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

arXiv: https://arxiv.org/abs/2603.13312 · HTML: https://mlsanity.com/paper/2603.13312/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 46 references that are in the map.
- First posted on arXiv 4 Mar 2026.

## Builds on (most cited first, 21 of 21)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark](https://mlsanity.com/paper/2402.04788/) (2024)
- [Holodeck: Language Guided Generation of 3D Embodied AI Environments](https://mlsanity.com/paper/2312.09067/) (2023)
- [ATISS: Autoregressive Transformers for Indoor Scene Synthesis](https://mlsanity.com/paper/2110.03675/) (2021)
- [House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation](https://mlsanity.com/paper/2003.06988/) (2020)
- [I-Design: Personalized LLM Interior Designer](https://mlsanity.com/paper/2404.02838/) (2024)
- [Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey](https://mlsanity.com/paper/2411.17558/) (2024)
- [LLMs Beyond English: Scaling the Multilingual Capability of LLMs with Cross-Lingual Feedback](https://mlsanity.com/paper/2406.01771/) (2024)
- [Multimodal Spatial Reasoning in the Large Model Era: A Survey and Benchmarks](https://mlsanity.com/paper/2510.25760/) (2025)
- [Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLM](https://mlsanity.com/paper/2407.21333/) (2024)
- [Surveying the MLLM Landscape: A Meta-Review of Current Surveys](https://mlsanity.com/paper/2409.18991/) (2024)
- [Learning to Think: Information-Theoretic Reinforcement Fine-Tuning for LLMs](https://mlsanity.com/paper/2505.10425/) (2025)
- [TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigation](https://mlsanity.com/paper/2411.16425/) (2024)
- [Follow-Your-Instruction: A Comprehensive MLLM Agent for World Data Synthesis](https://mlsanity.com/paper/2508.05580/) (2025)
- [MindGPT-4ov: An Enhanced MLLM via a Multi-Stage Post-Training Paradigm](https://mlsanity.com/paper/2512.02895/) (2025)
- [Group Causal Policy Optimization for Post-Training Large Language Models](https://mlsanity.com/paper/2508.05428/) (2025)
- [COPO: Causal-Oriented Policy Optimization for Hallucinations of MLLMs](https://mlsanity.com/paper/2508.04182/) (2025)
- [Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning](https://mlsanity.com/paper/2602.06475/) (2026)

## Abstract (arXiv)

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.