# Revisiting Hyper-Parameter Tuning for Search-based Test Data Generation

## TL;DR

This paper reevaluates the importance of hyper-parameter tuning in search-based test data generation, finding limited impact on most classes and that many configurations perform similarly to defaults.

## Contribution

It challenges previous claims by showing tuning has minimal effect on most classes and that many configurations are as effective as default settings.

## Key findings

- Tuning impacts only a small subset of classes.
- The difference between best and average configurations is minor.
- Many configurations outperform the baseline default.

## Abstract

Search-based software testing (SBST) has been studied a lot in the literature, lately. Since, in theory, the performance of meta-heuristic search methods are highly dependent on their parameters, there is a need to study SBST tuning. In this study, we partially replicate a previous paper on SBST tool tuning and revisit some of the claims of that paper. In particular, unlike the previous work, our results show that the tuning impact is very limited to only a small portion of the classes in a project. We also argue the choice of evaluation metric in the previous paper and show that even for the impacted classes by tuning, the practical difference between the best and an average configuration is minor. Finally, we will exhaustively explore the search space of hyper-parameters and show that half of the studied configurations perform the same or better than the baseline paper's default configuration.