Adaptive Evolutionary Search for Optimizing Large-Scale AI Server Test Campaigns

Abstract

Evolutionary Test Optimization is being reorganized around the joint demands of performance with evidence quality, resource limits, and transfer across settings. The review develops an evidence-centered account of using adaptive search to allocate finite test budgets across large configuration spaces. It synthesizes 1 focal paper with 13 independently retrieved publications reviewed against traceable publication metadata. The analysis is organized around fitness design, exploration-exploitation, constraint handling, stopping rules, and reproducibility. The comparison does not regard outcomes from different settings as equivalent, the review compares task scope, modeling premises, and evaluation limits. Across the literature, the recurring conclusion is that advances in evolutionary test optimization become credible when workload, dependency, and recovery policy are evaluated together and when uncertainty about observability is reported explicitly. The comparative structure connects method selection to decision consequence and recurring validity threats, and proposes a research agenda centered on transparent baselines, stress testing, and reproducible evidence.