Using an ensemble of models is one of the Ways to prevent overfitting in time series prediction.
Relatedly, in the systems theory, full optimization of a complex system is undesirable because the lack of slack and margins can turn small perturbations into large events. Diversity of opinion helps to prevent exhaustive optimization.
Part of Ensemble learning.
Related:
https://ai.googleblog.com/2020/12/using-automl-for-time-series-forecasting.html