Research

Paper

AI LLM February 26, 2026

ClawMobile: Rethinking Smartphone-Native Agentic Systems

Authors

Hongchao Du, Shangyu Wu, Qiao Li, Riwei Pan, Jinheng Li, Youcheng Sun, Chun Jason Xue

Abstract

Smartphones represent a uniquely challenging environment for agentic systems. Unlike cloud or desktop settings, mobile devices combine constrained execution contexts, fragmented control interfaces, and rapidly changing application states. As large language models (LLMs) evolve from conversational assistants to action-oriented agents, achieving reliable smartphone-native autonomy requires rethinking how reasoning and control are composed. We introduce ClawMobile as a concrete exploration of this design space. ClawMobile adopts a hierarchical architecture that separates high-level language reasoning from structured, deterministic control pathways, improving execution stability and reproducibility on real devices. Using ClawMobile as a case study, we distill the design principles for mobile LLM runtimes and identify key challenges in efficiency, adaptability, and stability. We argue that building robust smartphone-native agentic systems demands principled coordination between probabilistic planning and deterministic system interfaces. The implementation is open-sourced~\footnote{https://github.com/ClawMobile/ClawMobile} to facilitate future exploration.

Metadata

arXiv ID: 2602.22942
Provider: ARXIV
Primary Category: cs.MA
Published: 2026-02-26
Fetched: 2026-02-27 04:35

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.22942v1</id>\n    <title>ClawMobile: Rethinking Smartphone-Native Agentic Systems</title>\n    <updated>2026-02-26T12:34:57Z</updated>\n    <link href='https://arxiv.org/abs/2602.22942v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.22942v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Smartphones represent a uniquely challenging environment for agentic systems. Unlike cloud or desktop settings, mobile devices combine constrained execution contexts, fragmented control interfaces, and rapidly changing application states. As large language models (LLMs) evolve from conversational assistants to action-oriented agents, achieving reliable smartphone-native autonomy requires rethinking how reasoning and control are composed.\n  We introduce ClawMobile as a concrete exploration of this design space. ClawMobile adopts a hierarchical architecture that separates high-level language reasoning from structured, deterministic control pathways, improving execution stability and reproducibility on real devices. Using ClawMobile as a case study, we distill the design principles for mobile LLM runtimes and identify key challenges in efficiency, adaptability, and stability. We argue that building robust smartphone-native agentic systems demands principled coordination between probabilistic planning and deterministic system interfaces. The implementation is open-sourced~\\footnote{https://github.com/ClawMobile/ClawMobile} to facilitate future exploration.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.MA'/>\n    <published>2026-02-26T12:34:57Z</published>\n    <arxiv:comment>7 pages, 1 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.MA'/>\n    <author>\n      <name>Hongchao Du</name>\n    </author>\n    <author>\n      <name>Shangyu Wu</name>\n    </author>\n    <author>\n      <name>Qiao Li</name>\n    </author>\n    <author>\n      <name>Riwei Pan</name>\n    </author>\n    <author>\n      <name>Jinheng Li</name>\n    </author>\n    <author>\n      <name>Youcheng Sun</name>\n    </author>\n    <author>\n      <name>Chun Jason Xue</name>\n    </author>\n  </entry>"
}