<p>The multi-track, multi-layer laser cladding process is influenced by critical parameters, yet research on optimizing these parameters remains limited. This study aims to address this gap by focusing on the optimization of process parameters for multi-track, multi-layer laser cladding of 316L stainless steel. Orthogonal experiment was firstly conducted on laser power, scanning speed, powder feed rate, overlap rate, and Z-axis lift amount, and gray relational analysis (GRA) assessed their impact on quality indicators such as porosity, surface smoothness, and height difference. A Gaussian process regression (GPR) model was then developed to predict the relationship between process and quality parameters. Using an improved multi-objective particle swarm optimization (IMOPSO) algorithm, optimal parameters were identified, reducing porosity, surface smoothness, and height difference by 53.7%, 76.1%, and 92.7%, respectively. A repair experiment on a damaged 316L stainless steel tooth rack demonstrated that the optimized parameters increased microhardness to 310 HV₁, compared to 272 HV₁ for the substrate. The cladding formed a strong metallurgical bond, exhibited a uniform microstructure, and was free of cracks and pores. These results demonstrate the effectiveness of the proposed optimization approach in improving laser cladding repair quality.</p>