arXiv Open Access 2026

Intelligent support for Human Oversight: Integrating Reinforcement Learning with Gaze Simulation to Personalize Highlighting

Thorsten Klößner João Belo Zekun Wu Jörg Hoffmann Anna Maria Feit

Lihat Sumber

Abstrak

Interfaces for human oversight must effectively support users' situation awareness under time-critical conditions. We explore reinforcement learning (RL)-based UI adaptation to personalize alerting strategies that balance the benefits of highlighting critical events against the cognitive costs of interruptions. To enable learning without real-world deployment, we integrate models of users' gaze behavior to simulate attentional dynamics during monitoring. Using a delivery-drone oversight scenario, we present initial results suggesting that RL-based highlighting can outperform static, rule-based approaches and discuss challenges of intelligent oversight support.

Topik & Kata Kunci

cs.HC cs.AI

Penulis (5)

Thorsten Klößner

João Belo

Zekun Wu

Jörg Hoffmann

Anna Maria Feit

Format Sitasi

APA MLA BibTeX

Klößner, T., Belo, J., Wu, Z., Hoffmann, J., Feit, A.M. (2026). Intelligent support for Human Oversight: Integrating Reinforcement Learning with Gaze Simulation to Personalize Highlighting. https://arxiv.org/abs/2602.08403

Akses Cepat

Lihat di Sumber

Informasi Jurnal

Tahun Terbit: 2026
Bahasa: en
Sumber Database: arXiv
Akses: Open Access ✓