用自然语言指令自动更新幻灯片，支持用户自定义模板。
Automatic Slide Updating with User-Defined Dynamic Templates and Natural Language Instructions
- 通过智能代理解析幻灯片并理解自然语言指令。
- 基于20,036组真实指令-执行对进行训练与评估。
- 适合需要频繁更新报告的商务与数据分析师。
演示文稿是数据驱动报告的主要载体，但保持复杂、分析型幻灯片集的最新状态仍需大量人工操作。现有自动化方法多采用固定模板填充，难以支持多样化的用户自定义幻灯片集的动态更新。为此，我们提出「基于用户提供的模板和自然语言指令的动态幻灯片更新」任务，并构建了DynaSlide——一个包含20,036个真实世界指令执行三元组（源幻灯片、用户指令、目标幻灯片）的大规模基准数据集，所有三元组均基于共享外部数据库生成，且在自带模板（BYO-template）条件下构建于商业报告幻灯片之上。为解决该任务，我们提出SlideAgent，一种基于智能体的框架，结合多模态幻灯片解析、自然语言指令定位以及表格、图表和文本结论的工具增强推理能力。SlideAgent可在保持版式与风格不变的前提下更新内容，为DynaSlide提供强有力的基线。我们进一步设计端到端与组件级评估协议，揭示未来研究的关键挑战与机遇。数据集与代码已开源：https://github.com/XiaoZhou2024/SlideAgent。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。