Method and apparatus with autonomous driving decision learning

Provided is a method of learning a driving-decision algorithm. The method of learning a driving-decision algorithm for a vehicle includes: receiving a dataset related to driving from a database in which a driving scenario is stored; obtaining a first output by inputting the dataset into a first large language model (LLM), wherein the first output includes an inference of the first LLM based on the dataset; based on the first output, training a decision-trainer and a behavior-and-trajectory planner; generating a second LLM by updating the first LLM based on a result of the training; and generating a third LLM by updating the second LLM based on the trained decision-trainer and based on a selected traffic rule.