CAL-RAG: Retrieval-Augmented Multi-Agent Generation for Content-Aware Layout Design

TL;DR

CAL-RAG introduces a retrieval-augmented, multi-agent framework that leverages multimodal retrieval, large language models, and iterative reasoning to generate semantically aligned, visually coherent content-aware layouts, achieving state-of-the-art results.

Contribution

This work presents CAL-RAG, a novel framework combining retrieval, LLMs, and collaborative agents for improved automated layout design, addressing limitations of prior models.

Findings

Achieves state-of-the-art performance on PKU PosterLayout dataset

Outperforms baseline models like LayoutPrompter in multiple metrics

Demonstrates scalable and interpretable layout generation process

Abstract

Automated content-aware layout generation -- the task of arranging visual elements such as text, logos, and underlays on a background canvas -- remains a fundamental yet under-explored problem in intelligent design systems. While recent advances in deep generative models and large language models (LLMs) have shown promise in structured content generation, most existing approaches lack grounding in contextual design exemplars and fall short in handling semantic alignment and visual coherence. In this work we introduce CAL-RAG, a retrieval-augmented, agentic framework for content-aware layout generation that integrates multimodal retrieval, large language models, and collaborative agentic reasoning. Our system retrieves relevant layout examples from a structured knowledge base and invokes an LLM-based layout recommender to propose structured element placements. A vision-language grader agent evaluates the layout with visual metrics, and a feedback agent provides targeted refinements, enabling iterative improvement. We implement our framework using LangGraph and evaluate it on the PKU PosterLayout dataset, a benchmark rich in semantic and structural variability. CAL-RAG achieves state-of-the-art performance across multiple layout metrics -- including underlay effectiveness, element alignment, and overlap -- substantially outperforming strong baselines such as LayoutPrompter. These results demonstrate that combining retrieval augmentation with agentic multi-step reasoning yields a scalable, interpretable, and high-fidelity solution for automated layout generation.