Abstract: The increasing impact of the greenhouse effect on ecosystems is prompting transportation agencies to seek methods for reducing CO₂ emissions during pavement construction and maintenance. Additionally, the laboratory mix design process, which involves selecting aggregate gradation and binder content, is time-consuming and labor-intensive. To accelerate the traditional mix design procedure, this study presented a mix design procedure that can automatically determine gradation and binder content based on machine learning (ML) and a meta-heuristic algorithm. Specifically, ML approaches were employed to model the relationship between volumetric properties (mixture bulk specific gravity (G_mb) and air void (VV)) and both mixture component properties and mixture proportion, based on a dataset collected from literature with 660 mixture designs. Integrated with the prediction of ML models and the modified multi-objective grey wolf optimization (MOGWO) algorithm, an automatic asphalt mix design was proposed to pursue three goals, including VV, cost, and CO₂ emission. The results indicated that least squares support vector regression (LSSVR) and eXtreme gradient boosting (XGBoost) achieved the highest prediction accuracies (correlation coefficient: 0.92 for VV and 0.96 for G_mb). The MOGWO algorithm successfully found the 26 optimal mix designs for the case of VV vs. cost vs. CO₂ emission. Compared to the traditional laboratory design, the optimal mixture with VV of 4% achieves a cost saving of 2.46% and a reduction of 4.03% in carbon emission. The volumetric properties of the mixtures output by the approach also align closely with values measured in a laboratory.