Search-Based Software Engineering and AI Foundation Models: Current Landscape and Future Roadmap

TL;DR

This paper defines a forward-looking roadmap at the intersection of search-based software engineering (SBSE) and foundation models (FMs), arguing that five integration themes will shape the next decade: using FMs to design SBSE, applying FMs to SE problems with SBSE assistance, using SBSE to address FM challenges, adapting SBSE practices for FM-centric SE activities, and exploring their synergistic potential. It surveys the current landscape, identifies empirical-evaluation challenges, and presents a 2030 horizon grounded in McLuhan's Tetrad to anticipate how FMs could enhance, retrieve, or potentially obsolesce SBSE methods. The roadmap highlights concrete opportunities across SE artifacts, SBSE implementations, code testing, and domain-specific applications (e.g., autonomous driving, robotics, IoT, and quantum computing), while acknowledging limitations such as non-determinism, hallucinations, and resource demands. Collectively, the work guides researchers toward integrating SBSE with diverse FM modalities (LLMs, VLMs, multimodal models) to improve automation, validation, and adaptability in evolving software ecosystems. The paper emphasizes rigorous, replicable empirical evaluations and calls for community-wide guidelines to fairly compare hybrid FM–SBSE approaches.

Abstract

Search-based software engineering (SBSE), which integrates metaheuristic search techniques with 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 recent advances in AI, particularly the emergence of foundation models (FMs) such as large language models (LLMs), the evolution of SBSE alongside these models remains undetermined. In this window of opportunity, we present a research roadmap that articulates the current landscape of SBSE in relation to FMs, identifies open challenges, and outlines potential research directions to advance SBSE through its integration and interplay with FMs. Specifically, we analyze five core aspects: leveraging FMs for SBSE design, applying FMs to complement SBSE in SE problems, employing SBSE to address FM challenges, adapting SBSE practices for FMs tailored to SE activities, and exploring the synergistic potential between SBSE and FMs. Furthermore, we present a forward-thinking perspective that envisions the future of SBSE in the era of FMs, highlighting promising research opportunities to address challenges in emerging domains.

Figures (3)

• Figure 1: Roadmap overview showing the discussion flow: strengths and weaknesses (\ref{['sec:pros&cons']}), SBSE–FM synergies (\ref{['sec:FMs4SBSE', 'sec:FMs4SEGenSBSE', 'sec:SBSE4FMSE', 'sec:SBSE4FM', 'sec:SBSE&FMs']}), empirical evaluation challenges (\ref{['sec:empiricalchallenges']}), and the 2030 research horizon (\ref{['sec:horizon']}).
• Figure 2: Key aspects of the potential synergy between SBSE and FMs. The abbreviations used are: FMs (Foundation Models), LLMs (Large Language Models), VLMs (Vision-Language Models), MMs (Multimodal Models), SBSE (Search-Based Software Engineering), SE (Software Engineering), SDLC (Software Development Lifecycle), and ADS (Autonomous Driving Systems).
• Figure 3: An overview of the tetrad illustrating the disruptive effects of FMs on SBSE.