mlsanityData to 14 Oct 2026

Co-DSL: Human-LLM Co-design of Reusable Spatial Concepts for Layout Generation

arXiv 2610.15290 ↗First posted 11 Oct 2026cs.GR cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present Co-DSL, a framework in which users and LLMs co-design reusable spatial concepts for layout generation. In the first stage, our system allows users to create a library of personalized operations. To add a concept, a user provides a description, which the LLM converts into an initial implementation. The user can then observe the concept's execution behavior over example scenarios and provide lightweight feedback to the LLM, which revises the concept's implementation logic. In the second stage, given a library, an LLM can author a layout program that meets a new layout request from a user. Executing a layout program instantiates a concept-graph, a declarative composition of library concepts. In this way, we require the LLM only to specify which concepts should hold, while we use a solver to search for a layout that satisfies them. Across five spatial layout domains, we find that Co-DSL libraries let LLMs capture layout patterns that are challenging for prior fixed-operation systems, and demonstrate that our concept-graph representation is needed for LLMs to reliably compose concepts together. We further find that Co-DSL lets LLMs author generative layout programs that expose high-level parametric controls users can manipulate to explore a distribution of related layouts without re-prompting.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 65 references that are in the map. First posted on arXiv 11 Oct 2026.

Builds on

20 of 65 references.

References · 20

  1. 2023Holodeck: Language Guided Generation of 3D Embodied AI Environmentscited by 268
  2. 2021ATISS: Autoregressive Transformers for Indoor Scene Synthesiscited by 200
  3. 2023DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesiscited by 166
  4. 2024InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Priorcited by 117
  5. 2024GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guided Generative Gaussian Splattingcited by 109
  6. 2023GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphscited by 97
  7. 2024CAD-MLLM: Unifying Multimodality-Conditioned CAD Generation With MLLMcited by 81
  8. 2024TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Taskscited by 75
  9. 2025SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agentcited by 56
  10. 2023LILO: Learning Interpretable Libraries by Compressing and Documenting Codecited by 49
  11. 2021Leveraging Language to Learn Program Abstractions and Search Heuristicscited by 45
  12. 2024ReGAL: Refactoring Programs to Discover Generalizable Abstractionscited by 36
8 more
  1. 2024The Scene Language: Representing Scenes with Programs, Words, and Embeddingscited by 36
  2. 2025FlairGPT: Repurposing LLMs for Interior Designscited by 24
  3. 2022babble: Learning Better Abstractions with E-Graphs and Anti-Unificationcited by 23
  4. 2023ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitivescited by 23
  5. 2024Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLMcited by 21
  6. 2018Fast and Scalable Position-Based Layout Synthesiscited by 16
  7. 2025Procedural Scene Programs for Open-Universe Scene Generation: LLM-Free Error Correction via Program Searchcited by 10
  8. 2019Sketch-n-Sketch: Output-Directed Programming for SVGcited by 5

Built on by

Not cited yet.