OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910135773822976 |
|---|---|
| author | Cheng, Kanzhi Li, Zehao Ma, Zheng Chen, Nuo Cao, Jialin Sun, Qiushi Ding, Zichen Xu, Fangzhi Yan, Hang Chen, Jiajun Luu, Anh Tuan Zhang, Jianbing Lu, Lewei Lin, Dahua |
| author_facet | Cheng, Kanzhi Li, Zehao Ma, Zheng Chen, Nuo Cao, Jialin Sun, Qiushi Ding, Zichen Xu, Fangzhi Yan, Hang Chen, Jiajun Luu, Anh Tuan Zhang, Jianbing Lu, Lewei Lin, Dahua |
| contents | Mobile agents powered by vision-language models have demonstrated impressive capabilities in automating mobile tasks, with recent leading models achieving a marked performance leap, e.g., nearly 70% success on AndroidWorld. However, these systems keep their training data closed and remain opaque about their task and trajectory synthesis recipes. We present OpenMobile, an open-source framework that synthesizes high-quality task instructions and agent trajectories, with two key components: (1) The first is a scalable task synthesis pipeline that constructs a global environment memory from exploration, then leverages it to generate diverse and grounded instructions. and (2) a policy-switching strategy for trajectory rollout. By alternating between learner and expert models, it captures essential error-recovery data often missing in standard imitation learning. Agents trained on our data achieve competitive results across three dynamic mobile agent benchmarks: notably, our fine-tuned Qwen2.5-VL and Qwen3-VL reach 51.7% and 64.7% on AndroidWorld, far surpassing existing open-data approaches. Furthermore, we conduct transparent analyses on the overlap between our synthetic instructions and benchmark test sets, and verify that performance gains stem from broad functionality coverage rather than benchmark overfitting. We release data and code at https://njucckevin.github.io/openmobile/ to bridge the data gap and facilitate broader mobile agent research. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_15093 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis Cheng, Kanzhi Li, Zehao Ma, Zheng Chen, Nuo Cao, Jialin Sun, Qiushi Ding, Zichen Xu, Fangzhi Yan, Hang Chen, Jiajun Luu, Anh Tuan Zhang, Jianbing Lu, Lewei Lin, Dahua Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Human-Computer Interaction Mobile agents powered by vision-language models have demonstrated impressive capabilities in automating mobile tasks, with recent leading models achieving a marked performance leap, e.g., nearly 70% success on AndroidWorld. However, these systems keep their training data closed and remain opaque about their task and trajectory synthesis recipes. We present OpenMobile, an open-source framework that synthesizes high-quality task instructions and agent trajectories, with two key components: (1) The first is a scalable task synthesis pipeline that constructs a global environment memory from exploration, then leverages it to generate diverse and grounded instructions. and (2) a policy-switching strategy for trajectory rollout. By alternating between learner and expert models, it captures essential error-recovery data often missing in standard imitation learning. Agents trained on our data achieve competitive results across three dynamic mobile agent benchmarks: notably, our fine-tuned Qwen2.5-VL and Qwen3-VL reach 51.7% and 64.7% on AndroidWorld, far surpassing existing open-data approaches. Furthermore, we conduct transparent analyses on the overlap between our synthetic instructions and benchmark test sets, and verify that performance gains stem from broad functionality coverage rather than benchmark overfitting. We release data and code at https://njucckevin.github.io/openmobile/ to bridge the data gap and facilitate broader mobile agent research. |
| title | OpenMobile: Building Open Mobile Agents with Task and Trajectory Synthesis |
| topic | Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Human-Computer Interaction |
| url | https://arxiv.org/abs/2604.15093 |