Researchers have developed PalmClaw, an open-source framework enabling large language model (LLM) agents to run natively on mobile phones. Unlike existing systems that rely on graphical user interface interactions, PalmClaw directly accesses device capabilities through explicit tools, improving task success rates by 11.5% and reducing completion times by 94.9%. This on-device approach aims to leverage the accessibility and data on mobile devices for more efficient and controlled agent execution. AI
IMPACT Enables more capable and efficient AI agents directly on user mobile devices, potentially increasing adoption of on-device AI.
RANK_REASON The cluster describes a new open-source agent framework for mobile phones detailed in an arXiv paper.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
