Swarm intelligence algorithms exhibit remarkable potential in addressing complex optimization problems. Nevertheless, numerous existing approaches, including the Gannet Optimization Algorithm (GOA), encounter difficulties like premature convergence and restricted exploitation capacity during later iterative phases. This study presents a refined variant termed GSGOA, integrating a global best-guided mechanism, a Gaussian - based adaptive grouping strategy, and a Laplace - distributed scaling factor. These enhancements target strengthening the equilibrium between exploration and exploitation, alongside boosting convergence stability. The proposed algorithm undergoes assessment using the CEC 2017 benchmark suite, and experimental findings reveal that GSGOA consistently surpasses classical algorithms such as GOA, SCA, BOA, and WOA in solution precision and robustness.