FurniMAS: Language-Guided Furniture Decoration using Multi-Agent System

2025-07-07

AI Summary

Addressing the time-intensive nature and reliance on specialized artistic expertise in furniture decoration tasks, this paper proposes an automated approach based on a hybrid multi-agent system. The system integrates large language models (LLMs) with domain-specific non-linguistic agents—each assigned distinct roles—to jointly perform collaborative reasoning and multi-stage validation. It enables end-to-end generation of 3D decorative layouts from natural-language instructions specifying functional requirements, aesthetic preferences, and atmospheric intent. Technically, the method unifies multi-agent architecture, semantic understanding, 3D scene modeling, and logic-constrained reasoning. Experimental evaluation demonstrates that our approach significantly outperforms existing baselines in decoration plausibility, creative diversity, and visual fidelity. Moreover, it exhibits strong practicality and scalability in real-world deployment scenarios.

Technology Category

• Multiagent Systems: Mechanism Design
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction

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: Cost models of using LLMs in production systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Furniture decoration is an important task in various industrial applications. However, achieving a high-quality decorative result is often time-consuming and requires specialized artistic expertise. To tackle these challenges, we explore how multi-agent systems can assist in automating the decoration process. We propose FurniMAS, a multi-agent system for automatic furniture decoration. Specifically, given a human prompt and a household furniture item such as a working desk or a TV stand, our system suggests relevant assets with appropriate styles and materials, and arranges them on the item, ensuring the decorative result meets functionality, aesthetic, and ambiance preferences. FurniMAS assembles a hybrid team of LLM-based and non-LLM agents, each fulfilling distinct roles in a typical decoration project. These agents collaborate through communication, logical reasoning, and validation to transform the requirements into the final outcome. Extensive experiments demonstrate that our FurniMAS significantly outperforms other baselines in generating high-quality 3D decor.

Problem

• Automating furniture decoration using multi-agent systems
• Generating style-appropriate decor from human prompts
• Enhancing decor quality via collaborative agent roles

Innovation

• Multi-agent system automates furniture decoration
• Hybrid LLM and non-LLM agents collaborate
• Language-guided asset selection and arrangement