SNEAK: Faster Interactive Search-based SE

TL;DR

SNEAK is a novel data mining approach for interactive search-based software engineering that outperforms standard methods in speed, efficiency, and scalability, especially in large models with minimal human input.

Contribution

This paper introduces SNEAK, a data mining method that improves interactive search-based SE by recursing into data divisions, providing faster and more scalable solutions than existing approaches.

Findings

SNEAK runs faster than standard iSBSE methods.

SNEAK asks fewer questions to users.

SNEAK achieves solutions within 3% of the best in the sample space.

Abstract

When AI tools can generate many solutions, some human preference must be applied to determine which solution is relevant to the current project. One way to find those preferences is interactive search-based software engineering (iSBSE) where humans can influence the search process. This paper argues that when optimizing a model using human-in-the-loop, data mining methods such as our SNEAK tool (that recurses into divisions of the data) perform better than standard iSBSE methods (that mutates multiple candidate solutions over many generations). For our case studies, SNEAK runs faster, asks fewer questions, achieves better solutions (that are within 3% of the best solutions seen in our sample space), and scales to large problems (in our experiments, models with 1000 variables can be explored with half a dozen interactions where, each time, we ask only four questions). Accordingly, we recommend SNEAK as a baseline against which future iSBSE work should be compared. To facilitate that, all our scripts are online at https://github.com/ai-se/sneak.