SOURCE-LINKED INTELLIGENCE

Extending FunctionGemma for Practical On-Device Mobile Function Calling

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

On-device assistants require function-calling models that map natural language to local system actions, but existing resources emphasize web APIs or narrow mobile-action catalogs. We extend FunctionGemma 270M-it to practical Android workflows by introducing MOBILEACTIONSEXTENDED, a synthetic, schema-validated dataset of ~9,500 conversations covering fifteen device-control categories, including messaging, phone calls, camera/screenshot, brightness control, device-status queries, flashlight control, and application management. We fine-tune the 270M model with TRL supervised fine-tuning under com

Read original source ↗ Open in workspace

recordType

paper

region

Global