SNEAK: Faster Interactive Search-based SE
This addresses the need for more efficient human-in-the-loop optimization in software engineering, though it is incremental as it builds on existing iSBSE methods.
The paper tackles the problem of efficiently incorporating human preferences into AI-generated solutions through interactive search-based software engineering (iSBSE), and shows that their SNEAK tool runs faster, asks fewer questions, and achieves solutions within 3% of the best possible, scaling to models with 1000 variables using only half a dozen interactions.
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.