arXiv cs.MA· Athanasios Masouris, Zheng Jing, Benjamin Sam Chandler, Hadi Jamali-Rad·· 10 天前AI 评分26
CANDO：面向布局设计优化的协作式智能体网络
CANDO: Cooperative Agentic Network for Layout Design Optimization
AI 导读
针对现有生成式 AI 布局基准多局限于矩形区域、依赖 FID 和 IoU 等分布指标的问题，研究者提出 ALPS-Bench，包含 1,000 个专业标注的真实设施布局及基于结构化设计手册的评分协议。
正文 · 原文
Abstract: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.
| Comments: | Accepted to appear in NeurIPS 2026. This is the preprint version of the paper |
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.10044 [cs.MA] |
| (or arXiv:2610.10044v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.10044 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Athanasios Masouris [view email]
[v1]
Wed, 7 Oct 2026 13:20:52 UTC (6,420 KB)
来源：arXiv cs.MA · arxiv.org