Gaze-Informed Proactive AI Assistance for Children’s Picture Exploration

Zekun Wu, Man Su, Huiyong Li, Tomohiro Nagashima, Anna Maria Feit — submitted 1 Jul 2026

Zekun Wu, Man Su, Huiyong Li, Tomohiro Nagashima, Anna Maria Feit — submitted 1 Jul 2026

Ollie, a gaze-informed AI assistant for children's picture exploration, uses eye-tracking to trigger LLM narrative descriptions; within-subject experiment shows gaze-informed assistance keeps children's attention longer and guides exploration effectively.

Key Contributions

Connections to AI in Education

This paper contributes to the growing body of research on AI applications in educational settings, specifically in the domains of AI Education, Intelligent Tutoring, and Equity. The findings have implications for how educators design learning experiences that leverage AI while maintaining appropriate pedagogical oversight.

Connected Concepts

AI Education

Intelligent Tutoring

Equity

Connected Articles

Elevate GenAI Virtual Tutors — ELEVATE: Designing Human-Centered GenAI Virtual Tutors for Scalable and Inclusive Education

Child Safety GenAI — Child Safety in Generative AI: An Expert-Guided and Incident-Grounded Evaluation Framework

Tactile Statistical Graphs Accessibility — Touching and Feeling the Data: A Reusable Software Pipeline for Tactile Statistical Graphs in Accessible Education

Dura LLM Cs2 — Demystify, Use, Reflect, Assess (DURA): An Experience Report on LLM Integration in CS2

AI LMS Middle School Longitudinal — AI-Integrated Learning Management System for Middle School: A Longitudinal Study of Learning Outcomes

Mixed Reality Engineering Learning — Visualizing Engineering Fundamentals: Design of Mixed Reality and Physical Toolkits for Effective Learning

Citation

Zekun Wu, Man Su, Huiyong Li, Tomohiro Nagashima, Anna Maria Feit (2026). Gaze-Informed Proactive AI Assistance for Children’s Picture Exploration. arXiv:2607.00445. submitted 1 Jul 2026