Human-Agent Collaborative Paper-to-Page Crafting for Under $0.1
Qianli Ma, Siyu Wang, Yilin Chen, Yinhao Tang, Yixiang Yang, Chang Guo, Bingjie Gao, Zhening Xing, Yanan Sun, Zhipeng Zhang
2025-10-24
Summary
This paper introduces AutoPage, a system designed to automatically create project webpages from research papers, making it easier for scientists to share their work.
What's the problem?
Researchers spend a lot of time and effort manually building webpages to explain their complex research papers to a wider audience. Existing tools can automate things like creating slideshows, but they struggle with the interactive and dynamic nature of a good webpage. It's a repetitive task that takes away from actual research.
What's the solution?
The researchers tackled this by creating AutoPage, which works like a team of AI 'agents'. It breaks down webpage creation into steps: first planning the overall story, then generating text and images, and finally building an interactive webpage. Importantly, 'Checker' agents verify everything against the original paper to prevent the AI from making things up, and researchers can review and approve steps to ensure accuracy. They also created a new standard test, called PageBench, to measure how well these kinds of systems perform.
Why it matters?
This work is important because it significantly reduces the burden on researchers to communicate their findings. By automating webpage creation, AutoPage allows scientists to focus on the research itself, potentially speeding up scientific progress and making research more accessible to everyone. It also establishes a new area of research focused on automated webpage generation from scientific papers.
Abstract
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}$.