DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents

2026-09-24

AI Summary

This study addresses the high cognitive burden imposed on users when manually orchestrating discussions in AI-assisted collaborative writing. To mitigate this, we propose a mixed-initiative multi-agent system that transcends conventional unidirectional instruction paradigms. By dynamically monitoring document revisions, the agents can autonomously initiate and steer conversations, thereby enabling bidirectional human-AI iterative co-optimization. Experimental results demonstrate that this approach significantly enhances the novelty, relevance, and specificity of the generated content without increasing user cognitive load. These findings validate the effectiveness of the mixed-initiative mechanism for open-ended document creation.

Abstract

In open-ended problem solving, collaborators often rely on discussion to surface concerns, challenge perspectives, and refine shared work as it evolves. While AI agents are increasingly used as discussion partners, existing multi-agent systems place a heavy burden on users to initiate and carefully orchestrate the discussions. We present DocuTeam, a mixed-initiative multi-agent discussion system in which both users and agents can initiate and steer conversations. Agents monitor document changes to proactively start and redirect discussions as the work evolves, while users can flexibly shape the conversation or adopt agent ideas. In a within-subjects study (N=20), participants using DocuTeam produced outcomes rated significantly more novel, relevant, and specific than with a baseline without any increase in cognitive load. Rather than using agents for one-off idea sourcing, participants engaged in an iterative refinement loop in which document changes prompted agent reactions, which led users to revisit and further develop their work.

Problem

• multi-agent systems
• mixed-initiative
• open-ended problem solving
• collaborative discussion
• evolving documents

Innovation

• Mixed-Initiative
• Multi-Agent System
• Evolving Documents
• Iterative Refinement
• Human-AI Collaboration