{"ID":2875504,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.02444","arxiv_id":"2509.02444","title":"AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent","abstract":"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.","short_abstract":"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, A...","url_abs":"https://arxiv.org/abs/2509.02444","url_pdf":"https://arxiv.org/pdf/2509.02444v2","authors":"[\"Jingru Fan\",\"Yufan Dang\",\"Jingyao Wu\",\"Huatao Li\",\"Runde Yang\",\"Xiyuan Yang\",\"Yuheng Wang\",\"Chen Qian\"]","published":"2025-09-02T15:48:21Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.CV\",\"cs.HC\"]","methods":"[\"Language Model\"]","has_code":false}