Multi-task optimization (MTO) algorithms aim to simultaneously solve multiple optimization tasks. Addressing issues such as limited optimization precision and high computational costs in existing MTO algorithms, this article proposes a multi-task snake optimization (MTSO) algorithm. The MTSO algorithm operates in two phases: first, independently handling each optimization problem
second, transferring knowledge. Knowledge transfer is determined by the probability of knowledge transfer and the selection probability of elite individuals. Based on this decision, the algorithm either transfers elite knowledge from other tasks or updates the current task through self-perturbation. Experimental results indicate that, compared to other advanced MTO algorithms, the proposed algorithm achieves the most accurate solutions on multitask benchmark functions, the five-task and 10-task planar kinematic arm control problems, the multitask robot gripper problem, and the multitask car side-impact design problem. The code and data for this article can be obtained from: https://doi.org/10.5281/zenodo.14197420.