Metaheuristics, such as evolutionary algorithms, ant colony optimization, and particle swarm optimization, are among the most successful techniques for solving complex optimization problems. Historically, the design of metaheuristic algorithms has been a manual process, guided by the experience and intuition of the algorithm designers, who often spend an excessive amount of time and effort trying to find designs that perform well for the optimization problem at hand.

In this talk, after discussing the drawbacks of manually designing metaheuristic algorithms, I will elaborate on some of the unintended negative consequences that the initially successful approach of “looking to nature for inspiration” has brought to the field of optimization. I will then describe the basics of the automatic design approach, which is an efficient alternative to manual design that allows the creation of high-performance implementations without the need for human intervention. Finally, I will present METAFOR, a metaheuristics software specifically developed for the automatic design of hybrid metaheuristics that has been shown to be capable of automatically generating metaheuristic algorithms that outperform the state of the art.