Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards

• URL: http://arxiv.org/abs/2605.14117v1
• Date: Wed, 13 May 2026 21:06:12 GMT
• Title: Generative Floor Plan Design with LLMs via Reinforcement Learning with Verifiable Rewards
• Abstract summary: An AI system for professional floor plan design must precisely control room dimensions and areas while respecting the desired connectivity between rooms.<n>Existing generative approaches focus primarily on respecting the requested connectivity between rooms, but do not support generating floor plans that respect numerical constraints.<n>We introduce a text-based floor plan generation approach that fine-tunes a large language model (LLM) on real plans and then applies reinforcement learning with verifiable rewards.<n>Our results demonstrate that LLMs can effectively handle constraints in this setting, suggesting broader applications for text-based generative modeling.
• Score: 16.41930427892441
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: An AI system for professional floor plan design must precisely control room dimensions and areas while respecting the desired connectivity between rooms and maintaining functional and aesthetic quality. Existing generative approaches focus primarily on respecting the requested connectivity between rooms, but do not support generating floor plans that respect numerical constraints. We introduce a text-based floor plan generation approach that fine-tunes a large language model (LLM) on real plans and then applies reinforcement learning with verifiable rewards (RLVR) to improve adherence to topological and numerical constraints while discouraging invalid or overlapping outputs. Furthermore, we design a set of constraint adherence metrics to systematically measure how generated floor plans align with user-defined constraints. Our model generates floor plans that satisfy user-defined connectivity and numerical constraints and outperforms existing methods on Realism, Compatibility, and Diversity metrics. Across all tasks, our approach achieves at least a 94% relative reduction in Compatibility compared with existing methods. Our results demonstrate that LLMs can effectively handle constraints in this setting, suggesting broader applications for text-based generative modeling.

Related papers

• Leveraging Inter-object Affordances for Efficient Planning in Contact-rich Tasks [42.29257983447145]
  Traditional task-and-motion planning (TAMP) approaches focus on defining sequences of actions along with the necessary geometric and kinematic constraints.<n>We propose a method that leverages a TAMP approach, defining object-centric abstractions of execution constraints.<n>Our approach achieves significantly higher planning success rates and improves planning times by one to two orders of magnitude compared to other methods.
  arXiv  Detail & Related papers  (2026-08-26T11:12:46Z)
• AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints [65.27107190916512]
  We introduce AdaPlanBench, an interactive benchmark for evaluating whether Large Language Model (LLM) agents can adaptively plan and re-plan under progressively revealed constraints.<n>AdaPlanBench is built on 307 household tasks, with a scalable constraint construction pipeline that augments each task with dual constraints.<n>Experiments show that adaptive planning under dual constraints remains challenging, with the best model reaching only 67.75% accuracy.
  arXiv  Detail & Related papers  (2026-06-04T02:47:29Z)
• Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance [108.46436073194546]
  We argue that effective planning should be local, visually grounded, internally generated, and directly aligned with action.<n>We propose Afford-VLA, a unified framework that internalizes task-conditioned affordance as an explicit visual planning interface within VLA models.
  arXiv  Detail & Related papers  (2026-05-22T20:43:47Z)
• Unified Vector Floorplan Generation via Markup Representation [36.228613615394856]
  We introduce Floorplan Markup Language (FML), a representation that encodes floorplan information within a single structured grammar.<n>We develop a transformer-based generative model, FMLM, capable of producing high-fidelity and functional floorplans under diverse conditions.
  arXiv  Detail & Related papers  (2026-04-06T17:04:30Z)
• Connectivity-Aware Representations for Constrained Motion Planning via Multi-Scale Contrastive Learning [6.0393663164774125]
  The objective of constrained motion planning is to connect start and goal configurations while satisfying task-specific constraints.<n>This paper addresses these challenges by learning a connectivity-aware representation for selecting start and goal configurations prior to planning.
  arXiv  Detail & Related papers  (2026-03-26T10:44:21Z)
• LLM-Grounded Dynamic Task Planning with Hierarchical Temporal Logic for Human-Aware Multi-Robot Collaboration [17.886091169216538]
  Large Language Models (LLM) enable non-experts to specify openworld multi-robot tasks.<n>LLM plans often lack feasibility and are not efficient, especially in long-horizon scenarios.<n>We propose a neuro-symbolic framework that grounds reasoning into hierarchical specifications.
  arXiv  Detail & Related papers  (2026-02-10T07:11:36Z)
• TLC-Plan: A Two-Level Codebook Based Network for End-to-End Vector Floorplan Generation [19.063941053235567]
  We propose TLC-Plan, a hierarchical generative model that directly synthesizes vectors from spatial input boundaries.<n>TLC-Plan employs a two-level VQ-VAE to encode global layouts as semantically labeled room bounding boxes.<n>Experiments show state-of-the-art performance on RPLAN dataset and leading results on LI dataset.
  arXiv  Detail & Related papers  (2026-02-06T15:36:50Z)
• Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning [52.03884701766989]
  offline reinforcement learning (RL) algorithms typically impose constraints on action selection.<n>We propose a new neighborhood constraint that restricts action selection in the Bellman target to the union of neighborhoods of dataset actions.<n>We develop a simple yet effective algorithm, Adaptive Neighborhood-constrained Q learning (ANQ), to perform Q learning with target actions satisfying this constraint.
  arXiv  Detail & Related papers  (2025-11-04T13:42:05Z)
• Platform-Aware Mission Planning [50.56223680851687]
  We introduce the problem of Platform-Aware Mission Planning (PAMP), addressing it in the setting of temporal durative actions.<n>The first baseline approach amalgamates the mission and platform levels, while the second is based on an abstraction-refinement loop.<n>We prove the soundness and completeness of the proposed approaches and validate them experimentally.
  arXiv  Detail & Related papers  (2025-01-16T16:20:37Z)
• HouseTune: Two-Stage Floorplan Generation with LLM Assistance [10.558141230827847]
  This paper proposes a two-stage text-to-floorplan framework that combines the reasoning capability of Large Language Models with the generative power of diffusion models.<n> Experimental results demonstrate that our approach achieves state-of-the-art performance across all metrics, which validates its effectiveness in practical home design applications.
  arXiv  Detail & Related papers  (2024-11-19T06:57:45Z)
• Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification [76.14641982122696]
  We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control. We show that our approach leads to an LLM that produces fewer inappropriate responses while achieving competitive performance on benchmarks and a toxicity detection task.
  arXiv  Detail & Related papers  (2024-10-07T23:38:58Z)
• Planning as In-Painting: A Diffusion-Based Embodied Task Planning Framework for Environments under Uncertainty [56.30846158280031]
  Task planning for embodied AI has been one of the most challenging problems. We propose a task-agnostic method named 'planning as in-painting' The proposed framework achieves promising performances in various embodied AI tasks.
  arXiv  Detail & Related papers  (2023-12-02T10:07:17Z)
• DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability [58.75803543245372]
  Task and Motion Planning (TAMP) approaches are suited for planning multi-step autonomous robot manipulation. We propose to overcome these limitations by composing diffusion models using a TAMP system. We show how the combination of classical TAMP, generative modeling, and latent embedding enables multi-step constraint-based reasoning.
  arXiv  Detail & Related papers  (2023-06-22T20:40:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.