<p>Concrete mix design plays a vital role in achieving the desired mechanical and durability properties of concrete while optimizing material use and cost. Traditional design methods often rely on empirical formulas and multiple laboratory trials, making the process time-consuming, costly, and resource-intensive. Recent advancements in artificial intelligence (AI) offer a data-driven alternative that can predict performance outcomes and optimize mix proportions with high accuracy. This review explores the application of artificial intelligence (AI) and machine-learning techniques to predict and optimize concrete mix proportions by utilizing historical datasets containing material properties, mix ratios, and performance outcomes. The increasing demand for sustainable and high-performance concrete requires more accurate and efficient mix design approaches. Several studies have reported the use of Random Forest Regression (RF) models to estimate 28-day compressive strength with high accuracy. Existing studies have also employed optimization frameworks to identify cost-effective and environmentally sustainable mix designs that meet specific strength requirements. The reviewed literature indicates that AI-based frameworks are capable of reducing the number of laboratory trials, lowering costs, and supporting greener construction practices.</p>