Understanding Human-Multi-Agent Team Formation for Creative Work

2026-01-20

AI Summary

This study addresses the unpredictability and coordination challenges inherent in multi-agent interactions during complex creative tasks by proposing a human-led framework for Multi-Agent Creative Teams (HMATs). Through the development of CrafTeam—a technical probe enabling users to collaboratively ideate with generative AI agents across a three-phase cycle of team formation, co-ideation, and reflection—an empirical study with twelve design professionals reveals a strong user preference for actively orchestrating agent collaboration rather than relying on fully autonomous teams. Based on these findings, the research articulates key design principles that empower humans to effectively lead HMATs. This work contributes both theoretical insights and practical guidance for the design of multi-agent systems in creative collaboration contexts.

Technology Category

• Multiagent Systems: Teamwork
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation

Abstract

Team-based collaboration is a cornerstone of modern creative work. Recent advances in generative AI open possibilities for humans to collaborate with multiple AI agents in distinct roles to address complex creative workflows. Yet, how to form Human-Multi-Agent Teams (HMATs) is underexplored, especially given that inter-agent interactions increase complexity and the risk of unexpected behaviors. In this exploratory study, we aim to understand how to form HMATs for creative work using CrafTeam, a technology probe that allows users to form and collaborate with their teams. We conducted a study with 12 design practitioners, in which participants iterated through a three-step cycle: forming HMATs, ideating with their teams, and reflecting on their teams'ideation. Our findings reveal that while participants initially attempted autonomous team operations, they ultimately adopted team formations in which they directly orchestrated agents. We discuss design considerations for HMAT formation that humans can effectively orchestrate multiple agents.

Problem

• Human-Multi-Agent Teams
• team formation
• creative work
• multi-agent collaboration
• generative AI

Innovation

• Human-Multi-Agent Teams
• Generative AI
• Team Formation
• Creative Collaboration
• Technology Probe