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

2025-10-22

AI Summary

Researchers often manually convert academic papers into interactive web pages—a time-consuming, labor-intensive process that compromises both accuracy and interactivity. This paper introduces AutoPage, the first human-in-the-loop, multi-agent framework tailored for automated scholarly paper-to-webpage generation. AutoPage employs a hierarchical verification mechanism—including a “Checker” agent ensuring source-text fidelity—narrative-driven multimodal content generation, and interactive rendering to achieve end-to-end conversion from PDF to high-quality web pages. Its novel integration of AI generation with targeted human feedback mitigates hallucination and preserves academic rigor. Evaluated on our curated benchmark PageBench, AutoPage produces visually appealing, semantically accurate web pages in ≤15 minutes at a cost of <$0.10 per instance—significantly outperforming existing approaches in quality, efficiency, and affordability.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Sustainability of Web economics
• Web Mining and Content Analysis: Large pretrained models with web data

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

Problem

• Automating dynamic webpage creation from research papers efficiently
• Addressing AI hallucination through multi-agent verification systems
• Reducing manual effort in making research accessible interactively

Innovation

• Multi-agent system automates paper-to-webpage conversion
• Checker agents verify content against source to reduce errors
• Pipeline transforms narrative to interactive pages under $0.1