# OpenMobile-2 trains phone agents in simulated apps

> OpenMobile-2's authors report a gain on a separate physical-phone benchmark.

By BIGCHANGE.AI Editorial

Published: 2026-10-26T06:11:40.021Z
Updated: 2026-10-26T06:11:40.021Z
Canonical: https://bigchange.ai/blog/openmobile-2-simulated-app-training-real-phone-test

![Monitor image beside flat handset.](https://bigchange.ai/api/media/file/openmobile2-simulated-app-versus-physical-phone-hero-v1.png)
AI-generated conceptual illustration by BIG CHANGE.

An [October 9 preprint](https://arxiv.org/html/2610.14157v1) reports resettable app training and a separate physical-phone test.

## The big change

- **What changed:** The team built 35 commercial-style simulated apps with checkable state.
- **Why it matters:** Controlled tasks let researchers compare screen actions and experimental app-native tools; they do not prove live-app utility.
- **What to watch:** One physical-phone benchmark tests transfer, not everyday reliability.

## The measured boundary

MobileGym++ checks 215 simulated tasks. On SPA-Bench L3 physical phones, the 27B model scored 57.4% after hybrid supervised training and 59.6% after reinforcement learning: a 2.2 percentage-point gain. BIG CHANGE did not run either test.

## Sources

- [Paper v1](https://arxiv.org/html/2610.14157v1) — Author results.
- [Project](https://os-copilot.github.io/OpenMobile2-Home/) — Artifacts.
- [Code](https://github.com/OpenMobile2/OpenMobile2-Code) — Methods and licensing.
- [Simulator](https://github.com/OpenMobile2/MobileGym-plusplus) — Tasks and terms.