---
title: "PalmClaw：原生手机端Agent框架，效率提升94.9%"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.13027v1"
permalink: "https://feed.astralor.com/items/itm_5f0f3e0a23451b87f758e8ac"
published: "2026-07-14T17:58:57.000Z"
score: 75
channel: "ai"
tags: ["arXiv","GUI操作替代","LLM Agent框架","PalmClaw","移动设备原生Agent"]
---

# PalmClaw：原生手机端Agent框架，效率提升94.9%

## AI 点评

> 这篇论文的亮点在于从系统层面重构了移动Agent的交互范式，不像大部分工作只停留在GUI模拟。对手机厂商和应用开发者来说，PalmClaw展示了一条更高效的端侧Agent落地路径，值得关注。

## 速览

PalmClaw是一个开源的、原生运行在手机上的Agent框架，将设备能力暴露为结构化工具，使LLM Agent可以直接调用手机功能，替代传统GUI操作序列。实验表明，相比最强基线，任务成功率提升11.5%，完成时间减少94.9%，且设置负担更低。该框架定义了清晰的执行边界，每个动作显式可控，为移动端Agent落地提供了新范式。

## 关键点

- PalmClaw运行在手机本地，直接管理会话、记忆、技能、工具和Agent循环。
- 将设备能力封装为带显式参数、结构化结果和明确执行边界的工具。
- 相比GUI操作基线，任务成功率提升11.5%，完成时间减少94.9%。
- 开源代码已发布在GitHub。

## 全文

Large Language Model (LLM) agents have moved beyond generating responses to executing multi-step tasks by calling tools, observing the results, and iteratively deciding the next action. Most agent systems run on desktops or servers, which support tool use and task automation. Mobile devices are also important agent environments because they are widely accessible and contain users' data, sensors, and daily-use applications. Existing mobile agents mainly operate smartphones through graphical user interface (GUI) actions such as tapping, swiping, and typing, which often form long, interface-dependent sequences, cannot directly access device capabilities, and make execution boundaries difficult to define. We present \textbf{PalmClaw}, an open-source agent framework that runs natively on mobile phones and manages the sessions, memory, skills, tools, and agent loop directly on the device. PalmClaw exposes device capabilities as device tools with explicit arguments, structured results, and clearly defined execution boundaries. This design enables agents to use mobile capabilities directly while keeping each action explicit and controlled. Experiments show an 11.5\% relative improvement in task success and a 94.9\% reduction in completion time over the strongest baseline, with lower setup burden and traces illustrating how execution boundaries are applied. Code is available at https://github.com/ModalityDance/PalmClaw.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_5f0f3e0a23451b87f758e8ac