DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation

TL;DR

DeepPresenter is an environment-grounded framework for autonomous presentation generation that adapts to user needs, refines content iteratively, and corrects issues during execution, achieving state-of-the-art results.

Contribution

It introduces an agentic, environment-grounded approach that enables flexible, feedback-driven presentation creation beyond fixed templates and scripted pipelines.

Findings

Achieves state-of-the-art performance on diverse presentation tasks.

Fine-tuned 9B model remains highly competitive at lower cost.

Supports long-horizon refinement through environmental observations.

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 9B model remains highly competitive at substantially lower cost. Our project is available at: https://github.com/icip-cas/PPTAgent