Sign inGet started
Paper · arXiv

Faithful Mobile GUI Agents with Guided Advantage Estimator

Vision-language model based graphical user interface (GUI) agents have shown strong interaction capabilities. However, they often behave unfaithfully, relying on memorized shortcuts rather than grounding actions in displayed screen evidence or user instructions. To address this, we propose Faithful-Agent, a faithfulness-first framework that reformulates GUI interaction to prioritize evidence groundedness and internal consistency. Faithful-Agent employs a two-stage pipeline: (i) a faithfulness-oriented SFT stage to instill abstainment behaviors under evidence perturbations; (ii) an RFT stage that further amplifies faithfulness by introducing the guided advantage estimator (GuAE), an anchor...

AuthorsHaowen Hu, Pengzhou Cheng, Zheng Wu et al.
Primary categorycs.AI
Published2 May 2026
Last updated at source2 May 2026
cs.AI
Embed this entry
<iframe src="https://silytics.si/embed/item/a191f5f9-ba7a-4dce-b3d5-0c0b1ac81635" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.