Alibaba open-sources MAI-Gym, an all-in-one GUI agent eval and RL training platform
Tongyi-MAI · hf · 2026-10-16
Alibaba's Token Hub team released MAI-Gym, an open all-in-one platform unifying GUI agent evaluation, data collection, and online RL training across mobile, computer, and web environments.
- Online RL with verifiable rewards has advanced math, coding, and tool use, but GUI agents lag due to costly interactive environments and scarce realistic tasks — MAI-Gym targets exactly this gap
- A shared rollout pipeline keeps evaluation and training behavior consistent; supports ten established benchmarks and scales to 20,000 parallel environment instances
- Automated synthesis of diverse GUI tasks: resettable mocked apps and coherent cross-app worlds with execution-validated task verifiers
- Trained MAI-Gym-9B, a unified 9B mobile/computer-use agent achieving state-of-the-art among open GUI agents under 10B parameters (78.4% on MobileWorld)
- Code: github.com/Tongyi-MAI/MAI-Gym
More from coding & agent
- Fintech HR built a sourcing agent on 60,000 past applicants — 30 qualified candidates in a month — G0NZ0BOY · 2026-10-16
- 3x DGX Spark cluster runs GLM-5.3-Flash locally behind a proxy, 1.75M tokens/day at 119W — Teknium · 2026-10-16
- Builder's one rule for trusted desktop agents: read freely, but sending, deleting, buying always ask first — No_Fan5310 · 2026-10-16
- GPT-built unifi-simulator makes MikroTik switches appear inside UniFi Network — Pytlicek · 2026-10-16
- Stanford drops 45-min SpaceX lecture on how Grok Bot's always-on agent harness works — Hesamation · 2026-10-16
- Opus 5.5 + Three.js demo stuns with water physics, fish and blossoms — nikola_mr64990 · 2026-10-16