# Mirror in the Model: Ad Banner Image Generation via Reflective Multi-LLM and Multi-modal Agents

arXiv: https://arxiv.org/abs/2507.03326 · HTML: https://mlsanity.com/paper/2507.03326/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 17 references that are in the map.
- First posted on arXiv 4 Jul 2025.

## Builds on (most cited first, 6 of 6)

- [COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design](https://mlsanity.com/paper/2311.16974/) (2023)
- [AutoPoster: A Highly Automatic and Content-aware Design System for Advertising Poster Generation](https://mlsanity.com/paper/2308.01095/) (2023)
- [Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation](https://mlsanity.com/paper/2310.08541/) (2023)
- [OpenCOLE: Towards Reproducible Automatic Graphic Design Generation](https://mlsanity.com/paper/2406.08232/) (2024)
- [BannerAgency: Advertising Banner Design with Multimodal LLM Agents](https://mlsanity.com/paper/2503.11060/) (2025)
- [STRICT: Stress Test of Rendering Images Containing Text](https://mlsanity.com/paper/2505.18985/) (2025)

## Built on by (most cited first, 1 of 1)

- [WebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluation](https://mlsanity.com/paper/2510.15306/) (2025)

## Abstract (arXiv)

Recent generative models such as GPT-4o have shown strong capabilities in producing high-quality images with accurate text rendering. However, commercial design tasks like advertising banners demand more than visual fidelity -- they require structured layouts, precise typography, consistent branding, and more. In this paper, we introduce MIMO (Mirror In-the-Model), an agentic refinement framework for automatic ad banner generation. MIMO combines a hierarchical multi-modal agent system (MIMO-Core) with a coordination loop (MIMO-Loop) that explores multiple stylistic directions and iteratively improves design quality. Requiring only a simple natural language based prompt and logo image as input, MIMO automatically detects and corrects multiple types of errors during generation. Experiments show that MIMO significantly outperforms existing diffusion and LLM-based baselines in real-world banner design scenarios.