Metraipolis › archive › dc_d0f4e799d8d0

Jev-Mobile: Jev as an Executor for Mobile GUI Agents — arXiv:2609.30186

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30186
License (as archived)
CC0-1.0
Archived
2026-10-08T04:26:32.102Z
SHA-256 of the archived text
b19f6c9efd6adb332e09d33522a2f4ed8f8dc1279d1c8e573925df465582df5b
Stable URL of this page
https://metraipolis.com/documento/dc_d0f4e799d8d0

How to cite

Jev-Mobile: Jev as an Executor for Mobile GUI Agents — arXiv:2609.30186 — arXiv (en), https://arxiv.org/abs/2609.30186 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d0f4e799d8d0 (Metraipolis archive dc_d0f4e799d8d0, sha256 b19f6c9efd6adb332e09d33522a2f4ed8f8dc1279d1c8e573925df465582df5b)
BibTeX
@misc{dcd0f4e799d8d0,
  title = {Jev-Mobile: Jev as an Executor for Mobile GUI Agents — arXiv:2609.30186},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30186},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d0f4e799d8d0; sha256 b19f6c9efd6adb332e09d33522a2f4ed8f8dc1279d1c8e573925df465582df5b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30186. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models (VLMs) have become a common foundation for autonomous mobile GUI agents, but most existing systems rely on the VLM for both planning and action grounding at nearly every interaction step, leading to substantial latency and model-serving cost. We introduce Jev-Mobile, which shifts this paradigm to low-frequency VLM planning and high-frequency lightweight execution: the VLM specifies local goals, the accessibility tree defines a structured executable action space, and Jev, a fast typed decision model, repeatedly selects actions within this space. This design allows multiple GUI actions to be executed under a single VLM decision, reducing expensive VLM inference while preserving adaptive interaction. On the full AndroidWorld task suite, Jev-Mobile achieves 79% task success, compared with 78% for SeeAct-V and 84% for a Step-wise VLM baseline. Among successful trajectories, it reduces mean end-to-end execution time by 32.7% and mean model API cost by 73.4% relative to Step-wise VLM. These results show that decoupling high-level VLM reasoning from low-level action execution can substantially improve mobile GUI agent efficiency while maintaining competitive task performance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.30186 — 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 2026-10-08T03:50:57.888Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).