This paper proposes an adaptive grey wolf optimizer based on mutation strategies and generalized opposition-based learning (GOBL-IGWO) for optimizing truck dispatch in open-pit mines. To address the slow convergence in later stages and imbalance between global exploration and local exploitation capabilities inherent in the traditional grey wolf optimizer (GWO), an adaptive parameter adjustment mechanism, a generalized opposition-based learning strategy, and wolf pack mutation strategies were introduced. These modifications effectively enhanced the algorithm"s convergence and stability.2Comparative experiments evaluated the GOBL-IGWO algorithm against particle swarm optimization (PSO), differential evolution (DE), the traditional GWO, and an improved PSO (IPSO) using the CEC2005 benchmark functions (F1-F25). Results demonstrated that GOBL-IGWO exhibits superior optimization performance across unimodal, multimodal, hybrid, and composition functions. The algorithm showed particularly strong global search and local development capabilities on complex multimodal functions, effectively avoiding local optima. Furthermore, GOBL-IGWO significantly outperformed the compared algorithms in both convergence speed and solution accuracy, demonstrating higher optimization performance and robustness.These findings indicate that the GOBL-IGWO algorithm better adapts to the complexity and real-time requirements of open-pit mine truck scheduling problems. It provides a more reliable solution for practical applications, holding significant practical significance for improving mine transport efficiency and reducing production costs.