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

arXiv: https://arxiv.org/abs/2506.21934 · HTML: https://mlsanity.com/paper/2506.21934/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 27 Jun 2025.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG](https://mlsanity.com/paper/2501.09136/) (2025)
- [LayoutGAN: Generating Graphic Layouts with Wireframe Discriminators](https://mlsanity.com/paper/1901.06767/) (2019)
- [LayoutVAE: Stochastic Scene Layout Generation From a Label Set](https://mlsanity.com/paper/1907.10719/) (2019)
- [Variational Transformer Networks for Layout Generation](https://mlsanity.com/paper/2104.02416/) (2021)
- [Composition-aware Graphic Layout GAN for Visual-textual Presentation Designs](https://mlsanity.com/paper/2205.00303/) (2022)
- [LayoutDM: Transformer-based Diffusion Model for Layout Generation](https://mlsanity.com/paper/2305.02567/) (2023)
- [PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM](https://mlsanity.com/paper/2406.02884/) (2024)
- [Retrieval-Augmented Layout Transformer for Content-Aware Layout Generation](https://mlsanity.com/paper/2311.13602/) (2023)
- [VASCAR: Content-Aware Layout Generation via Visual-Aware Self-Correction](https://mlsanity.com/paper/2412.04237/) (2024)

## Built on by (most cited first, 7 of 7)

- [The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems](https://mlsanity.com/paper/2507.02097/) (2025)
- [LLMs as Orchestrators: Constraint-Compliant Multi-Agent Optimization for Recommendation Systems](https://mlsanity.com/paper/2601.19121/) (2026)
- [PSDesigner: Automated Graphic Design with a Human-Like Creative Workflow](https://mlsanity.com/paper/2603.25738/) (2026)
- [LLMs as Layout Designers: Enhanced Spatial Reasoning for Content-Aware Layout Generation](https://mlsanity.com/paper/2509.16891/) (2025)
- [From Pixels to Policies: Reinforcing Spatial Reasoning in Language Models for Content-Aware Layout Design](https://mlsanity.com/paper/2602.13912/) (2026)
- [MetaSynth: Multi-Agent Metadata Generation from Implicit Feedback in Black-Box Systems](https://mlsanity.com/paper/2510.01523/) (2025)
- [APD-Agents: A Large Language Model-Driven Multi-Agents Collaborative Framework for Automated Page Design](https://mlsanity.com/paper/2511.14101/) (2025)

## Abstract (arXiv)

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.