Problem
Research questions and friction points this paper is trying to address.
Layout Generation
Facility Layout Design
Benchmark Evaluation
Constraint-aware Synthesis
Generative AI
CANDO: Cooperative Agentic Network for Layout Design Optimization
🤖 AI Summary
This study addresses the generative challenges in real-world facility layout under complex constraints, including irregular boundaries, heterogeneous orientations, and motion planning feasibility. To this end, it proposes CANDO, a training-free multi-agent collaborative framework, alongside the ALPS-Bench benchmark. Methodologically, CANDO iteratively refines layout strategies through a verification-grounded reasoning loop guided by structured design specifications, while introducing a novel design-manual-based instance scoring protocol. Experimental results demonstrate that the proposed approach surpasses existing state-of-the-art models on mainstream benchmarks such as PubLayNet, significantly enhancing both the quality and novelty of layout generation in real-world scenarios. These findings establish the effectiveness of collaborative agents in constraint-aware layout synthesis.
📝 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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multi-agent framework
Training-free
Layout generation
Constraint-aware synthesis
Benchmark
🔎 Similar Papers
No similar papers found.
