← Saturday, October 17, 2026AgentsPaper

MAI-Gym scales GUI agent evaluation and RL training to 20,000 environments

huggingface.co by Panrong Tong et al. Editor score 8/10

MAI-Gym unifies GUI evaluation, data collection, and online RL across mobile, computer, and web environments, supporting 20,000 parallel instances. Its 9B agent scores 78.4% on MobileWorld and 76.2% on OSWorld-Verified, making the platform and results useful for teams building GUI agents.

What: MAI-Gym is an open platform for GUI agent evaluation, data collection, and online RL training across mobile, computer, and web environments.
Method: A shared rollout pipeline supports consistent agent behavior across evaluation and training; the platform scales to 20,000 parallel environment instances.
Why it matters: The platform supports reproducible GUI-agent development with synthesized applications and tasks; its mocked train-ticketing app training also transferred to a real phone.

A shared rollout pipeline supports GUI agent evaluation and online RL training. Sketched from the article's own text.

Read on huggingface.co → Code · 23 stars

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.