AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912653458276352 |
|---|---|
| author | Fan, Jingru Dang, Yufan Wu, Jingyao Li, Huatao Yang, Runde Yang, Xiyuan Wang, Yuheng Qian, Chen |
| author_facet | Fan, Jingru Dang, Yufan Wu, Jingyao Li, Huatao Yang, Runde Yang, Xiyuan Wang, Yuheng Qian, Chen |
| contents | With the raid evolution of large language models and multimodal models, the mobile-agent landscape has proliferated without converging on the fundamental challenges. This paper identifies four core problems that should be solved for mobile agents to deliver practical, scalable impact: (1) generalization across tasks, APPs, and devices; (2) accuracy, specifically precise on-screen interaction and click targeting; (3) long-horizon capability for sustained, multi-step goals; and (4) efficiency, specifically high-performance runtime on resource-constrained devices. We present AppCopilot, a multimodal, multi-agent, general-purpose mobile agent that operates across applications. AppCopilot operationalizes this position through an end-to-end pipeline spanning data collection, training, finetuning, efficient inference, and PC/mobile application. At the model layer, it integrates multimodal foundation models with robust Chinese-English support. At the reasoning and control layer, it combines chain-of-thought reasoning, hierarchical task planning and decomposition, and multi-agent collaboration. At the execution layer, it enables experiential adaptation, voice interaction, function calling, cross-APP and cross-device orchestration, and comprehensive mobile APP support. The system design incorporates profiling-driven optimization for latency and memory across heterogeneous hardware. Empirically, AppCopilot achieves significant improvements on four dimensions: stronger generalization, higher precision of on screen actions, more reliable long horizon task completion, and faster, more resource efficient runtime. By articulating a cohesive position and a reference architecture that closes the loop from data collection, training to finetuning and efficient inference, this paper offers a concrete roadmap for general purpose mobile agent and provides actionable guidance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_02444 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent Fan, Jingru Dang, Yufan Wu, Jingyao Li, Huatao Yang, Runde Yang, Xiyuan Wang, Yuheng Qian, Chen Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Human-Computer Interaction With the raid evolution of large language models and multimodal models, the mobile-agent landscape has proliferated without converging on the fundamental challenges. This paper identifies four core problems that should be solved for mobile agents to deliver practical, scalable impact: (1) generalization across tasks, APPs, and devices; (2) accuracy, specifically precise on-screen interaction and click targeting; (3) long-horizon capability for sustained, multi-step goals; and (4) efficiency, specifically high-performance runtime on resource-constrained devices. We present AppCopilot, a multimodal, multi-agent, general-purpose mobile agent that operates across applications. AppCopilot operationalizes this position through an end-to-end pipeline spanning data collection, training, finetuning, efficient inference, and PC/mobile application. At the model layer, it integrates multimodal foundation models with robust Chinese-English support. At the reasoning and control layer, it combines chain-of-thought reasoning, hierarchical task planning and decomposition, and multi-agent collaboration. At the execution layer, it enables experiential adaptation, voice interaction, function calling, cross-APP and cross-device orchestration, and comprehensive mobile APP support. The system design incorporates profiling-driven optimization for latency and memory across heterogeneous hardware. Empirically, AppCopilot achieves significant improvements on four dimensions: stronger generalization, higher precision of on screen actions, more reliable long horizon task completion, and faster, more resource efficient runtime. By articulating a cohesive position and a reference architecture that closes the loop from data collection, training to finetuning and efficient inference, this paper offers a concrete roadmap for general purpose mobile agent and provides actionable guidance. |
| title | AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent |
| topic | Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Human-Computer Interaction |
| url | https://arxiv.org/abs/2509.02444 |