The key contribution is the first transparent, reproducible NL→BIM generation pipeline that produces spatially coherent, structurally sound floor plan sketches directly importable into professional BIM tools. Evaluation on a medium-scale residential case demonstrates functional validity and structural integrity of generated layouts, significantly reducing manual drafting effort. This work establishes a practical, deployable technical pathway for integrating large language models into architectural design workflows.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Planning, Routing, and Scheduling: Planning with Language Models
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

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: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

This paper presents the development of an AI-powered workflow that uses Large Language Models (LLMs) to assist in drafting schematic architectural floor plans from natural language prompts. The proposed system interprets textual input to automatically generate layout options including walls, doors, windows, and furniture arrangements. It combines prompt engineering, a furniture placement refinement algorithm, and Python scripting to produce spatially coherent draft plans compatible with design tools such as Autodesk Revit. A case study of a mid-sized residential layout demonstrates the approach's ability to generate functional and structured outputs with minimal manual effort. The workflow is designed for transparent replication, with all key prompt specifications documented to enable independent implementation by other researchers. In addition, the generated models preserve the full range of Revit-native parametric attributes required for direct integration into professional BIM processes.

Problem

• Generating architectural floor plans from natural language prompts
• Automating layout design including walls, doors, windows and furniture
• Creating BIM-compatible draft plans with minimal manual effort

Innovation

• LLMs generate architectural layouts from text
• Combines prompt engineering with placement algorithms
• Produces BIM-compatible parametric Revit models