Reproduce “RenoLayout: Unified Floorplan Renovation and Furniture Layout for Constraint-Aware Residential Design” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jingguo Liu, Yuanqing Liu, Chong Zhang, Yue Yang
RenoLayout transforms existing homes by generating executable spatial plans from the current layout and requested design points. It learns from paired before-and-after renovations and uses staged training with preference optimization followed by rule-based reward optimization. On a 200-case benchmark, this Qwen3-8B-based system achieves 91.63% Recall@1 and 61.00% Pass@1, while professional designers rate it 5.43/10 versus 7.00/10 for ground-truth plans.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.