Splitting smart home commands with a small LLM
A smart built with a small has trouble when one sentence contains several actions. “Turn on the bedroom light, make it warm white, and set brightness to 20%” looks like three actions, but it is really one desired final device state. If the system splits it into steps, the light may turn on with a default setting, then change color, then dim, which creates a poor experience.
“Turn on the bedroom light and save this as my evening preference” should be split because it crosses two areas: device control and preference storage. Outlines can extract on/off state, brightness, and light temperature from one simple command. The harder case is a mixed command such as turning on three hall lights at 30% while turning off four bedroom lights, where naive splitting can damage the meaning of the sentence.
The practical question is whether to classify the domain first and let the device agent handle all device attributes together, or use another planning method that works better with .
Key points
- The system uses a small for a smart .
- Light power, color, and brightness may need to be handled as one final device state.
- Device control and preference saving are separate domains and should be split.
- Outlines can extract basic values from simple commands.
- Naive splitting can break commands with multiple rooms, devices, and actions.