@inproceedings{wang-etal-2025-mirror,
    title = "Mirror in the Model: Ad Banner Image Generation via Reflective Multi-{LLM} and Multi-modal Agents",
    author = "Wang, Zhao  and
      Chen, Bowen  and
      Shimose, Yotaro  and
      Moriyama, Sota  and
      Wang, Heng  and
      Takamatsu, Shingo",
    editor = "Potdar, Saloni  and
      Rojas-Barahona, Lina  and
      Montella, Sebastien",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2025",
    address = "Suzhou (China)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-industry.17/",
    pages = "246--266",
    ISBN = "979-8-89176-333-3",
    abstract = "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 etc. In this paper, we introduce **MIMO (Mirror In{-}the{-}Model)**, an agentic refinement framework for automatic ad banner generation. MIMO combines a hierarchical multimodal 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."
}