MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments

By Tong, Kong, Li +12Oct 14, 2026

Score████░░░░░░3.9

Key numbers

78.4% on MobileWorld and 76.2%
28.8% to 48.1%

VerdictWorth a reader's time today.

Read the original PDF Code

Abstract

Online reinforcement learning (RL) with verifiable rewards has driven rapid progress in mathematics, coding, and tool use, but scaling this success to GUI agents remains challenging due to the high cost of interactive environments and the scarcity of realistic training tasks. We introduce MAI-Gym, an open all-in-one platform that unifies GUI agent evaluation, data collection, and online RL training across mobile, computer, and web environments. Through a shared rollout pipeline, MAI-Gym ensures consistent agent behavior across evaluation and training, supports ten established benchmarks, and scales to 20,000 parallel environment instances. Beyond scalable infrastructure, MAI-Gym enables automated synthesis of diverse GUI applications and challenging tasks, including resettable mocked apps and coherent cross-app worlds with execution-validated task verifiers. Using MAI-Gym, we train MAI-Gym-9B, a unified 9B agent for mobile and computer use, achieving state-of-the-art performance among open GUI agents under 10B parameters: 78.4% on MobileWorld and 76.2% on OSWorld-Verified. Importantly, RL in a mocked train-ticketing app transfers to its real-world counterpart, improving task success on a phys- ical phone from 28.8% to 48.1%. We release the framework, synthesis skills, mocked apps, 2,000 verified tasks, and the model checkpoint to support repro- ducible research and further advances in scalable GUI agent training.

Panrong Tong, Quyu Kong, Pengxiang Li, Tianyu Xia, Hanzhang Zhou, Lei Wang, Chenglin Cai, Long Li, Long Chen, Jianan Zhang, Zhengwen Zeng, Xu Zhang, Gongjie Zhang, Yue Wang, Steven Hoi

The editor's rubric

Heuristic review

Dimension	Level	Weight	What that level means
Leverage	████░ 4	24%	A general-purpose tool used across several fields (Adam, ResNet, LoRA, next-generation sequencing).
Magnitude	███░░ 3	18%	Large gain: roughly 2x, or a clear new state of the art on a hard, unsaturated problem.
Evidence	███░░ 3	14%	Solid: multiple benchmarks or cohorts, ablations, fair baselines, released code or data.
Novelty	██░░░ 2	16%	A new combination of known ideas.
Trajectory	███░░ 3	18%	A clear path to scale.
Stakes	██░░░ 2	10%	Benefits a professional community (practitioners, clinicians, engineers).

Editor’s rationale

Heuristic triage from title and abstract text only, not a reading of the paper. Cues found: method (we propose); breadth (many tasks, programmable); gains (relative gain, state of the art); verification (multiple benchmarks, experimental validation, code released); scale (scalable); stakes (general AI).

How the score was computed

rank-2026-10-07

Score████░░░░░░3.9

Score = 10 × (65% × adjusted merit / 10 + 25% × attention + 10% × freshness)

Merit: 6.0 / 10; Weighted rubric, evidence-gated.
Adjusted merit: 4.9 / 10; Shrunk toward the desk prior by editor confidence (48%).
Attention: 0%; Citations, upvotes, points, mentions.
Freshness: 70%; Half-life decay since publication.

Citations0 (reference 15, via semantic-scholar, Oct 16, 2026, 13:29 UTC)
Influential citations0 (reference 3, via semantic-scholar, Oct 16, 2026, 13:29 UTC)
Hugging Face upvotes69 (reference 25, via hf-daily, Oct 16, 2026, 13:29 UTC)
GitHub stars6 (reference 250, via hf-daily, Oct 16, 2026, 13:29 UTC)

The record

Reviewed by heuristic-v2 on Oct 16, 2026, 13:29 UTC. Paper type: method.
Categories: cs.AI
TOP, No.1 in the Front page edition of October 16, 2026.
TOP, No.3 in the Artificial Intelligence edition of October 16, 2026.