Metraipolis › archive › dc_519dc6c116fc
FLOORA: A Human-Aligned Domain-Specific Language Model for Architectural Design — arXiv:2609.36064
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.36064
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:25:14.196Z
- SHA-256 of the archived text
89dc99c16bf8618eea2833b3c49ae9201ce0b891b4a5fa50a25481d45ce61c14- Stable URL of this page
https://metraipolis.com/documento/dc_519dc6c116fc
How to cite
FLOORA: A Human-Aligned Domain-Specific Language Model for Architectural Design — arXiv:2609.36064 — arXiv (en), https://arxiv.org/abs/2609.36064 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_519dc6c116fc (Metraipolis archive dc_519dc6c116fc, sha256 89dc99c16bf8618eea2833b3c49ae9201ce0b891b4a5fa50a25481d45ce61c14)
BibTeX
@misc{dc519dc6c116fc,
title = {FLOORA: A Human-Aligned Domain-Specific Language Model for Architectural Design — arXiv:2609.36064},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.36064},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_519dc6c116fc; sha256 89dc99c16bf8618eea2833b3c49ae9201ce0b891b4a5fa50a25481d45ce61c14},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36064. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Foundation models are powerful generators, but many engineering domains require structured representations that general-purpose systems handle poorly. We introduce FLOORA (Floor Layout Optimization with RL Alignment), a family of small domain-specific language (DSL) models for architectural layout generation. With specialized data and alignment, our 0.6B model outperforms much larger frontier models, achieving VLM judge win rates up to 92.0% on out-of-distribution real-world buildings and 96.0% on synthetic buildings. Human evaluations further corroborate these results, with FLOORA selected as the best model in 89.3% of evaluations. FLOORA combines a token-efficient DSL, custom tokenization, domain-specific pretraining, supervised fine-tuning (SFT), and reinforcement learning (RL) with learned human-preference and verifiable rewards. This pipeline improves architectural and geometric validity, supported by extensive empirical evaluation and ablation studies. Although focused on architecture, our results suggest that similar domain-specific recipes may be useful in other engineering domains with structured, verifiable outputs. Datasets, models, and inference code are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.36064 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T15:54:53.765Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).