Abstract
Mobile GUI agents increasingly operate on interfaces influenced by users' histories and preferences, but their reliability across different users remains underexplored. We introduce PAIR (Personalized Application-state Instantiation and Rendering), a pipeline for constructing user-conditioned application states that enables controlled evaluation of the same task across different users. We further introduce RePAIR (Reinforcement learning with Personalization-Aware Interaction Rewards), a training approach that learns from cross-user differences in subgoal outcomes to improve reliability across user-conditioned mobile environments. Across six agents, we find substantial variation in task success across users and consistently lower subgoal achievement in user-conditioned UI contexts (6.98 to 15.4 pp). This gap further increases for personal targets drawn from each user's own content (8.77 to 22.0 pp). Failures in these contexts frequently involve selecting another item instead of the intended target, particularly before target exposure. Finally, RePAIR improves user-conditioned SAR (+5.87 pp), all-success (+7.50 pp), and overall Task SR (+9.42 pp) over its supervised fine-tuning parent on unseen users, providing initial evidence that explicitly learning from cross-user variation can improve GUI-agent reliability.
Keywords
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Park, Y., Shim, J., & Gong, T. (2026). Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces. https://omanscience.com/en/articles/can-agents-work-for-everyone-cross-user-reliability-for-mobile-gui-agents-in-personalized-user-interfaces
MLA 9
Park, Yeji, et al. "Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces." https://omanscience.com/en/articles/can-agents-work-for-everyone-cross-user-reliability-for-mobile-gui-agents-in-personalized-user-interfaces.
Chicago (author–date)
Park, Yeji, Jaeyun Shim, and Taesik Gong. 2026. "Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces." https://omanscience.com/en/articles/can-agents-work-for-everyone-cross-user-reliability-for-mobile-gui-agents-in-personalized-user-interfaces.
Harvard
Park, Y., Shim, J. and Gong, T. (2026) 'Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces', Available at: https://omanscience.com/en/articles/can-agents-work-for-everyone-cross-user-reliability-for-mobile-gui-agents-in-personalized-user-interfaces.
Vancouver
Park Y, Shim J, Gong T. Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces. https://omanscience.com/en/articles/can-agents-work-for-everyone-cross-user-reliability-for-mobile-gui-agents-in-personalized-user-interfaces
IEEE
Y. Park, J. Shim, and T. Gong, "Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces," https://omanscience.com/en/articles/can-agents-work-for-everyone-cross-user-reliability-for-mobile-gui-agents-in-personalized-user-interfaces.