@inproceedings{xiang-etal-2025-promptsculptor,
    title = "{P}rompt{S}culptor: Multi-Agent Based Text-to-Image Prompt Optimization",
    author = "Xiang, Dawei  and
      Xu, Wenyan  and
      Chu, Kexin  and
      Ding, Tianqi  and
      Shen, Zixu  and
      Zeng, Yiming  and
      Su, Jianchang  and
      Zhang, Wei",
    editor = {Habernal, Ivan  and
      Schulam, Peter  and
      Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-demos.59/",
    pages = "774--786",
    ISBN = "979-8-89176-334-0",
    abstract = "The rapid advancement of generative AI has democratized access to powerful tools such as Text-to-Image (T2I) models. However, to generate high-quality images, users must still craft detailed prompts specifying scene, style, and context{---}often through multiple rounds of refinement. We propose PromptSculptor, a novel multi-agent framework that automates this iterative prompt optimization process. Our system decomposes the task into four specialized agents that work collaboratively to transform a short, vague user prompt into a comprehensive, refined prompt. By leveraging Chain-of-Thought (CoT) reasoning, our framework effectively infers hidden context and enriches scene and background details. To iteratively refine the prompt, a self-evaluation agent aligns the modified prompt with the original input, while a feedback-tuning agent incorporates user feedback for further refinement. Experimental results demonstrate that PromptSculptor significantly enhances output quality and reduces the number of iterations needed for user satisfaction. Moreover, its model-agnostic design allows seamless integration with various T2I models, paving the way for industrial applications."
}