Metraipolis › archive › dc_5af4fce02c09

CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications — arXiv:2608.11588

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11588
License (as archived)
CC0-1.0
Archived
2026-10-19T05:15:24.426Z
SHA-256 of the archived text
9df13560ba32b62594577506b91bd274e6ae7f289a89298e7725cd052bc98e57
Stable URL of this page
https://metraipolis.com/documento/dc_5af4fce02c09

How to cite

CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications — arXiv:2608.11588 — arXiv (en), https://arxiv.org/abs/2608.11588 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5af4fce02c09 (Metraipolis archive dc_5af4fce02c09, sha256 9df13560ba32b62594577506b91bd274e6ae7f289a89298e7725cd052bc98e57)
BibTeX
@misc{dc5af4fce02c09,
  title = {CoAdapt-GUI: Joint Workflow Context and Policy Adaptation for Unseen GUI Applications — arXiv:2608.11588},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11588},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5af4fce02c09; sha256 9df13560ba32b62594577506b91bd274e6ae7f289a89298e7725cd052bc98e57},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11588. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Mobile GUI agents remain brittle when deployed to applications absent from source training. We study novel-app generalization under a limited target interaction budget and without target demonstrations. We introduce CoAdapt-GUI, a test-time adaptation (TTA) framework that jointly adapts structured workflow context and policy from the agent's own target-app rollouts and rewards. The workflow context retains transferable procedures, failure modes, and verification rules while excluding app-bound source details. This separation allows reusable workflow knowledge to guide adaptation without transferring source-interface state. For policy adaptation, task-context-matched group-relative optimization updates a LoRA adapter on a frozen vision-language model. Across two unseen-app evaluations, CoAdapt-GUI reaches 45.0% on AndroidWorld-Generalization, compared with 37.5% for the reported Policy-Only TTA baseline, and raises AndroidWorld Plus performance from 38.6% to 52.9%. These results show that transfer-constrained workflow context provides substantial gains and that joint policy adaptation further improves held-out performance.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.11588 — 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 2026-10-19T05:08:46.632Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).