Co-Layout: LLM-driven Co-optimization for Interior Layout

2025-11-16

AI Summary

This work addresses the challenge of jointly optimizing room partitioning, furniture placement, and multiple constraints in automated indoor layout design. We propose an end-to-end collaborative optimization framework integrating large language models (LLMs) with grid-based integer programming. Methodologically, we introduce a unified, scalable grid representation inspired by Le Corbusier’s “Modulor,” enabling joint semantic understanding—parsing textual instructions to extract connectivity, accessibility, exclusivity, and user preferences—and mathematical planning via hierarchical integer optimization. A coarse-to-fine two-stage solving strategy ensures scalability and precision. Experiments demonstrate that our approach significantly outperforms existing two-stage methods in layout plausibility, functional compliance, and computational efficiency. To our knowledge, this is the first method to achieve integrated modeling and efficient resolution of semantic, geometric, and topological constraints within a single unified framework.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization
• Search and Optimization: Mixed Discrete/Continuous Search

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: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

We present a novel framework for automated interior design that combines large language models (LLMs) with grid-based integer programming to jointly optimize room layout and furniture placement. Given a textual prompt, the LLM-driven agent workflow extracts structured design constraints related to room configurations and furniture arrangements. These constraints are encoded into a unified grid-based representation inspired by ``Modulor". Our formulation accounts for key design requirements, including corridor connectivity, room accessibility, spatial exclusivity, and user-specified preferences. To improve computational efficiency, we adopt a coarse-to-fine optimization strategy that begins with a low-resolution grid to solve a simplified problem and guides the solution at the full resolution. Experimental results across diverse scenarios demonstrate that our joint optimization approach significantly outperforms existing two-stage design pipelines in solution quality, and achieves notable computational efficiency through the coarse-to-fine strategy.

Problem

• Jointly optimizes room layout and furniture placement using LLMs
• Encodes design constraints into unified grid representation for automation
• Improves computational efficiency through coarse-to-fine optimization strategy

Innovation

• LLM extracts design constraints from text
• Grid-based integer programming optimizes layouts
• Coarse-to-fine strategy enhances computational efficiency