שיפור יעילות ויכולת של סוכני GUI לאנדרואיד על ידי כלים עצמאיים

תקציר מקורי באנגליתarXiv:2609.06792v1 Announce Type: new Abstract: Android agents using a hybrid action space that combines GUI actions and tool actions (e.g., accessing application data via APIs) remain largely underexplored, mainly due to the excessive effort required to create tools. To address this gap, we introduce DroidTool, a framework for augmenting the agents with self-generated tools, which are realized as Python functions operating on application states (e.g., a database). To create tools with minimal human labor, DroidTool employs an agentic workflow featuring stages: proposal, implementation, test generation and execution, and repair. Notably, when testing the created tools for verification, it constructs relational tests across relevant tools for natural preparation of appropriate test precondi