Visually impaired individuals face barriers in online shopping because product details are often conveyed through images, and alternative text is frequently insufficient. The recent advent of Computer-Using Agents (CUA) based on Large Multimodal Models, which can directly manipulate graphical user interfaces, offers new opportunities for such accessibility. However, there is a lack of research that considers how voice-based systems should be designed to support visually impaired users in complex online shopping contexts. Thus, our study qualitatively explores the experiences and needs of visually impaired users as they shop online through voice interaction with a CUA We conducted a Semi-Automatic Wizard-of-Oz study with 12 visually impaired participants, in which they performed shopping tasks with a voice-based CUA system, followed by debriefing interviews. This paper proposes design implications for creating a more inclusive and disability-centered online shopping environment with voice-based CUA for visually impaired users.

This study proposes an adaptive heuristic evaluation method that tailors heuristics to evaluators and applies it to the usability evaluation of augmented reality (AR) applications to examine its effectiveness. The performance of the evaluation methods was assessed based on the usability problems discovered and their severity, and the differences were analyzed using the McNemar test. Results showed that the adaptive method considering evaluators’ heuristic satisfaction effectively identified screen design problems and problems related to the relationship between virtual objects and real-world objects in high-interaction AR interfaces. However, it was less effective in detecting problems related to virtual objects. The adaptive method based on the evaluators’ AR experience levels showed lower performance than the adaptive method considering heuristic satisfaction. This study demonstrates that the adaptive method reflecting evaluators’ heuristic satisfaction outperforms traditional method in specific aspects.