RevTogether: Supporting Science Story Revision with Multiple AI Agents

Yu Zhang; Kexue Fu; Zhicong Lu

doi:10.1145/3706599.3719888

RevTogether: Supporting Science Story Revision with Multiple AI Agents

Yu Zhang
, Kexue Fu
, Zhicong Lu^*

^*Corresponding author for this work

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

Abstract

As a popular form of science communication, science stories attract readers because they combine engaging narratives with comprehensible scientific knowledge. However, crafting such stories requires substantial skill and effort, as writers must navigate complex scientific concepts and transform them into coherent and accessible narratives tailored to audiences with varying levels of scientific literacy. To address the challenge, we propose RevTogether, a multi-agent system (MAS) designed to support revision of science stories with human-like AI agents (using GPT-4o). RevTogether allows AI agents to simulate affects in addition to providing comments and writing suggestions, while offering varying degrees of user agency. Our preliminary user study with non-expert writers (N=3) highlighted the need for transparency in AI agents’ decision-making processes to support learning and suggested that emotional interactions could enhance human-AI collaboration in science storytelling.
© 2025 Copyright held by the owner/author(s).

Original language	English
Title of host publication	CHI EA '25
Subtitle of host publication	Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems
Editors	Naomi Yamashita, Vanessa Evers, Koji Yatani, Xianghua (Sharon) Ding
Place of Publication	New York, United States
Publisher	Association for Computing Machinery
ISBN (Print)	9798400713958
DOIs	https://doi.org/10.1145/3706599.3719888
Publication status	Published - 25 Apr 2025
Event	2025 ACM CHI Conference on Human Factors in Computing Systems (CHI 2025): IkiCHI - PACIFICO Yokohama, Yokohama, Japan Duration: 26 Apr 2025 → 1 May 2025 https://chi2025.acm.org/

Conference

Conference	2025 ACM CHI Conference on Human Factors in Computing Systems (CHI 2025)
Abbreviated title	CHI'25
Place	Japan
City	Yokohama
Period	26/04/25 → 1/05/25
Internet address	https://chi2025.acm.org/

Research Keywords

Writing Support
Human-AI Collaboration
Science Storytelling

Access Output

10.1145/3706599.3719888

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

Zhang, Yu ; Fu, Kexue ; Lu, Zhicong. / RevTogether : Supporting Science Story Revision with Multiple AI Agents. CHI EA '25: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems. editor / Naomi Yamashita ; Vanessa Evers ; Koji Yatani ; Xianghua (Sharon) Ding. New York, United States : Association for Computing Machinery, 2025.

@inproceedings{03c388a1f7144c4a98aefe25c6b645bd,

title = "RevTogether: Supporting Science Story Revision with Multiple AI Agents",

abstract = "As a popular form of science communication, science stories attract readers because they combine engaging narratives with comprehensible scientific knowledge. However, crafting such stories requires substantial skill and effort, as writers must navigate complex scientific concepts and transform them into coherent and accessible narratives tailored to audiences with varying levels of scientific literacy. To address the challenge, we propose RevTogether, a multi-agent system (MAS) designed to support revision of science stories with human-like AI agents (using GPT-4o). RevTogether allows AI agents to simulate affects in addition to providing comments and writing suggestions, while offering varying degrees of user agency. Our preliminary user study with non-expert writers (N=3) highlighted the need for transparency in AI agents{\textquoteright} decision-making processes to support learning and suggested that emotional interactions could enhance human-AI collaboration in science storytelling. {\textcopyright} 2025 Copyright held by the owner/author(s).",

keywords = "Writing Support, Human-AI Collaboration, Science Storytelling",

author = "Yu Zhang and Kexue Fu and Zhicong Lu",

year = "2025",

month = apr,

day = "25",

doi = "10.1145/3706599.3719888",

language = "English",

isbn = "9798400713958",

editor = "Naomi Yamashita and Vanessa Evers and Koji Yatani and Ding, \{Xianghua (Sharon)\}",

booktitle = "CHI EA '25",

publisher = "Association for Computing Machinery",

address = "United States",

note = "2025 ACM CHI Conference on Human Factors in Computing Systems (CHI 2025) : IkiCHI, CHI'25 ; Conference date: 26-04-2025 Through 01-05-2025",

url = "https://chi2025.acm.org/",

}

Zhang, Y , Fu, K & Lu, Z 2025, RevTogether: Supporting Science Story Revision with Multiple AI Agents. in N Yamashita, V Evers, K Yatani & X Ding (eds), CHI EA '25: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems., 462, Association for Computing Machinery, New York, United States, 2025 ACM CHI Conference on Human Factors in Computing Systems (CHI 2025), Yokohama, Japan, 26/04/25. https://doi.org/10.1145/3706599.3719888

RevTogether: Supporting Science Story Revision with Multiple AI Agents. / Zhang, Yu ; Fu, Kexue ; Lu, Zhicong.
CHI EA '25: Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems. ed. / Naomi Yamashita; Vanessa Evers; Koji Yatani; Xianghua (Sharon) Ding. New York, United States: Association for Computing Machinery, 2025. 462.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - RevTogether

T2 - 2025 ACM CHI Conference on Human Factors in Computing Systems (CHI 2025)

AU - Zhang, Yu

AU - Fu, Kexue

AU - Lu, Zhicong

PY - 2025/4/25

Y1 - 2025/4/25

N2 - As a popular form of science communication, science stories attract readers because they combine engaging narratives with comprehensible scientific knowledge. However, crafting such stories requires substantial skill and effort, as writers must navigate complex scientific concepts and transform them into coherent and accessible narratives tailored to audiences with varying levels of scientific literacy. To address the challenge, we propose RevTogether, a multi-agent system (MAS) designed to support revision of science stories with human-like AI agents (using GPT-4o). RevTogether allows AI agents to simulate affects in addition to providing comments and writing suggestions, while offering varying degrees of user agency. Our preliminary user study with non-expert writers (N=3) highlighted the need for transparency in AI agents’ decision-making processes to support learning and suggested that emotional interactions could enhance human-AI collaboration in science storytelling. © 2025 Copyright held by the owner/author(s).

AB - As a popular form of science communication, science stories attract readers because they combine engaging narratives with comprehensible scientific knowledge. However, crafting such stories requires substantial skill and effort, as writers must navigate complex scientific concepts and transform them into coherent and accessible narratives tailored to audiences with varying levels of scientific literacy. To address the challenge, we propose RevTogether, a multi-agent system (MAS) designed to support revision of science stories with human-like AI agents (using GPT-4o). RevTogether allows AI agents to simulate affects in addition to providing comments and writing suggestions, while offering varying degrees of user agency. Our preliminary user study with non-expert writers (N=3) highlighted the need for transparency in AI agents’ decision-making processes to support learning and suggested that emotional interactions could enhance human-AI collaboration in science storytelling. © 2025 Copyright held by the owner/author(s).

KW - Writing Support

KW - Human-AI Collaboration

KW - Science Storytelling

UR - https://www.scopus.com/pages/publications/105005746407

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-105005746407&origin=recordpage

U2 - 10.1145/3706599.3719888

DO - 10.1145/3706599.3719888

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9798400713958

BT - CHI EA '25

A2 - Yamashita, Naomi

A2 - Evers, Vanessa

A2 - Yatani, Koji

A2 - Ding, Xianghua (Sharon)

PB - Association for Computing Machinery

CY - New York, United States

Y2 - 26 April 2025 through 1 May 2025

ER -

RevTogether: Supporting Science Story Revision with Multiple AI Agents

Abstract

Conference

Research Keywords

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this