Eye Gaze as a Signal for Conveying User Attention in Contextual AI Systems
This work addresses the need for reduced friction in human-AI collaboration by providing an implicit signal of user intent, though it is incremental as it builds on existing eye tracking and vision language models.
The paper tackled the problem of implicit communication in contextual AI systems by exploring wearable eye tracking to convey user attention, showing that it effectively maps gaze to objects and improves AI agent understanding.
Advanced multimodal AI agents can now collaborate with users to solve challenges in the world. Yet, these emerging contextual AI systems rely on explicit communication channels between the user and system. We hypothesize that implicit communication of the user's interests and intent would reduce friction and improve user experience when collaborating with AI agents. In this work, we explore the potential of wearable eye tracking to convey signals about user attention. We measure the eye tracking signal quality requirements to effectively map gaze traces to physical objects, then conduct experiments that provide visual scanpath history as additional context when querying vision language models. Our results show that eye tracking provides high value as a user attention signal and can convey important context about the user's current task and interests, improving understanding of contextual AI agents.