DocuTeam enables flexible AI and human conversations around changing documents
DocuTeam: Mixed-Initiative Multi-Agent Discussions around Evolving Documents
Human-Computer InteractionArtificial Intelligence
Summary
People working together to solve problems often discuss changes to shared documents to improve them. The authors created DocuTeam, a system where humans and AI agents can start and guide discussions about evolving documents, making collaboration smoother. These AI agents watch what users change in documents and suggest new ideas or directions when needed, while users can also control the conversation freely. In tests, teams using DocuTeam created more novel and useful results without feeling more mentally tired. Instead of just asking for ideas once, users and AI agents kept refining the work together over time.
What this means in practice
- •For product design teams: Coordinate evolving design documents with AI agents that proactively suggest discussion points and improvements alongside human input.
- •For marketing content creators: Enhance collaborative editing and idea generation on evolving marketing materials through automated mixed-initiative agent conversations.
Authors
Heechan Lee, Juhyeon Choi, Tae Soo Kim, Juho Kim, Joseph Seering
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.