Metraipolis › archive › dc_0ac581eb41e1
MAPLE: A Multimodal Mobile Agent with Playbook-Learned Experience — arXiv:2611.01351
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01351
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T10:49:30.381Z
- SHA-256 of the archived text
f743d504fd43dc808a5b0ecd93453a230ef17613391d81e1da4e82bd45bbe27b- Stable URL of this page
https://metraipolis.com/documento/dc_0ac581eb41e1
How to cite
MAPLE: A Multimodal Mobile Agent with Playbook-Learned Experience — arXiv:2611.01351 — arXiv (en), https://arxiv.org/abs/2611.01351 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0ac581eb41e1 (Metraipolis archive dc_0ac581eb41e1, sha256 f743d504fd43dc808a5b0ecd93453a230ef17613391d81e1da4e82bd45bbe27b)
BibTeX
@misc{dc0ac581eb41e1,
title = {MAPLE: A Multimodal Mobile Agent with Playbook-Learned Experience — arXiv:2611.01351},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01351},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0ac581eb41e1; sha256 f743d504fd43dc808a5b0ecd93453a230ef17613391d81e1da4e82bd45bbe27b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01351. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Autonomous agents powered by vision-language models (VLMs) show great potential in navigating mobile graphical user interfaces (GUIs) to complete complex tasks. However, existing paradigms face fundamental scalability bottlenecks: fine-tuning requires massive high-fidelity datasets or prohibitive training time and compute, while gradient-free approaches rely on custom static heuristics or costly trial-and-error trajectory exploration where feedback is deferred until the end of execution. To address these limitations, we introduce MAPLE (Multimodal Agent with Playbook-Learned Experience), a novel gradient-free multi-agent framework that enables dynamic, step-wise experience sharing and execution-time prompt evolution. Unlike traditional action-reflection architectures that depend on costly, post-hoc self-reflection, MAPLE enables agents to cross-reference and distribute runtime insights in real time at each operational step. This dynamic exchange eliminates blind trial-and-error looping and steers agents along direct, grounded interaction paths. Extensive evaluations on the AndroidWorld and MobileWorld benchmarks demonstrate that MAPLE achieves state-of-the-art performance on complex, long-horizon mobile tasks, while proving scalable and adaptable across novel environments. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2611.01351 — 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 2026-11-03T10:49:22.881Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).