AI-Driven Usability Testing: Integrating Eye-Tracking Data and Agentic Systems for Automated UI Evaluation
Proceedings of the AAAI Symposium Series · 01.08.2025 · 6 (1) · 244-254
DOI: 10.1609/aaaiss.v6i1.36059 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Symposium Series, online erschienen am 01.08.2025. Verfasst von Mehweesh Kadegaonkar und 1 weiteren Autor:innen. Die Arbeit wurde bisher 4-mal zitiert (Crossref).
Abstract (Originalsprache)
Despite the benefits of user interface/experience (UI/UX) design, traditional usability testing remains resource-intensive and repetitive. This study proposes a novel system that integrates real-time browser-based eye-tracking with a multimodal agentic framework to automate UI evaluation. Participants interacted with task-specific interfaces while their gaze data was captured and analysed by a multi-agent system to generate structured usability reports grounded in heuristic principles. Precision metrics were used to quantify qualitative insights, enabling measurable evaluation. To enhance accessibility, a comparative analysis was conducted between proprietary and open-source Large Language Models (LLMs). Results showed that proprietary models consistently delivered accurate insights, whereas smaller local models struggled with reliability — highlighting future directions for offline deployment. The findings contribute to the advancement of AI-driven solutions in usability evaluation, showcasing how agentic systems integrated with browser-based eye-tracking tools can overcome traditional limitations.
Zitieren
APA
Kadegaonkar, M., & Karim, K. (2025). AI-Driven Usability Testing: Integrating Eye-Tracking Data and Agentic Systems for Automated UI Evaluation. Proceedings of the AAAI Symposium Series, 6(1), 244-254. https://doi.org/10.1609/aaaiss.v6i1.36059
Vancouver
Kadegaonkar M, Karim K. AI-Driven Usability Testing: Integrating Eye-Tracking Data and Agentic Systems for Automated UI Evaluation. Proceedings of the AAAI Symposium Series. 2025;6(1):244-254. doi:10.1609/aaaiss.v6i1.36059
BibTeX
@article{Kadegaonkar2025,
author = {Kadegaonkar, Mehweesh and Karim, Kayvan},
title = {AI-Driven Usability Testing: Integrating Eye-Tracking Data and Agentic Systems for Automated UI Evaluation},
journal = {Proceedings of the AAAI Symposium Series},
year = {2025},
volume = {6},
number = {1},
pages = {244--254},
doi = {10.1609/aaaiss.v6i1.36059}
}
EUVIMED