Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration

TL;DR

ViviDoc is a collaborative system that uses multi-agent planning and a human-readable specification to generate and refine interactive educational documents from a single topic, improving control and usability.

Contribution

It introduces a multi-agent pipeline and the Document Specification (DocSpec) for better control and review in generating interactive documents with LLMs.

Findings

ViviDoc outperforms naive agentic generation in quality.

Users find ViviDoc's interface intuitive for editing.

Expert evaluation confirms improved control and output quality.

Abstract

Interactive articles help readers engage with complex ideas through exploration, yet creating them remains costly, requiring both domain expertise and web development skills. Recent LLM-based agents can automate content creation, but naively applying them yields uncontrollable and unverifiable outputs. We present ViviDoc, a human-agent collaborative system that generates interactive educational documents from a single topic input. ViviDoc introduces a multi-agent pipeline (Planner, Executor, Evaluator) and the Document Specification (DocSpec), a human-readable intermediate representation that decomposes each interactive visualization into State, Render, Transition, and Constraint components. The DocSpec enables educators to review and refine generation plans before code is produced, bridging the gap between pedagogical intent and executable output. Expert evaluation and a user study show that ViviDoc substantially outperforms naive agentic generation and provides an intuitive editing experience. Our project homepage is available at https://vividoc-homepage.vercel.app/.