OpenPhone让手机端智能体在本地运行，只把难题丢给云端，省成本还高效。
OpenPhone: Mobile Agentic Foundation Models
- 用合成界面数据训练3B小模型，分两阶段提升决策能力。
- 在资源紧张下实现长推理与历史记忆管理，关键任务才上云。
- 适合追求低延迟、低成本的移动端智能体开发者。
随着多模态大语言模型（MLLM）的发展，构建图形界面智能体系统成为有前景的方向，尤其在拥有丰富应用生态和直观触控交互的移动平台。然而，移动GUI智能体面临核心困境：真正运行在设备上的小型模型（4B或更小）性能不足，而能力强的模型（从7B起）要么过大难以部署，要么成本过高（如仅限云端的闭源MLLM）。为解决此问题，我们提出OpenPhone，一种基于设备-云端协作的移动GUI智能体系统，兼顾本地模型的成本效益与云端模型的强大能力，同时规避其缺陷。具体而言，OpenPhone通过两阶段SFT→GRPO训练，在合成界面数据上增强Qwen2.5-VL-3B模型，使其具备强决策能力；集成高效长推理与内存管理机制，在资源受限环境下利用历史交互；默认本地执行，仅通过实时复杂度评估将挑战性子任务升级至云端。在AndroidLab在线基准及多种应用上的实验表明，OpenPhone表现接近甚至媲美更大模型，同时显著降低云端开销。
原文摘要 · Abstract (English)
With the advancement of multimodal large language models (MLLMs), building GUI agent systems has become an increasingly promising direction--especially for mobile platforms, given their rich app ecosystems and intuitive touch interactions. Yet mobile GUI agents face a critical dilemma: truly on-device models (4B or smaller) lack sufficient performance, while capable models (starting from 7B) are either too large for mobile deployment or prohibitively costly (e.g., cloud-only closed-source MLLMs). To resolve this, we propose OpenPhone, a mobile GUI agent system that leverages device-cloud collaboration to tap the cost-efficiency of on device models and the high capability of cloud models, while avoiding their drawbacks. Specifically, OpenPhone enhances Qwen2.5-VL-3B via two-stage SFT->GRPO training on synthetic GUI data for strong decision-making, integrates an efficient long-reasoning and memory management mechanism to utilize historical interactions under tight resources, and defaults to on-device execution--only escalating challenging subtasks to the cloud via real-time complexity assessment. Experiments on the online AndroidLab benchmark and diverse apps show OpenPhone matches or nears larger models, with a significant reduction in cloud costs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。