Metraipolis › archive › dc_199d16756aa7

Subgoal-aware Memory Graph for GUI Agent — arXiv:2610.31307

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.31307
License (as archived)
CC0-1.0
Archived
2026-10-25T20:53:23.587Z
SHA-256 of the archived text
4007eb13164aecf06e01b60427ca1988c4febcb65c95ca5eb247105ca5b62367
Stable URL of this page
https://metraipolis.com/documento/dc_199d16756aa7

How to cite

Subgoal-aware Memory Graph for GUI Agent — arXiv:2610.31307 — arXiv (en), https://arxiv.org/abs/2610.31307 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_199d16756aa7 (Metraipolis archive dc_199d16756aa7, sha256 4007eb13164aecf06e01b60427ca1988c4febcb65c95ca5eb247105ca5b62367)
BibTeX
@misc{dc199d16756aa7,
  title = {Subgoal-aware Memory Graph for GUI Agent — arXiv:2610.31307},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31307},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_199d16756aa7; sha256 4007eb13164aecf06e01b60427ca1988c4febcb65c95ca5eb247105ca5b62367},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31307. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

GUI agents aim to automate complex user tasks by interacting with mobile interfaces, but ef- fective decision-making in long-horizon set- tings requires reusing prior experience rather than relying solely on the environment ob- servations. Existing memory-based methods typically store experience either at the single- action level or as entire trajectories. Single- step actions are often too fine-grained to carry meaningful semantics, since the success of an individual action does not necessarily imply progress towards the overall goal. In contrast, whole trajectories are often too coarse-grained and difficult to reuse across different tasks. We propose a subgoal-aware memory graph that distils past trajectories into structured, reusable evidence at the level of subgoals. We define a subgoal as consecutive actions shar- ing a single intent, the granularity at which progress toward the task becomes meaning- ful. To reduce redundancy and support cross- task reuse, we organise subgoal experiences as nodes in a graph, where related memories can be merged, extended, and retrieved based on the environment observation. On SPA-Bench, our method improves success rate by 11.11% over the baseline.

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/2610.31307 — 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 2026-10-25T20:47:56.927Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).