Agentic Designer: Progressive Multi-Agent Collaboration for Structure-Aware Interior Layout Generation

2026-07-22

AI Summary

This study addresses the challenge of automatically generating indoor furniture layouts that satisfy architectural constraints—such as walls, doors, and windows—while ensuring functional plausibility. The authors propose a progressive multi-agent collaborative framework that decomposes layout generation into three stages: proposal, validation, and refinement, executed jointly by a generator, evaluator, and optimizer to verify and correct geometric constraints. A novel progressive consensus mechanism is introduced to incrementally validate constraints, thereby mitigating error accumulation. Additionally, the work presents InStruct, the first structure-aware indoor layout benchmark, comprising over 18,000 parametrically annotated samples and structure-centric evaluation metrics. Extensive experiments demonstrate that the proposed method significantly outperforms existing approaches in both structural compliance and functional reasonableness, as confirmed through quantitative evaluation, qualitative analysis, and user studies.

Abstract

Generating realistic interior furniture layouts that strictly adhere to architectural constraints (e.g., walls, doors, and windows) remains a fundamental challenge in automated spatial design. Existing approaches, primarily based on one-shot generation using diffusion models or Large Language Models (LLMs), lack explicit mechanisms for intermediate geometric constraint verification, often resulting in structural collisions and functionally infeasible arrangements under complex room constraints. To address these challenges, we propose Agentic Designer, a progressive, multi-agent framework that formulates structure-aware interior layout generation as an iterative and constraint-verified decision process. By decomposing layout synthesis into modular stages of proposal, verification, and adjustment, the framework coordinates three specialized agents, a Generator, an Evaluator, and a Refiner, through a Progressive Consensus Mechanism. This mechanism enforces stepwise geometric validation and correction before each placement is committed, thereby preventing error accumulation. To facilitate this structure-aware paradigm and standardize evaluation, we establish InStruct, a comprehensive benchmark that integrates a dataset comprising over 18,000 high-quality, parametrically annotated samples with a novel suite of structure-centric metrics. Extensive quantitative evaluations, qualitative analyses, and user studies show that Agentic Designer significantly outperforms state-of-the-art methods, demonstrating substantial improvements in strict structural adherence and functional design coherence.

Problem

• interior layout generation
• architectural constraints
• structure-aware design
• geometric constraint verification
• functional feasibility

Innovation

• multi-agent collaboration
• structure-aware generation
• progressive consensus mechanism
• geometric constraint verification
• interior layout synthesis