EngageCue: Enabling Balanced Engagement in Face-to-Face Group Collaboration via AI Cues Through Smart Glasses

Abstract

In face-to-face group collaboration, uneven engagement often undermines efficiency and interaction quality. Although AI and wearable devices are increasingly applied to support collaboration, existing approaches largely remain confined to online or screen-based environments, leaving multimodal and dynamic regulation in real interactions underexplored. To address this gap, we conducted a formative study and distilled three design goals that informed EngageCue—a smart glasses–based AI system that combines multimodal behavior sensing, engagement-state assessment, and LLM-based cue formulation to provide real-time cues, forming a “sensing–analysis–feedback–interaction” loop. A user study with 36 participants in 12 groups showed that the system significantly improved the balance of speaking engagement, but its effects on overall engagement were modest, and cue effectiveness depended on timing and tone. These findings highlight the potential of smart glasses–mediated AI to support behavioral participation regulation, especially speaking balance regulation, in face-to-face collaboration and inform wearable AI for group support.