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

TL;DR

Addresses the challenge of converting dense academic papers into interactive project pages. Proposes AutoPage, a multi-agent coarse-to-fine pipeline with narrative planning, multimodal content generation, and interactive rendering, guarded by dedicated checkers and optional human-in-the-loop. Introduces PageBench, the first benchmark for automated paper-to-page generation, with metrics for content fidelity, visual quality, and authorial alignment. Demonstrates AutoPage can produce high-quality pages in under $0.1 and within 15 minutes, across multiple backbones, enabling scalable and accessible scientific communication.

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 $\href{https://mqleet.github.io/AutoPage_ProjectPage/}{Webpage}$.

Figures (12)

• Figure 1: Overview of our work. (a) End-to-end LLMs directly convert papers into project pages, resulting in unreasonable layouts and lacking human feedback. (b) Our proposed AutoPage integrates human-agent collaboration into automated page generation with higher content and visual quality. The figure also illustrates the process for constructing the PageBench benchmark.
• Figure 2: Overview of AutoPage. AutoPage conducts a multi-agent pipeline for transforming papers into interactive webpages: (1) Narrative Planning and Structuring parses PDFs into Markdown and generates section-level outlines; (2) Multimodal Content Generation produces coherent text–visual sections; (3) Interactive Page Rendering matches templates, compiles full HTML pages, and performs final layout checks. Throughout all phases, AutoPage integrates verification mechanisms and optional human-in-the-loop checkpoints for reliable and flexible generation.
• Figure 3: Human preference study. The bar chart shows that AutoPage attains the highest user preference score, surpassing all baselines with more informative, coherent, and visually engaging webpages.
• Figure 4: Qualitative comparison illustrating AutoPage’s superior generation quality over baselines. The figure highlights four common scenarios where AutoPage demonstrates superior performance: (a) Formula Presentation; (b) Image Layout; (c) Table Presentation; (d) Content Planning. This qualitative comparison demonstrates AutoPage's ability not just to fill a page with content, but to thoughtfully design it.
• Figure 5: Comprehensive Evaluation of Model Performance with and without AutoPage. The radar plot shows that integrating AutoPage consistently boosts both content and visual quality, thereby demonstrating its strong advantage in generating more accurate, coherent, and visually appealing webpages.