Metraipolis › archive › dc_e976da159ad3
DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents — arXiv:2610.11707
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11707
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T05:48:17.669Z
- SHA-256 of the archived text
ab6f5652b2fe151f10ac6b771b983e73873c4e1433ce3ab70f6eb4d362982b5a- Stable URL of this page
https://metraipolis.com/documento/dc_e976da159ad3
How to cite
DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents — arXiv:2610.11707 — arXiv (en), https://arxiv.org/abs/2610.11707 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e976da159ad3 (Metraipolis archive dc_e976da159ad3, sha256 ab6f5652b2fe151f10ac6b771b983e73873c4e1433ce3ab70f6eb4d362982b5a)
BibTeX
@misc{dce976da159ad3,
title = {DeltaReplay: Task-Relative Memory Reuse for Mobile GUI Agents — arXiv:2610.11707},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11707},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e976da159ad3; sha256 ab6f5652b2fe151f10ac6b771b983e73873c4e1433ce3ab70f6eb4d362982b5a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11707. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Memory-augmented mobile GUI agents store successful execution trajectories and reuse them in later tasks, but a stored trajectory rarely matches a new task exactly. The new task may use different parameters, share only some of its steps with a stored trajectory, or have no relevant record in memory. Forcing the agent to use irrelevant memory can mislead it, whereas discarding memory that may still be useful deprives it of guidance from past experience. To address this dilemma, we propose DeltaReplay, a step-level memory reuse framework that decides how to use existing memory without modifying it. We observe that the reusable part of a stored record is determined not by the record itself but by its relation to the new task, mainly through two factors: page-level consistency and action-level generality. We therefore store execution trajectories as paths in a transition graph, whose nodes (pages) and edges (actions between pages) capture these two factors. At reuse time, the action on each edge is split into a task-independent operation and task-specific parameters. DeltaReplay then compares each recorded step with the new task and the current screen, and decides whether to follow it, execute it after replacing its parameters, or leave it to the base agent. On AndroidWorld and SPA-Bench, DeltaReplay improves the task success rate over a base agent with the same backbone by up to 10.3 and 25.0 percentage points, respectively. These results indicate that deciding at each step how to use retrieved memory lets agents benefit even from partially matching trajectories. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.11707 — 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 2026-10-09T05:47:00.897Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).