发表机构
Shell Information Technology International; Shell China Limited; Delft University of Technology (TU Delft)（壳牌信息技术国际公司; 壳牌中国有限公司; 代尔夫特理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有布局基准忽视真实世界复杂性和设计创新，本文提出ALPS-Bench基准和CANDO多智能体框架，通过验证驱动的迭代优化，在多个基准上超越现有方法，实现约束感知布局合成。
AI 中文摘要
面向真实世界设施的布局生成是一项具有挑战性的问题，需要对不规则的场地边界、异构朝向、考虑通行的放置以及运动规划可行性进行推理。然而，生成式人工智能领域现有的大多数布局基准都针对矩形域上的简单放置，并依赖FID和IoU等分布性指标，这些指标奖励对数据集先验的符合，从而低估了设计创新。基于这些差距，我们引入了ALPS-Bench，一个包含1,000个专业标注的真实世界设施布局的基准，并配有一个基于结构化设计手册的实例特定评分协议。作为ALPS-Bench的强基线，我们提出了CANDO，一个无需训练的多智能体框架，其中专门的智能体通过验证驱动的循环迭代地细化布局，将推理集中在战略性的空间决策上。我们证明，CANDO在广泛采用的PubLayNet、RICO和PKU-PosterLayout基准上超越了最先进的训练基线和基于LLM的基线，确立了协作式智能体设计作为约束感知布局合成的一种广泛有效的方法。
英文摘要
Layout generation for real-world facilities is a challenging problem, requiring reasoning over irregular site boundaries, heterogeneous orientations, access-aware placements, and motion-planning feasibility. Yet, most existing layout benchmarks in the generative AI space target simpler placements over rectangular domains and rely on distributional metrics such as FID and IoU that reward conformity to dataset priors, thus discounting design innovation. Motivated by these gaps, we introduce ALPS-Bench, a benchmark of $1,000$ professionally annotated real-world facility layouts paired with an instance-specific scoring protocol grounded in a structured design manual. As a strong baseline for ALPS-Bench, we propose CANDO, a training-free multi-agent framework in which specialized agents iteratively refine layouts through a verification-grounded loop, concentrating reasoning on strategic spatial decisions. We demonstrate that CANDO surpasses state-of-the-art trained and LLM-based baselines on the widely adopted PubLayNet, RICO, and PKU-PosterLayout benchmarks, establishing cooperative agentic design as a broadly effective recipe for constraint-aware layout synthesis.
CommentsAccepted to appear in NeurIPS 2026. This is the preprint version of the paper
