Metraipolis › archive › dc_8ddeae79cf22
Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces — arXiv:2610.07972
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07972
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:19:19.189Z
- SHA-256 of the archived text
b04d29aa1b3b2f176b97901be11f6bb7cc00402fbc7612ad60f3ee448b821cf9- Stable URL of this page
https://metraipolis.com/documento/dc_8ddeae79cf22
How to cite
Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces — arXiv:2610.07972 — arXiv (en), https://arxiv.org/abs/2610.07972 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8ddeae79cf22 (Metraipolis archive dc_8ddeae79cf22, sha256 b04d29aa1b3b2f176b97901be11f6bb7cc00402fbc7612ad60f3ee448b821cf9)
BibTeX
@misc{dc8ddeae79cf22,
title = {Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces — arXiv:2610.07972},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07972},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8ddeae79cf22; sha256 b04d29aa1b3b2f176b97901be11f6bb7cc00402fbc7612ad60f3ee448b821cf9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07972. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.07972 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:15:24.572Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).