Research · Saturday 17 October 2026 · story 5
MAI-Gym unifies GUI agent evaluation and online RL training
Hugging Face reports that MAI-Gym brings GUI agent testing, data collection, and online RL into one open platform for mobile, computer, and web environments. The paper says it covers 10 benchmarks, can run 20,000 parallel instances, and that MAI-Gym-9B scored 78.4% in the MobileWorld test and 76.2% in OSWorld-Verified.
Why it matters. It gives GUI agent teams an open setup for evaluation and online RL, with released apps, tasks, and model weights for reproducible work.
Read the original at huggingface.co