Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration
This addresses the challenge for educators and content creators who need to produce interactive articles without extensive web development skills, though it is incremental as it builds on existing LLM-based agent methods.
The authors tackled the problem of costly creation of interactive educational documents by introducing ViviDoc, a human-agent collaborative system that generates such documents from a single topic input, showing it substantially outperforms naive agentic generation in expert evaluations and user studies.
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/.