Paper 2510.19600
Human-Agent Collaborative Paper-to-Page Crafting
- Published
- Oct 2025
- Research lab
- Independent
- Citations
- 6
- GitHub
- 169 stars
01 In brief
Summary
AutoPage is a multi-agent system that automatically converts academic papers into interactive project webpages.
It uses a coarse-to-fine pipeline with three phases: narrative planning, multimodal content generation, and interactive page rendering.
Dedicated 'Checker' agents verify each step against the source paper to prevent hallucination, and optional human checkpoints allow authors to refine the output.
The authors also introduce PageBench, the first benchmark for this task, containing over 1,500 papers and 100 test pages, with metrics for content and visual quality.
Experiments show AutoPage improves content and visual quality over end-to-end baselines, narrows performance gaps between weaker and stronger models, and generates pages in under 15 minutes for less than $0.1.
A user study with 20 participants rated AutoPage highest (7.66/10).
Ablations confirm the importance of the planner, text generator, and verifiers.
The system is model-agnostic and works with various LLMs.
02 From the paper
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 $\textbf{AutoPage}$, 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 $\textbf{PageBench}$, 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 $\href{https://mqleet.github.io/AutoPage_ProjectPage/}{Webpage}$.