DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation
This work addresses the problem of generating high-quality, adaptable presentations for users by moving beyond predefined workflows and fixed templates, offering an incremental improvement in agentic presentation generation.
This paper introduces DeepPresenter, an agentic framework for presentation generation that autonomously plans, renders, and revises slides based on environmental observations. It achieves state-of-the-art performance on diverse presentation-generation scenarios, with a fine-tuned 9B model remaining highly competitive at a substantially lower cost.
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