将科研论文自动转为可交互网页系统，让读者动态体验研究机制。
I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications
- 基于论文内容自动生成可操作的交互式网页系统。
- 在19篇论文上测试，新方法生成系统质量显著提升。
- 适合科研人员、教育者快速理解复杂技术机制。
视觉语言模型的进步使得自主智能体能够完成复杂推理、工具使用和文档理解。然而，现有文档智能体主要将论文转化为静态内容（如摘要、网页或幻灯片），难以呈现涉及动态机制与状态转换的技术论文。本文提出一种「论文转交互系统」智能体，可将PDF论文端到端转化为可执行的交互式网页系统。该系统支持用户修改输入并观察动态行为变化。为此，我们构建了一个包含19篇论文及专家制作的交互系统作为真实标准的基准数据集。同时提出PaperVoyager框架，通过显式建模机制与交互逻辑提升生成质量。实验表明，PaperVoyager显著改善了生成系统的准确性与可用性，为科学论文的交互式理解提供了新范式。
原文摘要 · Abstract (English)
Recent advances in visual language models have enabled autonomous agents for complex reasoning, tool use, and document understanding. However, existing document agents mainly transform papers into static artifacts such as summaries, webpages, or slides, which are insufficient for technical papers involving dynamic mechanisms and state transitions. In this work, we propose a Paper-to-Interactive-System Agent that converts research papers into executable interactive web systems. Given a PDF paper, the agent performs end-to-end processing without human intervention, including paper understanding, system modeling, and interactive webpage synthesis, enabling users to manipulate inputs and observe dynamic behaviors. To evaluate this task, we introduce a benchmark of 19 research papers paired with expert-built interactive systems as ground truth. We further propose PaperVoyager, a structured generation framework that explicitly models mechanisms and interaction logic during synthesis. Experiments show that PaperVoyager significantly improves the quality of generated interactive systems, offering a new paradigm for interactive scientific paper understanding.
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。