# Rethinking Floorplan Generation with Space Syntax: From Design Theory to Model Improvement

arXiv: https://arxiv.org/abs/2602.22507 · HTML: https://mlsanity.com/paper/2602.22507/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 51 references that are in the map.
- First posted on arXiv 26 Feb 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)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models](https://mlsanity.com/paper/2312.06585/) (2023)
- [Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling](https://mlsanity.com/paper/1908.00222/) (2019)
- [Diffusion Policy Policy Optimization](https://mlsanity.com/paper/2409.00588/) (2024)
- [Deep Generative Models in Engineering Design: A Review](https://mlsanity.com/paper/2110.10863/) (2021)
- [House-GAN: Relational Generative Adversarial Networks for Graph-constrained House Layout Generation](https://mlsanity.com/paper/2003.06988/) (2020)
- [HouseDiffusion: Vector Floorplan Generation via a Diffusion Model with Discrete and Continuous Denoising](https://mlsanity.com/paper/2211.13287/) (2022)
- [Multimodal Image Synthesis and Editing: The Generative AI Era](https://mlsanity.com/paper/2112.13592/) (2021)
- [Generative Layout Modeling using Constraint Graphs](https://mlsanity.com/paper/2011.13417/) (2020)
- [Graph Transformer GANs for Graph-Constrained House Generation](https://mlsanity.com/paper/2303.08225/) (2023)
- [Scores as Actions: a framework of fine-tuning diffusion models by continuous-time reinforcement learning](https://mlsanity.com/paper/2409.08400/) (2024)
- [iPLAN: Interactive and Procedural Layout Planning](https://mlsanity.com/paper/2203.14412/) (2022)
- [GSDiff: Synthesizing Vector Floorplans via Geometry-enhanced Structural Graph Generation](https://mlsanity.com/paper/2408.16258/) (2024)
- [DStruct2Design: Data and Benchmarks for Data Structure Driven Generative Floor Plan Design](https://mlsanity.com/paper/2407.15723/) (2024)
- [The complexity of testing all properties of planar graphs, and the role of isomorphism](https://mlsanity.com/paper/2108.10547/) (2021)

## Abstract (arXiv)

Architectural design increasingly adopts generative AI (GenAI) for floorplan generation, an early-stage design task exploring how spaces should be organized for use. Yet fidelity objectives inherited from native visual and geometric generators do not automatically capture this design purpose. This organization remains largely implicit in generated representations, limiting direct evaluation and feedback. Drawing on space syntax, an established architectural design theory, the Space Syntax Integration Operator (SSIO) recovers convex-space access graphs across heterogeneous formats. This theory-grounded shared intermediate representation, which we call a design container, supports evaluation and model understanding of spatial design. Applying SSIO to four residential corpora spanning 15 countries reveals public spaces' integration levels are highest, with corpus-dependent distributions. These patterns underpin the RPLAN-SSI benchmark, an empirical design reference system assessing population-level functional-profile alignment (IPD) and within-plan public-space advantage (PIA). Comparison with this residential reference reveals a design gap: public spaces in generated floorplans have a smaller integration advantage over other spaces. To address this gap, Space Syntax-Guided Post-Training (SSPT) provides a plug-and-play design-learning interface: SSIO-derived RL feedback improves IPD and PIA across five heterogeneous diffusion backbones while preserving native mechanisms. We further discuss how this approach may inform GenAI applications in other design domains.