评测智能体对真实幻灯片的自然语言编辑能力，发现现有方法仍难处理复杂文档任务。
PPTArena: A Benchmark for PowerPoint Editing
- 构建包含1300+人工标注修改的幻灯片编辑基准，覆盖文本、图表、动画等多维度操作。
- 提出PPTPilot智能体，通过结构感知规划和迭代验证，在复杂编辑上提升超10个百分点。
- 适合研究AI自动化办公、人机交互与文档智能的开发者与研究人员参考。
我们提出PPTArena，一个用于评估智能体根据自然语言指令修改真实幻灯片的基准。不同于依赖图像或PDF渲染的基准，PPTArena包含100个幻灯片文稿，涵盖2,125张幻灯片上的1,300多个由人类精心标注的编辑操作，涉及文本、图表、动画及专业母版样式。每个编辑任务均提供原始文稿与目标规范，并由两名视觉-语言模型（VLM）裁判评分：一名基于结构差异评估指令遵循度，另一名基于幻灯片图像评估视觉质量。在此基准之上，我们提出PPTPilot——一种具备结构感知能力的智能体，能规划语义编辑序列，协调程序化工具与确定性XML操作，并在迭代的“计划-编辑-检查”循环中验证每一步结果。PPTPilot在复合型、布局敏感型及跨幻灯片编辑任务上显著优于强基线VLM智能体，性能提升超过10个百分点，且在视觉保真度与文稿一致性方面表现更优。然而，所有智能体在长周期、文档级任务上仍表现不佳，凸显可靠幻灯片编辑的挑战性。代码已公开于 https://github.com/michaelofengend/PPTArena。
原文摘要 · Abstract (English)
We introduce PPTArena, a benchmark for PowerPoint editing that evaluates how agents modify real slides from natural-language instructions. Unlike benchmarks that rely on image-PDF renderings or text-to-slide generation, PPTArena features 100 decks with over 1,300 human-curated edits across 2,125 slides, spanning text, charts, animations, and professional master styles. Each edit pairs a ground-truth deck with a target rubric and is scored by two Vision-Language Model (VLM) judges: one rates instruction following from structural diffs, the other visual quality from slide images. On top of this benchmark, we present PPTPilot, a structure-aware agent that plans semantic edit sequences, routes between programmatic tools and deterministic XML operations, and verifies each result in an iterative plan-edit-check loop. PPTPilot outperforms strong VLM-based agents by more than 10 percentage points on compound, layout-sensitive, and cross-slide edits, with large gains in visual fidelity and deck-wide consistency. Despite this, all agents still struggle on long-horizon, document-scale tasks, underscoring how hard reliable PowerPoint editing remains. We publicly release our code at https://github.com/michaelofengend/PPTArena .
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。