Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration

2026-03-02

AI Summary

This work addresses the high barrier to creating interactive educational documents and the limited controllability and verifiability of outputs generated by existing large language model (LLM) agents. To overcome these challenges, the authors propose ViviDoc, a novel system that employs a multi-agent collaboration framework—comprising a planner, executor, and evaluator—and introduces DocSpec, an intermediate representation that decouples interactive logic into four orthogonal components: state, rendering, transitions, and constraints. This design enables users to inspect and refine content before code generation, enhancing both transparency and user control. Experimental results demonstrate that ViviDoc substantially outperforms conventional approaches, achieving significant improvements in output quality, controllability, and the overall editing experience.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Multiagent Planning
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

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/.

Problem

• interactive documents
• human-agent collaboration
• educational content generation
• controllable output
• visualization authoring

Innovation

• human-agent collaboration
• interactive document generation
• multi-agent pipeline
• Document Specification (DocSpec)
• controllable LLM output