Fine-tuned LLMs trained with reinforcement learning using verifiable rewards produce floor plans that satisfy connectivity and numerical constraints, outperforming prior methods with at least 94% relative improvement in compatibility.
ArXiv:2506.14702v1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards
Fine-tuned LLMs trained with reinforcement learning using verifiable rewards produce floor plans that satisfy connectivity and numerical constraints, outperforming prior methods with at least 94% relative improvement in compatibility.