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

## TL;DR

This paper introduces an AI-driven workflow utilizing Large Language Models to automatically generate architectural floor plans from natural language prompts, streamlining early design stages.

## Contribution

It presents a novel integration of LLMs, prompt engineering, and scripting to produce detailed, BIM-compatible floor plans with minimal manual input.

## Key findings

- Successfully generated functional residential layouts
- Maintained Revit parametric attributes for BIM integration
- Demonstrated workflow's effectiveness with a case study

## 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.