Metraipolis › archive › dc_3b253a136183
AndroidFlux: Evaluating and Reward Modeling Failure Recovery Capabilities in Mobile Use Multimodal Agents — arXiv:2610.34384
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.34384
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T08:01:22.549Z
- SHA-256 of the archived text
74647880918df5a7fb19e6c239e4fa562a8b94981662533398160a1f9f6109fc- Stable URL of this page
https://metraipolis.com/documento/dc_3b253a136183
How to cite
AndroidFlux: Evaluating and Reward Modeling Failure Recovery Capabilities in Mobile Use Multimodal Agents — arXiv:2610.34384 — arXiv (en), https://arxiv.org/abs/2610.34384 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3b253a136183 (Metraipolis archive dc_3b253a136183, sha256 74647880918df5a7fb19e6c239e4fa562a8b94981662533398160a1f9f6109fc)
BibTeX
@misc{dc3b253a136183,
title = {AndroidFlux: Evaluating and Reward Modeling Failure Recovery Capabilities in Mobile Use Multimodal Agents — arXiv:2610.34384},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.34384},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3b253a136183; sha256 74647880918df5a7fb19e6c239e4fa562a8b94981662533398160a1f9f6109fc},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.34384. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Mobile-use multimodal agents are typically evaluated by task success from a clean initial state, which does not isolate their ability to recover from intermediate errors. Because mobile environments change dynamically, a general mobile-use agent must complete tasks robustly even from unexpected states and in unseen environments. This requires knowing when and where an agent makes errors, and whether it can recover from errors and subsequent states. To evaluate this capability, we introduce AndroidFlux, a failure-recovery benchmark built on AndroidWorld. AndroidFlux restores recorded trajectories to controlled checkpoints before, at, and after the first recoverable error, so that different agents continue from the same device state and history. On these checkpoints, a complementary reward-modeling benchmark evaluates recovery-action preferences using downstream rollout outcomes. We further release an offline reinforcement learning (RL) dataset that improves both error recovery and overall task success. Our evaluations show that recovery performance only partially correlates with clean-start success, and that explicit reasoning helps only models trained with GUI-domain specific RL. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2610.34384 — 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 2026-10-27T07:55:30.898Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).