PalmClaw: A Native On-Device Agent Framework for Mobile Phones

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Hongru Cai, Yongqi Li, Ran Wei, Wenjie Li
• Venue: arXiv: cs.CL
• Published: 2026-07-14
• Collected: 2026-07-15
• URL: http://arxiv.org/abs/2607.13027v1
• PDF: https://arxiv.org/pdf/2607.13027v1
• DOI: UNKNOWN

Plain-Language Brief

The paper introduces PalmClaw, a native agent framework designed to run on mobile phones. It aims to overcome the limitations of existing mobile agents by directly accessing device capabilities, making each action explicit and controlled. The results show an improvement in task success and reduction in completion time compared to the strongest baseline.

What the Document Says

• The paper presents PalmClaw, an open-source agent framework that runs natively on mobile phones.
• PalmClaw manages sessions, memory, skills, tools, and the agent loop directly on the device.
• It 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.
• The setup burden is lower compared to other methods.
• Code for PalmClaw is available at https://github.com/ModalityDance/PalmClaw.

Key Concepts Mentioned

• Large Language Model (LLM) agents
• mobile devices
• agent framework
• device capabilities
• task automation
• execution boundaries

Claims Made by the Document

• PalmClaw improves task success and reduces completion time compared to the strongest baseline.
• PalmClaw has a lower setup burden than other methods.

Evidence Used

• The provided text states that experiments show an 11.5% relative improvement in task success and a 94.9% reduction in completion time over the strongest baseline.
• It also mentions that the setup burden is lower compared to other methods.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.