@inproceedings{zheng-etal-2026-deeppresenter,
    title = "{D}eep{P}resenter: Environment-Grounded Reflection for Agentic Presentation Generation",
    author = "Zheng, Hao  and
      Mo, Guozhao  and
      Yan, Xinru  and
      Yuan, Qianhao  and
      Zhang, Wenkai  and
      Chen, Xuanang  and
      Lu, Yaojie  and
      Lin, Hongyu  and
      Han, Xianpei  and
      Sun, Le",
    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.1578/",
    pages = "31545--31558",
    ISBN = "979-8-89176-395-1",
    abstract = "Presentation generation requires deep content research, coherent visual design, and iterative refinement based on observation. However, existing presentation agents often rely on predefined workflows and fixed templates. To address this, we present DeepPresenter, an agentic framework that adapts to diverse user intents, enables effective feedback-driven refinement, and generalizes beyond a scripted pipeline. Specifically, DeepPresenter autonomously plans, renders, and revises intermediate slide artifacts to support long-horizon refinement with environmental observations. Furthermore, rather than relying on self-reflection over internal signals (e.g., reasoning traces), our environment-grounded reflection conditions the generation process on perceptual artifact states (e.g., rendered slides), enabling the system to identify and correct presentation-specific issues during execution. Results on the evaluation set covering diverse presentation-generation scenarios show that DeepPresenter achieves state-of-the-art performance, and the fine-tuned DeepPresenter-9B remains highly competitive at substantially lower cost."
}