Towards Realistic Artificial User-Guided Usability Test Executions Using GenAI

Arends, Mathis; Winkelmann, Hendrik; Griesbach, Marie; Lahme-Hütig, Norman; Grimme, Christian

Abstract

Usability testing in human–computer interaction is effective but time‑consuming. Large language models allow
for natural specifications of simulated user interactions to accelerate early‑stage evaluation. This paper introduces vizron, a system that automates qualitative usability testing on web applications through persona‑guided LLM agents acting as artificial users. Building on the Browser‑Use framework, vizron combines visual, structural, and textual inputs to simulate realistic user navigation and generate think‑aloud feedback. Initial findings reveal a tension between goal‑oriented automation and persona realism, motivating a revised architecture that separates technical execution from persona guidance. Additionally, we argue for artificial users based on dynamic mental models rather than static personas only.

Keywords

usability testing; user experience; generative artificial intelligence; large language model; simulating human users; artificial users

Cite as

Arends, M., Winkelmann, H., Griesbach, M., Lahme-Hütig, N., & Grimme, C. (2026). Towards Realistic Artificial User-Guided Usability Test Executions Using GenAI.

Details

Publication type
Research article in digital collection (conference)

Peer reviewed
Yes

Publication status
Published

Year
2026

Conference
ACM CHI Conference on Human Factors in Computing Systems

Venue
Barcelona

Book title
ACM CHI’26 Workshop on Responsible Use of AI Personas in Human-Centered Design and Research,

Editor
Kocaballi, A. Baki; Prpa, Mirjana; Salminen, Joni; Amin, Danial; Jansen, Bernard J.

Full text