Augmenting Teamwork through AI Agents as Spatial Collaborators

TL;DR

This paper addresses enabling AI agents to function as spatial collaborators in AR to support human-AI teamwork, moving beyond one-to-one assistance to team-level facilitation. It proposes dynamically generating collaboration resources such as virtual blackboards, shared mental maps, and memory recall of spatial configurations to support coordination and decision-making. Through a review of AI agents in immersive environments, it identifies limitations in team-level understanding and proxemics, and argues for context-driven interventions tailored to multi-user AR settings. The authors outline a future work program and a workshop plan to explore design questions about AR agent embodiment, spatial factors, and intervention timing, aiming to advance collaborative intelligence in mixed-reality environments.

Abstract

As Augmented Reality (AR) and Artificial Intelligence (AI) continue to converge, new opportunities emerge for AI agents to actively support human collaboration in immersive environments. While prior research has primarily focused on dyadic human-AI interactions, less attention has been given to Human-AI Teams (HATs) in AR, where AI acts as an adaptive teammate rather than a static tool. This position paper takes the perspective of team dynamics and work organization to propose that AI agents in AR should not only interact with individuals but also recognize and respond to team-level needs in real time. We argue that spatially aware AI agents should dynamically generate the resources necessary for effective collaboration, such as virtual blackboards for brainstorming, mental map models for shared understanding, and memory recall of spatial configurations to enhance knowledge retention and task coordination. This approach moves beyond predefined AI assistance toward context-driven AI interventions that optimize team performance and decision-making.