Understanding Human-Multi-Agent Team Formation for Creative Work

TL;DR

This study explores how humans form and manage multi-agent teams for creative tasks, revealing that users prefer direct orchestration over autonomous operation, with implications for designing effective human-AI collaboration tools.

Contribution

Introduces CrafTeam, a novel tool for forming and managing human-multi-agent teams, and provides insights into user preferences and strategies for effective team orchestration in creative workflows.

Findings

Participants prefer direct orchestration over autonomous team operation.

Humans tend to directly control AI agents in creative collaboration.

Design considerations are discussed for effective HMAT formation.

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.