Researchers Release OpenMobile-2 Smartphone Agents, Training Environment and Data

Researchers from Nanjing University, SenseTime, and other universities have released two OpenMobile-2 smartphone agent models, along with their training environment, data, and reproduction instructions. The models use Qwen3.5 with 9 billion parameters and Qwen3.6 with 27 billion parameters. The larger model’s score on the real-device SPA-Bench benchmark rose from 31.9 to 59.6 points, which the researchers describe as the best result among open models. The researchers also tested how training across more varied apps affects performance. With training data volume held constant, increasing app diversity raised task success on unseen apps from 60.7 to 67.5 percent. Experimental direct-command interfaces also improved task completion after targeted training.

Generated by AI from reports · Updated 51 minutes ago

There is not enough continuous observation data to plot a trend yet.