Decouple high-level VLM planning from low-level execution to speed up mobile agents

Introducing Jev-Mobile, using a fast typed decision model to execute multiple GUI actions per VLM call, achieving 32.7% faster completion and 73.4% lower API cost.

Industry
Linghua Zhang

Rice University

Research Digest··3 min read
The authors present Jev-Mobile, a mobile GUI agent that uses a large VLM only for occasional high-level planning while a lightweight model (Jev) handles frequent low-level action execution.

The authors built Jev-Mobile, an agent for Android GUI tasks.

Why this paper

From Rice University · Part of Agent Harness Optimization, now 67 papers

In one line

Jev-Mobile uses a lightweight decision model for frequent GUI actions, cutting VLM cost and latency while keeping competitive task success.

What we could check

  • ·No code link found
  • ·No weights link found
  • ·No dataset link found
  • ·No compute details found
  • ✓Limitations stated by the authors (2 noted)
  • ✓Reports numbers on named benchmarks

Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.

§
newspaper

Research Digest

Articles published under the Zotpaper byline are synthesized from multiple source publications by our AI editor and reviewed by our editorial process. Each story combines reporting from credible outlets to give readers a balanced, comprehensive view.