# Collaborative Document Editing with Multiple Users and AI Agents

arXiv: https://arxiv.org/abs/2509.11826 · HTML: https://mlsanity.com/paper/2509.11826/

## 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 (most cited first, 30 of 32)

- [CoAuthor: Designing a Human-AI Collaborative Writing Dataset for Exploring Language Model Capabilities](https://mlsanity.com/paper/2201.06796/) (2022)
- [The Metacognitive Demands and Opportunities of Generative AI](https://mlsanity.com/paper/2312.10893/) (2023)
- [Sparks: Inspiration for Science Writing using Language Models](https://mlsanity.com/paper/2110.07640/) (2021)
- [A Design Space for Intelligent and Interactive Writing Assistants](https://mlsanity.com/paper/2403.14117/) (2024)
- [Evaluating Large Language Models on Controlled Generation Tasks](https://mlsanity.com/paper/2310.14542/) (2023)
- [Help me write a poem: Instruction Tuning as a Vehicle for Collaborative Poetry Writing](https://mlsanity.com/paper/2210.13669/) (2022)
- [The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writers](https://mlsanity.com/paper/2101.09157/) (2021)
- [How to Prompt? Opportunities and Challenges of Zero- and Few-Shot Learning for Human-AI Interaction in Creative Applications of Generative Models](https://mlsanity.com/paper/2209.01390/) (2022)
- [AI-Augmented Brainwriting: Investigating the use of LLMs in group ideation](https://mlsanity.com/paper/2402.14978/) (2024)
- [Is Stack Overflow Obsolete? An Empirical Study of the Characteristics of ChatGPT Answers to Stack Overflow Questions](https://mlsanity.com/paper/2308.02312/) (2023)
- [DynaVis: Dynamically Synthesized UI Widgets for Visualization Editing](https://mlsanity.com/paper/2401.10880/) (2024)
- [Choice Over Control: How Users Write with Large Language Models using Diegetic and Non-Diegetic Prompting](https://mlsanity.com/paper/2303.03199/) (2023)
- [Writer-Defined AI Personas for On-Demand Feedback Generation](https://mlsanity.com/paper/2309.10433/) (2023)
- [DirectGPT: A Direct Manipulation Interface to Interact with Large Language Models](https://mlsanity.com/paper/2310.03691/) (2023)
- [CollabStory: Multi-LLM Collaborative Story Generation and Authorship Analysis](https://mlsanity.com/paper/2406.12665/) (2024)
- [From Text to Self: Users' Perceptions of Potential of AI on Interpersonal Communication and Self](https://mlsanity.com/paper/2310.03976/) (2023)
- ["It Felt Like Having a Second Mind": Investigating Human-AI Co-creativity in Prewriting with Large Language Models](https://mlsanity.com/paper/2307.10811/) (2023)
- [ABScribe: Rapid Exploration & Organization of Multiple Writing Variations in Human-AI Co-Writing Tasks using Large Language Models](https://mlsanity.com/paper/2310.00117/) (2023)
- ["It was 80% me, 20% AI": Seeking Authenticity in Co-Writing with Large Language Models](https://mlsanity.com/paper/2411.13032/) (2024)
- [Co-Writing with AI, on Human Terms: Aligning Research with User Demands Across the Writing Process](https://mlsanity.com/paper/2504.12488/) (2025)
- [Collage is the New Writing: Exploring the Fragmentation of Text and User Interfaces in AI Tools](https://mlsanity.com/paper/2405.17217/) (2024)
- [Heteroglossia: In-Situ Story Ideation with the Crowd](https://mlsanity.com/paper/2001.04519/) (2020)
- [Summaries, Highlights, and Action items: Design, implementation and evaluation of an LLM-powered meeting recap system](https://mlsanity.com/paper/2307.15793/) (2023)
- [Script&Shift: A Layered Interface Paradigm for Integrating Content Development and Rhetorical Strategy with LLM Writing Assistants](https://mlsanity.com/paper/2502.10638/) (2025)
- [Canvil: Designerly Adaptation for LLM-Powered User Experiences](https://mlsanity.com/paper/2401.09051/) (2024)
- [MAP: Multi-user Personalization with Collaborative LLM-powered Agents](https://mlsanity.com/paper/2503.12757/) (2025)
- [ChatCollab: Exploring Collaboration Between Humans and AI Agents in Software Teams](https://mlsanity.com/paper/2412.01992/) (2024)
- [Inspo: Writing with Crowds Alongside AI](https://mlsanity.com/paper/2311.16521/) (2023)
- [One Agent Too Many: User Perspectives on Approaches to Multi-agent Conversational AI](https://mlsanity.com/paper/2401.07123/) (2024)
- [AI-Powered Reminders for Collaborative Tasks: Experiences and Futures](https://mlsanity.com/paper/2403.01365/) (2024)

## Built on by (most cited first, 5 of 5)

- ["When to Hand Off, When to Work Together": Understanding Concurrent Human-Agent Interaction in Shared Co-Creative Workspaces](https://mlsanity.com/paper/2603.02050/) (2026)
- [Designing Proactive Thought Partners for Writing](https://mlsanity.com/paper/2609.01588/) (2026)
- [Co-Writing with AI: An Empirical Study of Diverse Academic Writing Workflows](https://mlsanity.com/paper/2604.25389/) (2026)
- [DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents](https://mlsanity.com/paper/2609.29309/) (2026)
- [Ream: Unfolding Mutual Awareness in Human-Agent Workspaces](https://mlsanity.com/paper/2610.09497/) (2026)

## 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.