https://arxiv.org/abs/2510.19600
🔥 Project Page: https://mqleet.github.io/AutoPage_ProjectPage (Refresh the page to see a new version each time)
🕹️ Code: https://github.com/AutoLab-SAI-SJTU/AutoPage (⭐️)
🤗 Huggingface Space: https://huggingface.co/spaces/Mqleet/AutoPage

\n","updatedAt":"2025-10-24T03:27:35.094Z","author":{"_id":"6448b2f53e7b3c11be684348","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6448b2f53e7b3c11be684348/QvlUQG3pWf8ZyEVBV6F7w.jpeg","fullname":"Qianli Ma","name":"Mqleet","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.4377704858779907},"editors":["Mqleet"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6448b2f53e7b3c11be684348/QvlUQG3pWf8ZyEVBV6F7w.jpeg"],"reactions":[],"isReport":false},"replies":[{"id":"68faedbf9c9b42f9440c9645","author":{"_id":"6448b2f53e7b3c11be684348","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6448b2f53e7b3c11be684348/QvlUQG3pWf8ZyEVBV6F7w.jpeg","fullname":"Qianli Ma","name":"Mqleet","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false},"createdAt":"2025-10-24T03:08:47.000Z","type":"comment","data":{"edited":true,"hidden":false,"latest":{"raw":"Welcome to use AutoPage in our huggingface space!","html":"

Welcome to use AutoPage in our huggingface space!

\n","updatedAt":"2025-10-24T03:09:00.380Z","author":{"_id":"6448b2f53e7b3c11be684348","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6448b2f53e7b3c11be684348/QvlUQG3pWf8ZyEVBV6F7w.jpeg","fullname":"Qianli Ma","name":"Mqleet","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false}},"numEdits":1,"identifiedLanguage":{"language":"en","probability":0.8133873343467712},"editors":["Mqleet"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6448b2f53e7b3c11be684348/QvlUQG3pWf8ZyEVBV6F7w.jpeg"],"reactions":[],"isReport":false,"parentCommentId":"68faed6dbb66bce66558baa0"}}]},{"id":"68faedb0faf468a3fbe3e6df","author":{"_id":"6448b2f53e7b3c11be684348","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6448b2f53e7b3c11be684348/QvlUQG3pWf8ZyEVBV6F7w.jpeg","fullname":"Qianli Ma","name":"Mqleet","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false},"createdAt":"2025-10-24T03:08:32.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"To address the questions \"How to create a webpage from an academic paper?\" and \"How to evaluate the project webpage?\", we propose AutoPage and PageBench. AutoPage transforms academic papers into polished, published-ready project webpages through a human-in-the-loop multi-agent pipeline, while PageBench provides automatic evaluation across content quality and visual design quality dimensions.","html":"

To address the questions \"How to create a webpage from an academic paper?\" and \"How to evaluate the project webpage?\", we propose AutoPage and PageBench. AutoPage transforms academic papers into polished, published-ready project webpages through a human-in-the-loop multi-agent pipeline, while PageBench provides automatic evaluation across content quality and visual design quality dimensions.

\n","updatedAt":"2025-10-24T03:08:32.698Z","author":{"_id":"6448b2f53e7b3c11be684348","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6448b2f53e7b3c11be684348/QvlUQG3pWf8ZyEVBV6F7w.jpeg","fullname":"Qianli Ma","name":"Mqleet","type":"user","isPro":true,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":4,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8729801177978516},"editors":["Mqleet"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/6448b2f53e7b3c11be684348/QvlUQG3pWf8ZyEVBV6F7w.jpeg"],"reactions":[],"isReport":false}},{"id":"68fc2904ab6a6c56616c89e5","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false},"createdAt":"2025-10-25T01:33:56.000Z","type":"comment","data":{"edited":false,"hidden":false,"latest":{"raw":"This is an automated message from the [Librarian Bot](https://huggingface.co/librarian-bots). I found the following papers similar to this paper. \n\nThe following papers were recommended by the Semantic Scholar API \n\n* [Paper2Web: Let's Make Your Paper Alive!](https://huggingface.co/papers/2510.15842) (2025)\n* [PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation](https://huggingface.co/papers/2508.21720) (2025)\n* [VideoAgent: Personalized Synthesis of Scientific Videos](https://huggingface.co/papers/2509.11253) (2025)\n* [Presenting a Paper is an Art: Self-Improvement Aesthetic Agents for Academic Presentations](https://huggingface.co/papers/2510.05571) (2025)\n* [IWR-Bench: Can LVLMs reconstruct interactive webpage from a user interaction video?](https://huggingface.co/papers/2509.24709) (2025)\n* [WebGen-V Bench: Structured Representation for Enhancing Visual Design in LLM-based Web Generation and Evaluation](https://huggingface.co/papers/2510.15306) (2025)\n* [Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations](https://huggingface.co/papers/2509.11062) (2025)\n\n\n Please give a thumbs up to this comment if you found it helpful!\n\n If you want recommendations for any Paper on Hugging Face checkout [this](https://huggingface.co/spaces/librarian-bots/recommend_similar_papers) Space\n\n You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: `@librarian-bot recommend`","html":"

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: \n\n@librarian-bot\n\t recommend

\n","updatedAt":"2025-10-25T01:33:56.321Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7438985705375671},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2510.19600","authors":[{"_id":"68faed18f158a71c5a2f5883","user":{"_id":"6448b2f53e7b3c11be684348","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6448b2f53e7b3c11be684348/QvlUQG3pWf8ZyEVBV6F7w.jpeg","isPro":true,"fullname":"Qianli Ma","user":"Mqleet","type":"user"},"name":"Qianli Ma","status":"claimed_verified","statusLastChangedAt":"2025-10-24T16:01:53.631Z","hidden":false},{"_id":"68faed18f158a71c5a2f5884","name":"Siyu Wang","hidden":false},{"_id":"68faed18f158a71c5a2f5885","name":"Yilin Chen","hidden":false},{"_id":"68faed18f158a71c5a2f5886","name":"Yinhao Tang","hidden":false},{"_id":"68faed18f158a71c5a2f5887","name":"Yixiang Yang","hidden":false},{"_id":"68faed18f158a71c5a2f5888","name":"Chang Guo","hidden":false},{"_id":"68faed18f158a71c5a2f5889","user":{"_id":"645e0282412d9e9cd044c764","avatarUrl":"/avatars/1eebe4e89e151611ea96c38483549bd0.svg","isPro":false,"fullname":"gao","user":"bingjie","type":"user"},"name":"Bingjie Gao","status":"claimed_verified","statusLastChangedAt":"2025-10-27T10:29:33.298Z","hidden":false},{"_id":"68faed18f158a71c5a2f588a","name":"Zhening Xing","hidden":false},{"_id":"68faed18f158a71c5a2f588b","name":"Yanan Sun","hidden":false},{"_id":"68faed18f158a71c5a2f588c","name":"Zhipeng Zhang","hidden":false}],"publishedAt":"2025-10-22T13:53:57.000Z","submittedOnDailyAt":"2025-10-24T01:37:25.642Z","title":"Human-Agent Collaborative Paper-to-Page Crafting for Under $0.1","submittedOnDailyBy":{"_id":"6448b2f53e7b3c11be684348","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6448b2f53e7b3c11be684348/QvlUQG3pWf8ZyEVBV6F7w.jpeg","isPro":true,"fullname":"Qianli Ma","user":"Mqleet","type":"user"},"summary":"In the quest for scientific progress, communicating research is as vital as\nthe discovery itself. Yet, researchers are often sidetracked by the manual,\nrepetitive chore of building project webpages to make their dense papers\naccessible. While automation has tackled static slides and posters, the\ndynamic, interactive nature of webpages has remained an unaddressed challenge.\nTo bridge this gap, we reframe the problem, arguing that the solution lies not\nin a single command, but in a collaborative, hierarchical process. We introduce\nAutoPage, a novel multi-agent system that embodies this philosophy.\nAutoPage deconstructs paper-to-page creation into a coarse-to-fine pipeline\nfrom narrative planning to multimodal content generation and interactive\nrendering. To combat AI hallucination, dedicated \"Checker\" agents verify each\nstep against the source paper, while optional human checkpoints ensure the\nfinal product aligns perfectly with the author's vision, transforming the\nsystem from a mere tool into a powerful collaborative assistant. To rigorously\nvalidate our approach, we also construct PageBench, the first\nbenchmark for this new task. Experiments show AutoPage not only generates\nhigh-quality, visually appealing pages but does so with remarkable efficiency\nin under 15 minutes for less than \\0.1. Code and dataset will be released at\nhttps://mqleet.github.io/AutoPage_ProjectPage/{Webpage}$.","upvotes":69,"discussionId":"68faed18f158a71c5a2f588d","projectPage":"https://mqleet.github.io/AutoPage_ProjectPage","githubRepo":"https://github.com/AutoLab-SAI-SJTU/AutoPage","githubRepoAddedBy":"user","ai_summary":"AutoPage, a multi-agent system, automates the creation of interactive research webpages through a hierarchical process, ensuring high-quality and efficient results.","ai_keywords":["multi-agent system","narrative planning","multimodal content generation","interactive rendering","AI hallucination","Checker agents","human checkpoints","PageBench","benchmark"],"githubStars":162,"organization":{"_id":"68ee0edd23dc954f7744ac27","name":"AutoLab-SJTU","fullname":"AutoLab"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6448b2f53e7b3c11be684348","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6448b2f53e7b3c11be684348/QvlUQG3pWf8ZyEVBV6F7w.jpeg","isPro":true,"fullname":"Qianli Ma","user":"Mqleet","type":"user"},{"_id":"6690d197954d6a467783572b","avatarUrl":"/avatars/d9df98adb2f47ca81ce18945745b971e.svg","isPro":false,"fullname":"jiaxuan chen","user":"csdahunzi","type":"user"},{"_id":"675ed921418a4b36266355ee","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/8hJeg1pkj4Ee8ZEx4rZS1.png","isPro":false,"fullname":"Haonan Zhao","user":"2zz-n","type":"user"},{"_id":"6431a7c31e22a07ceb8b7f1e","avatarUrl":"/avatars/772167de9f529a959612e1cf3b2b908c.svg","isPro":false,"fullname":"Yanan Sun","user":"nowsyn","type":"user"},{"_id":"6571e85f78f54c59a6e4d42e","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6571e85f78f54c59a6e4d42e/XASu2zNmM1iNlje2WEzj3.jpeg","isPro":false,"fullname":"Bo Yang","user":"BorisYang326","type":"user"},{"_id":"645e0282412d9e9cd044c764","avatarUrl":"/avatars/1eebe4e89e151611ea96c38483549bd0.svg","isPro":false,"fullname":"gao","user":"bingjie","type":"user"},{"_id":"6373037cd3ba6bd3f9bc32fa","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6373037cd3ba6bd3f9bc32fa/dIL4AIcL24QL_Rp4B9ewS.png","isPro":false,"fullname":"Shuai Yang","user":"ysmikey","type":"user"},{"_id":"661d21f306936ccab51d402b","avatarUrl":"/avatars/ae720e29e91ffc82b782143c48e2fc4e.svg","isPro":false,"fullname":"Shuochen Chang","user":"miraclecsc","type":"user"},{"_id":"62aba5ebab9ed4f63c36b1e2","avatarUrl":"/avatars/c1f53a6c3ca558f82d102dd8995a530f.svg","isPro":false,"fullname":"Yue","user":"Bohr","type":"user"},{"_id":"620783f24e28382272337ba4","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/620783f24e28382272337ba4/zkUveQPNiDfYjgGhuFErj.jpeg","isPro":false,"fullname":"GuoLiangTang","user":"Tommy930","type":"user"},{"_id":"65d7b983baa72790a1151923","avatarUrl":"/avatars/938531e84ca01a0c5a2a174057e3e9c5.svg","isPro":false,"fullname":"Chen Huang","user":"Albus-Chen","type":"user"},{"_id":"66000b5c41d8fee2c410222a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/66000b5c41d8fee2c410222a/9NnY1xu0J1RtkvKX8PLAd.png","isPro":false,"fullname":"Jinhui Yin","user":"huitailang1","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":1,"organization":{"_id":"68ee0edd23dc954f7744ac27","name":"AutoLab-SJTU","fullname":"AutoLab"}}">

Papers

arxiv:2510.19600

Human-Agent Collaborative Paper-to-Page Crafting for Under $0.1

Published on Oct 22, 2025

· Submitted by

Qianli Ma on Oct 24, 2025

#1 Paper of the day

· AutoLab

Upvote

Authors:

Qianli Ma ,

Bingjie Gao ,

Abstract

AutoPage, a multi-agent system, automates the creation of interactive research webpages through a hierarchical process, ensuring high-quality and efficient results.

AI-generated summary

In the quest for scientific progress, communicating research is as vital as the discovery itself. Yet, researchers are often sidetracked by the manual, repetitive chore of building project webpages to make their dense papers accessible. While automation has tackled static slides and posters, the dynamic, interactive nature of webpages has remained an unaddressed challenge. To bridge this gap, we reframe the problem, arguing that the solution lies not in a single command, but in a collaborative, hierarchical process. We introduce AutoPage, a novel multi-agent system that embodies this philosophy. AutoPage deconstructs paper-to-page creation into a coarse-to-fine pipeline from narrative planning to multimodal content generation and interactive rendering. To combat AI hallucination, dedicated "Checker" agents verify each step against the source paper, while optional human checkpoints ensure the final product aligns perfectly with the author's vision, transforming the system from a mere tool into a powerful collaborative assistant. To rigorously validate our approach, we also construct PageBench, the first benchmark for this new task. Experiments show AutoPage not only generates high-quality, visually appealing pages but does so with remarkable efficiency in under 15 minutes for less than \0.1. Code and dataset will be released at https://mqleet.github.io/AutoPage_ProjectPage/{Webpage}$.

View arXiv page View PDF Project page GitHub 162 Add to collection

Community

Mqleet

Paper author Paper submitter Oct 24, 2025

•

edited Oct 24, 2025

🌐 Paper: https://arxiv.org/abs/2510.19600
🔥 Project Page: https://mqleet.github.io/AutoPage_ProjectPage (Refresh the page to see a new version each time)
🕹️ Code: https://github.com/AutoLab-SAI-SJTU/AutoPage (⭐️)
🤗 Huggingface Space: https://huggingface.co/spaces/Mqleet/AutoPage

Mqleet

Paper author Oct 24, 2025

•

edited Oct 24, 2025

Welcome to use AutoPage in our huggingface space!

Mqleet

Paper author Paper submitter Oct 24, 2025

To address the questions "How to create a webpage from an academic paper?" and "How to evaluate the project webpage?", we propose AutoPage and PageBench. AutoPage transforms academic papers into polished, published-ready project webpages through a human-in-the-loop multi-agent pipeline, while PageBench provides automatic evaluation across content quality and visual design quality dimensions.