---
title: "PalmClaw: Native On-Device Agent Framework Boosts Efficiency by 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 Replacement","LLM Agent Framework","PalmClaw","On-Device Agent"]
---

# PalmClaw: Native On-Device Agent Framework Boosts Efficiency by 94.9%

## AI commentary

> This paper stands out by rethinking the mobile agent interaction paradigm at the system level, not just GUI simulation. For phone manufacturers and app developers, PalmClaw shows a more efficient path for on-device agent deployment and is worth paying attention to.

## At a glance

PalmClaw is an open-source agent framework running natively on mobile phones, exposing device capabilities as structured tools so that LLM agents can directly invoke mobile functions instead of GUI-based sequences. 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 overhead. The framework defines clear execution boundaries, making each action explicit and controllable, offering a new paradigm for on-device agent deployment.

## Key points

- PalmClaw runs natively on phones, managing sessions, memory, skills, tools, and the agent loop locally.
- Device capabilities are exposed as tools with explicit arguments, structured results, and clear execution boundaries.
- Achieves 11.5% relative improvement in task success and 94.9% reduction in completion time over GUI-based baselines.
- Open-source code is available on GitHub.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_5f0f3e0a23451b87f758e8ac