Collaborative Document Editing with Multiple Users and AI Agents
Not on the map. Why?
Abstract (arXiv)
Current AI writing support tools are largely designed for individuals, complicating collaboration when co-writers must leave the shared workspace to use AI and then communicate and reintegrate results. We propose integrating AI agents directly into collaborative writing environments. Our prototype makes AI use visible to all users through two new shared objects: user-defined agent profiles and tasks. Agent responses appear in the familiar comment feature. In a user study (N=30), 14 teams worked on writing projects during one week. Interaction logs and interviews show that teams incorporated agents into existing norms of authorship, control, and coordination, rather than treating them as team members. Agent profiles were viewed as personal territory, while created agents and outputs became shared resources. We discuss implications for team-based AI interaction, highlighting opportunities and boundaries for treating AI as a shared resource in collaborative work.
Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 32 of its 91 references that are in the map. First posted on arXiv 15 Sep 2025.
Builds on
32 of 91 references.
References · 32
- 2022CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilitiescited by 249
- 2023The Metacognitive Demands and Opportunities of Generative AIcited by 87
- 2021Sparks: Inspiration for Science Writing using Language Modelscited by 80
- 2024A Design Space for Intelligent and Interactive Writing Assistantscited by 76
- 2023Evaluating Large Language Models on Controlled Generation Taskscited by 73
- 2022Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writingcited by 71
- 2021The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writerscited by 61
- 2022How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Modelscited by 44
- 2024AI-Augmented Brainwriting: Investigating the use of LLMs in group ideationcited by 44
- 2023Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questionscited by 42
- 2024DynaVis: Dynamically Synthesized UI Widgets for Visualization Editingcited by 37
- 2023Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Promptingcited by 36
20 more
- 2023Writer-Defined AI Personas for On-Demand Feedback Generationcited by 36
- 2023DirectGPT: A Direct Manipulation Interface to Interact with Large Language Modelscited by 32
- 2024CollabStory: Multi-LLM Collaborative Story Generation and Authorship Analysiscited by 26
- 2023From Text to Self: Users' Perceptions of Potential of AI on Interpersonal Communication and Selfcited by 18
- 2023"It Felt Like Having a Second Mind": Investigating Human-AI Co-creativity in Prewriting with Large Language Modelscited by 17
- 2023ABScribe: Rapid Exploration & Organization of Multiple Writing Variations in Human-AI Co-Writing Tasks using Large Language Modelscited by 17
- 2024"It was 80% me, 20% AI": Seeking Authenticity in Co-Writing with Large Language Modelscited by 14
- 2025Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Processcited by 14
- 2024Collage is the New Writing: Exploring the Fragmentation of Text and User Interfaces in AI Toolscited by 13
- 2020Heteroglossia: In-Situ Story Ideation with the Crowdcited by 12
- 2023Summaries, Highlights, and Action items: Design, implementation and evaluation of an LLM-powered meeting recap systemcited by 12
- 2025Script&Shift: A Layered Interface Paradigm for Integrating Content Development and Rhetorical Strategy with LLM Writing Assistantscited by 12
- 2024Canvil: Designerly Adaptation for LLM-Powered User Experiencescited by 9
- 2025MAP: Multi-user Personalization with Collaborative LLM-powered Agentscited by 7
- 2024ChatCollab: Exploring Collaboration Between Humans and AI Agents in Software Teamscited by 6
- 2023Inspo: Writing with Crowds Alongside AIcited by 5
- 2024One Agent Too Many: User Perspectives on Approaches to Multi-agent Conversational AIcited by 4
- 2024AI-Powered Reminders for Collaborative Tasks: Experiences and Futurescited by 2
- 2025StudyAlign: A Software System for Conducting Web-Based User Studies with Functional Interactive Prototypescited by 2
- 2025Comparing Native and Non-native English Speakers' Behaviors in Collaborative Writing through Visual Analyticscited by 1
Built on by
Citing papers per year: 2026: 5.
5 papers.
- 2026"When to Hand Off, When to Work Together": Understanding Concurrent Human-Agent Interaction in Shared Co-Creative Workspacescited by 1
- 2026Designing Proactive Thought Partners for Writingcited by 1
- 2026Co-Writing with AI: An Empirical Study of Diverse Academic Writing Workflowscited by 0
- 2026DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documentscited by 0
- 2026Ream: Unfolding Mutual Awareness in Human-Agent Workspacescited by 0
- 2026Ream: Unfolding Mutual Awareness in Human-Agent Workspaces7 Oct 2026
- 2026DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents24 Sep 2026
- 2026Designing Proactive Thought Partners for Writing1 Sep 2026
- 2026Co-Writing with AI: An Empirical Study of Diverse Academic Writing Workflows28 Apr 2026
- 2026"When to Hand Off, When to Work Together": Understanding Concurrent Human-Agent Interaction in Shared Co-Creative Workspaces2 Mar 2026