Search-Based Software Engineering in the Landscape of AI Foundation Models (2505.19625v1)

Abstract: Search-based software engineering (SBSE), at the intersection of AI and software engineering, has been an active area of research for about 25 years. It has been applied to solve numerous problems across the entire software engineering lifecycle and has demonstrated its versatility in multiple domains. With the recent advancements in AI, particularly the emergence of foundation models (FMs), the evolution of SBSE alongside FMs remains undetermined. In this window of opportunity, we propose a research roadmap that articulates the current landscape of SBSE in relation to foundation models (FMs), highlights open challenges, and outlines potential research directions for advancing SBSE through its interplay with FMs. This roadmap aims to establish a forward-thinking and innovative perspective for the future of SBSE in the era of FMs.