RRM-GPT generates 5G NR scheduling grants field by field with an autoregressive model and transfers learned behavior to an unseen scenario
The authors propose RRM-GPT, an autoregressive framework that generates radio resource management decisions field by field as a language model generates text: an encoder maps heterogeneous network observations into common tokens and a decoder emits each decision conditioned on the network state and the fields already committed; in a 5G NR case study, a single model generates complete scheduling grants spanning user selection, timing, link adaptation, resource allocation, and control signaling, and transfers learned behavior to an unseen scenario without adaptation.