| title | Training Open Models for Agentic Phone Use |
|---|---|
| authors | Zhengyang Tang, Xin Lai, Pengyuan Lyu, Xinyuan Wang, Tianyi Bai, Chenxin Li, Yiduo Guo, Huawen Shen, Yuxuan Liu, Junyi Li, Zhengyao Fang, Yang Ding, Yi Zhang, Weinong Wang, Xingran Zhou, Liang Wu, Fei Tang, Sunqi Fan, Shangpin Peng, Zheng Ruan, Anran Zhang, Benyou Wang, Ji-Rong Wen, Rui Yan, Chengquan Zhang, Han Hu |
| date | 2026-06-22 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.23049 |
| affiliation | Tencent Hunyuan |
| upvotes | 18 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Phones are becoming an important execution surface for general-purpose agents, but training open models for reliable phone use remains difficult because the environment that matters at deployment, real devices running real apps, is slow, stateful, side-effectful, and hard to reset or verify, while scalable mock environments only approximate real behavior. We present PhoneBuddy, a training recipe and open-model line for agentic phone use that combines a real-app environment with a mock-app environment, PhoneWorld, which reconstructs runnable mock apps from real GUI usage structure. PhoneBuddy first builds a shared supervised fine-tuning stage from trajectories collected in both environments, then compares real-app RL against mixed RL across both environments. Across a 150-task human evaluation on real phones spanning apps, mini-apps, and cross-app workflows, task success rate improves from 36.67\% after supervised fine-tuning to 40.67\% after real-app RL and 45.33\% after mixed RL. On AndroidWorld, the same progression rises from 60.3\% to 77.2\% to 83.2\%. These results show that mock-app training is not a replacement for real-app RL, but a complementary source of scalable, resettable, and automatically checked interaction. The gains are strongest on app and mini-app tasks, while long-horizontal cross-app workflows remain an important open challenge. |
cite
@misc{tang2026training,
title={Training Open Models for Agentic Phone Use},
author={Zhengyang Tang and Xin Lai and Pengyuan Lyu and Xinyuan Wang and Tianyi Bai and Chenxin Li and Yiduo Guo and Huawen Shen and Yuxuan Liu and Junyi Li and Zhengyao Fang and Yang Ding and Yi Zhang and Weinong Wang and Xingran Zhou and Liang Wu and Fei Tang and Sunqi Fan and Shangpin Peng and Zheng Ruan and Anran Zhang and Benyou Wang and Ji-Rong Wen and Rui Yan and Chengquan Zhang and Han Hu},
year={2026},
eprint={2606.23049},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.23049}
}