Paper2Web：让您的论文焕发生机！

Paper2Web: Let's Make Your Paper Alive!

October 17, 2025

作者: Yuhang Chen, Tianpeng Lv, Siyi Zhang, Yixiang Yin, Yao Wan, Philip S. Yu, Dongping Chen

cs.AI

摘要

学术项目网站若能清晰呈现核心内容并实现直观的导航与互动，将更有效地传播研究成果。然而，现有方法如直接使用大型语言模型（LLM）生成、模板化或直接HTML转换，均难以制作出布局合理、交互性强的网站，且针对此任务的全面评估体系尚属空白。本文提出了Paper2Web，一个用于评估学术网页生成的基准数据集与多维度评价框架。该框架融合了基于规则的指标（如连通性、完整性）、经人工验证的LLM-as-a-Judge（涵盖交互性、美观度与信息量），以及衡量论文层面知识保留的PaperQuiz。此外，我们介绍了PWAgent，一个将科学论文转化为互动性强、多媒体丰富的学术主页的自动化流程。该代理通过MCP工具迭代优化内容与布局，提升重点突出、平衡感及展示质量。实验表明，PWAgent在保持低成本的同时，大幅超越基于模板的网页及arXiv/alphaXiv版本等端到端基线方法，实现了学术网页生成的帕累托前沿。

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.