Metraipolis › archive › dc_6cab8db2e75a

Reuse, Rewrite, or Reject: Evidence-Constrained Trace Reuse for Repeated Mobile GUI Control — arXiv:2610.31712

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.31712
License (as archived)
CC0-1.0
Archived
2026-10-26T19:50:54.688Z
SHA-256 of the archived text
dcf4a04e7abc00495799da46b6099ce3ec2a696b21b08be0fe45e85b412aad5e
Stable URL of this page
https://metraipolis.com/documento/dc_6cab8db2e75a

How to cite

Reuse, Rewrite, or Reject: Evidence-Constrained Trace Reuse for Repeated Mobile GUI Control — arXiv:2610.31712 — arXiv (en), https://arxiv.org/abs/2610.31712 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6cab8db2e75a (Metraipolis archive dc_6cab8db2e75a, sha256 dcf4a04e7abc00495799da46b6099ce3ec2a696b21b08be0fe45e85b412aad5e)
BibTeX
@misc{dc6cab8db2e75a,
  title = {Reuse, Rewrite, or Reject: Evidence-Constrained Trace Reuse for Repeated Mobile GUI Control — arXiv:2610.31712},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31712},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6cab8db2e75a; sha256 dcf4a04e7abc00495799da46b6099ce3ec2a696b21b08be0fe45e85b412aad5e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31712. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Mobile GUI agents frequently perform repetitive tasks with similar interaction procedures. Reusing previous executions can reduce redundant LLM inference and execution overhead, but variations in user instructions and execution environments may invalidate previously successful actions. We systematically characterize these variations into six representative categories and observe that such changes do not necessarily invalidate entire procedures: individual transitions can remain reusable when validated against the current task context and interface state. Based on this insight, we propose graph-text templates for selective execution-trace reuse. The graph captures UI states and action transitions, while the text encodes task intent, procedural structure, and typed slots for variable content. A record-template-replay framework constructs templates from verified executions and leverages the current instruction and live UI state to reuse, adapt, or discard individual transitions. Given an execution trace, our framework reduces LLM inference token consumption by approximately 80% on average across five base agents on AndroidWorld, with most agents achieving at least 1.5-fold execution speedup over LLM-only execution. In real-device evaluations on Android and HarmonyOS, our framework achieves action reuse ratios of 70.7-79.8% while maintaining over 2-fold execution speedup in most evaluated configurations.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.31712 — 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 2026-10-26T19:45:33.352Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).