Design-MLLM: A Reinforcement Alignment Framework for Verifiable and Aesthetic Interior Design

TL;DR

Design-MLLM introduces a reinforcement learning framework that effectively balances spatial feasibility and aesthetic preferences in interior design generation, ensuring practical and visually appealing results.

Contribution

It presents a novel reinforcement alignment approach that explicitly separates and optimizes for feasibility and aesthetics in interior design using dual-branch rewards.

Findings

Achieves higher feasibility in generated designs.

Improves aesthetic coherence among feasible solutions.

Outperforms baseline models on benchmark datasets.

Abstract

Interior design is a requirements-to-visual-plan generation process that must simultaneously satisfy verifiable spatial feasibility and comparative aesthetic preferences. While recent multimodal large language models (MLLMs) offer a unified foundation for interpreting user intent and producing design rationales, our empirical analysis reveals a persistent contradiction in real-world deployment: MLLMs often produce layouts that are unbuildable and aesthetically inconsistent. These findings indicate that simply adding in-domain text is insufficient; effective interior design requires an alignment mechanism that separates hard constraints from soft preferences and coordinates them during optimization. To address this, we propose Design-MLLM, a reinforcement alignment framework that optimizes a feasibility-first preference objective via a dual-branch, aesthetic-oriented reward. Specifically, Design-MLLM (i) explicitly evaluates spatial feasibility using programmatic constraint checks, (ii) assesses aesthetic preference only among feasible candidates to avoid visually appealing but unexecutable shortcuts, and (iii) performs group-relative optimization to obtain stable preference signals. Through this process, Design-MLLM learns a controllable policy that consistently selects and generates solutions that are both executable and aesthetically coherent, rather than occasionally producing visually appealing but infeasible designs. Extensive experiments on various benchmark datasets demonstrate the advantages of Design-MLLM.