用AI自动把论文变成交互式网页，效果远超现有方法。
Paper2Web: Let's Make Your Paper Alive!
- 开发自主代理系统，分步优化内容与布局
- 在多项指标上超越模板和LLM生成网页，且成本低
- 提供完整评估体系，含知识留存测试
学术项目网站若能清晰呈现核心内容并支持直观导航与交互，将更有效地传播研究成果。然而，当前基于大语言模型生成、模板或直接HTML转换的方法难以产出布局合理、具备交互性的网站，且缺乏全面的评估体系。本文提出Paper2Web，一个基准数据集与多维评估框架，包含规则化指标（如连通性、完整性）以及人工验证的LLM评分（涵盖交互性、美观度与信息量），还有衡量论文级知识保留的PaperQuiz。我们进一步提出PWAgent，一种可自主运行的管道系统，将科学论文转化为富含多媒体的互动式学术主页。该代理通过MCP工具迭代优化内容与版式，增强重点突出、视觉平衡与呈现质量。实验表明，PWAgent在多项指标上显著优于端到端基线方法（如模板网页及arXiv/alphaXiv版本），且保持低成本，达到学术网页生成的帕累托最优。
原文摘要 · Abstract (English)
Academic project websites can more effectively disseminate research when they clearly present core content and enable intuitive navigation and interaction. However, current approaches such as direct Large Language Model (LLM) generation, templates, or direct HTML conversion struggle to produce layout-aware, interactive sites, and a comprehensive evaluation suite for this task has been lacking. In this paper, we introduce Paper2Web, a benchmark dataset and multi-dimensional evaluation framework for assessing academic webpage generation. It incorporates rule-based metrics like Connectivity, Completeness and human-verified LLM-as-a-Judge (covering interactivity, aesthetics, and informativeness), and PaperQuiz, which measures paper-level knowledge retention. We further present PWAgent, an autonomous pipeline that converts scientific papers into interactive and multimedia-rich academic homepages. The agent iteratively refines both content and layout through MCP tools that enhance emphasis, balance, and presentation quality. Our experiments show that PWAgent consistently outperforms end-to-end baselines like template-based webpages and arXiv/alphaXiv versions by a large margin while maintaining low cost, achieving the Pareto-front in academic webpage generation.
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。