DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zheng, Hao, Mo, Guozhao, Yan, Xinru, Yuan, Qianhao, Zhang, Wenkai, Chen, Xuanang, Lu, Yaojie, Lin, Hongyu, Han, Xianpei, Sun, Le
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908977469587456
author Zheng, Hao
Mo, Guozhao
Yan, Xinru
Yuan, Qianhao
Zhang, Wenkai
Chen, Xuanang
Lu, Yaojie
Lin, Hongyu
Han, Xianpei
Sun, Le
author_facet Zheng, Hao
Mo, Guozhao
Yan, Xinru
Yuan, Qianhao
Zhang, Wenkai
Chen, Xuanang
Lu, Yaojie
Lin, Hongyu
Han, Xianpei
Sun, Le
contents 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 9B model remains highly competitive at substantially lower cost. Our project is available at: https://github.com/icip-cas/PPTAgent
format Preprint
id arxiv_https___arxiv_org_abs_2602_22839
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation
Zheng, Hao
Mo, Guozhao
Yan, Xinru
Yuan, Qianhao
Zhang, Wenkai
Chen, Xuanang
Lu, Yaojie
Lin, Hongyu
Han, Xianpei
Sun, Le
Artificial Intelligence
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 9B model remains highly competitive at substantially lower cost. Our project is available at: https://github.com/icip-cas/PPTAgent
title DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation
topic Artificial Intelligence
url https://arxiv.org/abs/2602.22839