The forthcoming 6G wireless networks will be characterized by unprecedented network densification, driven by the explosive growth of human-type and machine-type devices. This paradigm shift introduces new challenges, rendering conventional optimization techniques ineffective. To address these challenges, this paper proposes the Graeco-Latin Square-Based Modified Moss Growth Optimization (GLS-mMGO) technique, a novel paradigm for solving complex optimization problems in 6G network resource allocation. Inspired by the intricate growth patterns of moss, GLS-mMGO integrates a Graeco-Latin Square Design to orchestrate the placement of moss individuals, ensuring a balanced exploration of the solution space. The algorithm leverages the orthogonal properties of Graeco-Latin Squares to create a structured framework for moss placement, enabling efficient exploration and avoiding premature convergence. Furthermore, GLS-mMGO incorporates a Modified Spore Dispersal Search mechanism to adaptively adjust the dispersal range and optimize the trade-off between exploration and exploitation. To evaluate the effectiveness of GLS-mMGO, we compare its performance with the existing Moss Growth Optimization (MGO) technique using 23 standard benchmark functions. The results demonstrate the GLS-mMGO technique’s superior performance, robustness, and efficacy in solving complex optimization problems in 6G network resource allocation.