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