ViviDoc: Generating Interactive Documents through Human-Agent Collaboration
Yinghao Tang, Yupeng Xie, Yingchaojie Feng, Tingfeng Lan, Jiale Lao, Yue Cheng, and Wei Chen

TL;DR
ViviDoc is a novel system that systematically generates interactive documents through a multi-agent pipeline, incorporating human control and a new benchmark for evaluation.
Contribution
It introduces a controllable, multi-agent framework for interactive document creation and a comprehensive benchmark with evaluation metrics.
Findings
ViviDoc achieves high content richness and interaction quality.
The system is easy to use and provides effective control.
Automated evaluation correlates well with human ratings.
Abstract
Interactive documents help readers engage with complex ideas through dynamic visualization, interactive animations, and exploratory interfaces. However, creating such documents remains costly, as it requires both domain expertise and web development skills. Recent Large Language Model (LLM)-based agents can automate content creation, but directly applying them to interactive document generation often produces outputs that are difficult to control. To address this, we present ViviDoc, to the best of our knowledge the first work to systematically address interactive document generation. ViviDoc introduces a multi-agent pipeline (Planner, Styler, Executor, Evaluator). To make the generation process controllable, we provide three levels of human control: (1) the Document Specification (DocSpec) with SRTC Interaction Specifications (State, Render, Transition, Constraint) for structured…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
