Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions

TL;DR

This paper introduces DynaSlide, a large dataset and framework for automatically updating presentation slides using natural language instructions and user-defined templates, addressing the challenge of dynamic, data-driven slide editing.

Contribution

The paper presents DynaSlide, a novel benchmark dataset and SlideAgent framework that enable natural language-guided, template-based slide updates with a focus on preserving style and layout.

Findings

SlideAgent effectively updates slides while maintaining layout and style.

DynaSlide provides over 20,000 real-world instruction-execution triples for training and evaluation.

Evaluation protocols highlight key challenges and future research directions.

Abstract

Presentation slides are a primary medium for data-driven reporting, yet keeping complex, analytics-style decks up to date remains labor-intensive. Existing automation methods mostly follow fixed template filling and cannot support dynamic updates for diverse, user-authored slide decks. We therefore define "Dynamic Slide Update via Natural Language Instructions on User-provided Templates" and introduce DynaSlide, a large-scale benchmark with 20,036 real-world instruction-execution triples (source slide, user instruction, target slide) grounded in a shared external database and built from business reporting slides under bring-your-own-template (BYO-template) conditions. To tackle this task, we propose SlideAgent, an agent-based framework that combines multimodal slide parsing, natural language instruction grounding, and tool-augmented reasoning for tables, charts, and textual conclusions. SlideAgent updates content while preserving layout and style, providing a strong reference baseline on DynaSlide. We further design end-to-end and component-level evaluation protocols that reveal key challenges and opportunities for future research. The dataset and code are available at https://github.com/XiaoZhou2024/SlideAgent.