Metraipolis › archive › dc_4430f00cee53
Same Tasks, Different Apps: Why Mobile GUI Agents Fail to Generalize? — arXiv:2609.34139
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34139
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:57:26.958Z
- SHA-256 of the archived text
4594d8799402791744ab2100de33a269ca33a6e15fe57d32186882b68ec77d5c- Stable URL of this page
https://metraipolis.com/documento/dc_4430f00cee53
How to cite
Same Tasks, Different Apps: Why Mobile GUI Agents Fail to Generalize? — arXiv:2609.34139 — arXiv (en), https://arxiv.org/abs/2609.34139 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4430f00cee53 (Metraipolis archive dc_4430f00cee53, sha256 4594d8799402791744ab2100de33a269ca33a6e15fe57d32186882b68ec77d5c)
BibTeX
@misc{dc4430f00cee53,
title = {Same Tasks, Different Apps: Why Mobile GUI Agents Fail to Generalize? — arXiv:2609.34139},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34139},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4430f00cee53; sha256 4594d8799402791744ab2100de33a269ca33a6e15fe57d32186882b68ec77d5c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34139. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Mobile GUI agents deployed in real settings must work across different applications that support the same functionality. Most existing benchmarks test each task in only one app, so a high score can mean the agent understands the task, or only that it knows that particular app. We introduce AnyAppBench, a category-controlled live Android benchmark that evaluates cross-application generalization while keeping the user goal fixed. It spans 10 functional categories, 100 task templates, and 520 task--application pairs over 52 applications. Agents run from raw instructions and with app-independent sub-goals, and a VLM judge labels every failed run under a fixed failure taxonomy whose reliability is measured by human annotation. We find that, across 13 agents, success on the original application does not transfer reliably to new applications with the same goal. Furthermore, providing high-level sub-goal decomposition produces only small, category-dependent changes that do not close the gap, and the mix of failure types changes with the target interface. Based on those insights, we believe the AnyAppBench benchmark provides an important stepping stone toward robust real-world deployment of mobile GUI agents. Our code, data and the leaderboard can be found at the project website this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.34139 — 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 2026-10-07T20:29:01.450Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).