跳到正文
arXiv:cs.AI· R. Kenny Jones, Jiajun Wu, Maneesh Agrawala·· 17 小时前

Co-DSL:人类与 LLM 协同设计可复用空间概念用于布局生成

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

AI 导读

Co-DSL 让用户与 LLM 协同设计可复用的空间概念库,用户给出描述、LLM 生成初始实现,再通过示例场景观察执行行为并轻量反馈来修订逻辑。第二阶段 LLM 依据该库编写布局程序,执行后实例化为 concept-graph,由求解器搜索满足概念的布局。

正文

View PDF HTML (experimental)

Abstract: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.
Comments: Project page: this http URL
Subjects: Graphics (cs.GR); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2610.15290 [cs.GR]
  (or arXiv:2610.15290v1 [cs.GR] for this version)
  https://doi.org/10.48550/arXiv.2610.15290

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: R. Kenny Jones [view email]
[v1] Sun, 11 Oct 2026 02:49:48 UTC (22,797 KB)

来源:arXiv:cs.AI · arxiv.org