Signals 4 · free daily AI digest

Jev-Mobile: Jev as an Executor for Mobile GUI Agents

Paper recorded by Signals 4 on 2026-09-24 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-24 on arXiv · recorded by Signals 4 on 2026-09-25

Category: cs.AI · 人工智能 · first seen 2026-09-25

Abstract

Vision-language models (VLMs) have become a common foundation for autonomous mobile GUI agents, but most existing systems rely on the VLM for both planning and action grounding at nearly every interaction step, leading to substantial latency and model-serving cost. We introduce Jev-Mobile, which shifts this paradigm to low-frequency VLM planning and high-frequency lightweight execution: the VLM sp

Read on arXiv →

#16 most recent of 400 cs.AI papers we have recorded · ↑ newer: SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidanc · ↓ older: Search-Aware Reinforcement Learning for Multi-Component Query Understa
Cite this page: Jev-Mobile: Jev as an Executor for Mobile GUI Agents: the #16 most recent of 400 cs.AI papers we have recorded (as of 2026-09-24). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/jev-mobile-jev-as-an-executor-for-mobile-gui-agents.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions