Machine learning assisted predictive retransmission feedback

A method for wireless communication at a network entity, comprising:

• obtaining a capability parameter indicating one or more predictive retransmission feedback capabilities of a user equipment (UE);
• configuring an activation indicator in accordance with the obtained capability parameter;
• providing the activation indicator indicating that a predictive retransmission feedback procedure is enabled;
• providing data;
• and
• obtaining a predictive retransmission feedback associated with the data prior to a decoding of the data being completed, wherein obtaining the predictive retransmission feedback associated with the data comprises:
• obtaining a request to increase or decrease an aspect of a physical downlink resource indicated via the activation indicator.

An apparatus for wireless communication at a user equipment (UE), comprising:

• one or more memories;
• and
• one or more processors coupled with the one or more memories and configured to cause the UE to:
• transmit, to a network entity, a capability parameter that indicates one or more predictive retransmission feedback capabilities of the UE;
• receive, from the network entity, an activation indicator that indicates a predictive retransmission feedback procedure is enabled;
• receive data from the network entity;
• and
• transmit a predictive retransmission feedback associated with the data to the network entity, wherein the predictive retransmission feedback is configured to be computed, in accordance with the activation indicator, prior to completing a decoding of the data, and wherein to transmit the predictive retransmission feedback associated with the data, the one or more processors are configured to cause the UE to:
• transmit, to the network entity, a request to increase or decrease an aspect of a physical downlink resource indicated via the activation indicator in response to computation of the predictive retransmission feedback.

An apparatus for wireless communication at a network entity, comprising:

• one or more memories;
• and
• one or more processors coupled with the one or more memories and configured to cause the network entity to:
• obtain a capability parameter indicating one or more predictive retransmission feedback capabilities of a user equipment (UE);
• configure an activation indicator in accordance with the obtained capability parameter;
• provide the activation indicator indicating that a predictive retransmission feedback procedure is enabled;
• provide data;
• and
• obtain a predictive retransmission feedback associated with the data prior to a decoding of the data being completed, wherein to obtain the predictive retransmission feedback associated with the data, the one or more processors are configured to cause the network entity to:
• obtain a request to increase or decrease an aspect of a physical downlink resource indicated via the activation indicator.