# AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent

arXiv: https://arxiv.org/abs/2509.02444 · HTML: https://mlsanity.com/paper/2509.02444/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in GUI and mobile agents, one of 16 directions in LLM agents and tool use.
- First posted on arXiv 2 Sep 2025.

## Placed in

- LLM agents and tool use / [GUI and mobile agents](https://mlsanity.com/agents/gui-and-mobile-agents/)

## Built on by (most cited first, 4 of 4)

- [Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible](https://mlsanity.com/paper/2602.10139/) (2026)
- [Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation](https://mlsanity.com/paper/2511.22235/) (2025)
- [TeachMaster: Generative Teaching via Code](https://mlsanity.com/paper/2601.04204/) (2025)
- [OctoNest: Adaptive Cross-Device Execution through Stateful Control](https://mlsanity.com/paper/2606.20487/) (2026)

## Abstract (arXiv)

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.