@inproceedings{tang-etal-2026-demonstrating,
title = "Demonstrating {V}ivi{D}oc: Generating Interactive Documents through Human-Agent Collaboration",
author = "Tang, Yinghao and
Xie, Yupeng and
Feng, Yingchaojie and
Lan, Tingfeng and
Chen, Wei",
editor = "Durrett, Greg and
Jian, Ping",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 3: System Demonstrations)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-demo.79/",
pages = "804--811",
ISBN = "979-8-89176-392-0",
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. We collect a dataset of 101 real-world interactive documents across 11 domains and conduct a user study showing that ViviDoc produces documents comparable in quality to human-authored ones. Our demo is available at \url{https://vividoc.vercel.app/} and a video demonstration at \url{https://www.youtube.com/watch?v=rJrnPJLyHUI}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2026-demonstrating">
<titleInfo>
<title>Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yinghao</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yupeng</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingchaojie</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tingfeng</namePart>
<namePart type="family">Lan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Durrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ping</namePart>
<namePart type="family">Jian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-392-0</identifier>
</relatedItem>
<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. We collect a dataset of 101 real-world interactive documents across 11 domains and conduct a user study showing that ViviDoc produces documents comparable in quality to human-authored ones. Our demo is available at https://vividoc.vercel.app/ and a video demonstration at https://www.youtube.com/watch?v=rJrnPJLyHUI.</abstract>
<identifier type="citekey">tang-etal-2026-demonstrating</identifier>
<location>
<url>https://aclanthology.org/2026.acl-demo.79/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>804</start>
<end>811</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration
%A Tang, Yinghao
%A Xie, Yupeng
%A Feng, Yingchaojie
%A Lan, Tingfeng
%A Chen, Wei
%Y Durrett, Greg
%Y Jian, Ping
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-392-0
%F tang-etal-2026-demonstrating
%X 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. We collect a dataset of 101 real-world interactive documents across 11 domains and conduct a user study showing that ViviDoc produces documents comparable in quality to human-authored ones. Our demo is available at https://vividoc.vercel.app/ and a video demonstration at https://www.youtube.com/watch?v=rJrnPJLyHUI.
%U https://aclanthology.org/2026.acl-demo.79/
%P 804-811
Markdown (Informal)
[Demonstrating ViviDoc: Generating Interactive Documents through Human-Agent Collaboration](https://aclanthology.org/2026.acl-demo.79/) (Tang et al., ACL 2026)
ACL