Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration

Yinghao Tang, Yupeng Xie, Yingchaojie Feng, Tingfeng Lan, Wei Chen

TL;DR

Expert evaluation and a user study show that ViviDoc substantially outperforms naive agentic generation and provides an intuitive editing experience.

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/.

Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration

TL;DR

Expert evaluation and a user study show that ViviDoc substantially outperforms naive agentic generation and provides an intuitive editing experience.

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/.
Paper Structure (22 sections, 5 figures, 1 table)

This paper contains 22 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Interactive Document
  4. LLM Agents for Content Creation
  5. System Overview
  6. Pipeline
  7. Planner.
  8. Executor.
  9. Evaluator.
  10. Human Review.
  11. Document Specification
  12. Structure
  13. Interaction Specification: SRTC
  14. Example.
  15. Experiments
  16. ...and 7 more sections

Figures (5)

  • Figure 1: Three approaches to creating interactive documents: manual authoring, fully automatic generation, and human-agent collaboration through DocSpec.
  • Figure 2: The ViviDoc pipeline. The Planner generates a Document Specification (DocSpec) from a topic. The user can review and edit the DocSpec before the Executor generates the final document. The Evaluator checks the output and provides feedback.
  • Figure 3: The ViviDoc user interface. Users follow a Topic $\rightarrow$ Spec $\rightarrow$ Doc workflow to generate interactive educational documents.
  • Figure 4: Expert blind evaluation scores for ViviDoc and Naive Agent across three dimensions.
  • Figure 5: Participant ratings of ViviDoc on five usability dimensions. Values show mean and standard deviation.