Metraipolis › archive › dc_7474c136e2ff

Coati: Host-Grounded Execution for Installable Mobile GUI Agents — arXiv:2611.02644

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.02644
License (as archived): CC0-1.0
Archived: 2026-11-03T10:59:25.028Z
SHA-256 of the archived text: fbf0705d0b9b78b88155587fac441335c8fd132fca7ebf397c32a9e49de0354e
Stable URL of this page: https://metraipolis.com/documento/dc_7474c136e2ff

How to cite

Coati: Host-Grounded Execution for Installable Mobile GUI Agents — arXiv:2611.02644 — arXiv (en), https://arxiv.org/abs/2611.02644 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7474c136e2ff (Metraipolis archive dc_7474c136e2ff, sha256 fbf0705d0b9b78b88155587fac441335c8fd132fca7ebf397c32a9e49de0354e)

BibTeX

@misc{dc7474c136e2ff,
  title = {Coati: Host-Grounded Execution for Installable Mobile GUI Agents — arXiv:2611.02644},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02644},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7474c136e2ff; sha256 fbf0705d0b9b78b88155587fac441335c8fd132fca7ebf397c32a9e49de0354e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02644. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Mobile GUI agents can carry out tasks across apps, yet most run on a separate computer that drives a phone over the Android Debug Bridge (ADB), out of reach of ordinary users and of the apps through which most people reach Web services. We present Coati, a source-available agent that users install as an Android app. Its runtime on the phone, the host, records what a model alone cannot see: the effect of each action at its target, result screens across apps, and the progress of repeated steps. VerifyLoop checks action outcomes and completion claims against host evidence and reports a completion it cannot audit as unverified. AppMemory builds per-app procedural memory from observations that the interface supports and reuses it on later visits. A routed fast executor lets a lightweight selection model take simple, confident steps and lets the host repeat loops of simple steps that the large model plans once. On all 116 AndroidWorld tasks, with Gemini 3.8 Flash as every agent's backbone, Coati succeeds on 86.5% of the tasks over three trials, ahead of the strongest open-source agent Artemis (77.6% with the same accessibility-only access, 76.5% even when allowed ADB) and far ahead of FinalRun and Midscene (about 59%), and VerifyLoop cuts false completion claims by about a third at comparable success. In everyday use, the fast executor cuts the median time of phone tasks by 39% at comparable success and runs three of four loop tasks 2.8-5.4x faster with 6-9x fewer model tokens, while AppMemory shortens a repeated deep route in an unfamiliar app from 18.5 steps to 6-7. On an Android 16 phone, routed execution completes all 27 benchmark runs with 76% fewer Reasoning calls on the critical path. Host evidence, not model self-assessment, makes an installable agent reliable and fast.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.02644 — 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 2026-11-03T10:59:22.296Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).