The container relocation problem (CRP) is a complex combinatorial optimization problem that involves determining a sequence of container relocations to retrieve all containers in a specified order with minimal moves. Given the NP-hard nature of this problem, metaheuristic approaches have been extensively explored in prior research. This study proposes an adaptive Genetic Algorithm (GA)-based approach that dynamically prioritizes empty stacks during the relocation process to reduce unnecessary moves. Unlike traditional static relocation rules, our approach introduces an adaptive decision mechanism that prioritizes empty stacks when the proportion of empty stacks reaches or exceeds a threshold. This threshold is determined based on empirical evaluations and aims to strike a balance between minimizing relocations and maintaining operational efficiency. Experimental results in both small and large-scale datasets demonstrate that our adaptive model outperforms the existing model in terms of reducing the number of relocations, especially in larger bays.