presenting, by the head-mounted device via an assistant xbot, a suggestion to a user of the head-mounted device during a dialog session between the user and the assistant xbot, wherein the suggestion is associated with a plurality of actions to be performed by an assistant system associated with the assistant xbot;

accessing, by the head-mounted device, one or more signals from one or more inertial measurement unit (IMU) sensors of the head-mounted device during the dialog session;

determining, by an on-device head-gesture detection model trained only on IMU training data and based only on the one or more signals from the IMU sensors, a head gesture performed by the user during the dialog session; and

executing, by the assistant system executing on the head-mounted device, a first action from the plurality of actions, wherein the first action is selected based on the determined head gesture during the dialog session.