@inproceedings{cui-etal-2026-design,
    title = "Design First, Code Later: Aesthetically Pleasing Template-Free Slides Generation",
    author = "Cui, Zhiyao  and
      Wang, Chenxu  and
      Hu, Shuyue  and
      Zhang, Yiqun  and
      Shao, Wenqi  and
      Zhang, Qiaosheng  and
      Wang, Zhen",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.1524/",
    pages = "30470--30490",
    ISBN = "979-8-89176-395-1",
    abstract = "Producing presentation slides automatically entails coordinating narrative structure with page-level graphic design under strict spatial constraints. For such structured multimodal tasks, a well-organized design process is essential to ensure the final quality of slides. Existing approaches rely on fixed templates or directly emit executable code, thereby both limiting the creative layout-design capabilities of LLMs and bypassing the essential slide-page design step. To address these limitations, this paper: (1) proposes a hierarchical slides generation workflow \textbf{DeepSlides} that systematically organizes slide design tasks without any predefined template or style, decoupling slide-page design from implementation; (2) introduces \textbf{SlideDesign}, a dataset tailored specifically for slides generation tasks; (3) presents a multi-agent reinforcement learning training paradigm and trains a couple of models \textbf{SlideQwens} for slide design and implementation. Experimental results demonstrate that our proposed framework outperforms baseline methods on evaluated metrics and achieves superior performance in human preference evaluations. The dataset and code are available at: \url{https://anonymous.4open.science/r/DeepSlides-D14D}"
}