Electrocatalytic carbon dioxide reduction (CO2RR) technology enables the conversion of excessive CO2 into high-value fuels and chemicals, thereby mitigating atmospheric CO2 concentrations and addressing energy scarcity. Single-atom alloys (SAAs) possess the potential to enhance the CO2RR performance by full utilization of atoms and breaking linear scaling relationships. However, quickly screening high-performance metal portfolios of SAAs remains a formidable challenge. In this study, we proposed an active learning (AL) framework to screen high-performance catalysts for CO2RR to yield fuels such as CH4 and CH3OH. After four rounds of AL iterations, the ML model attained optimal prediction performance with the test set R2 of approximately 0.94 and successful prediction was achieved for the binding free energy of *CHO, *COH, *CO, and *H on 380 catalyst surfaces with an accuracy within 0.20 eV. Subsequent analysis of the SAA catalysts' activity, selectivity, and stability led to the discovery of eight previously unexplored SAA catalysts for CO2RR. Notably, the surface activity of Ti@Cu(100), Au@Pt(100), and Ag@Pt(100) shines prominently. Utilizing DFT calculations, we elucidated the complete reaction pathway of the CO2RR on the surfaces of these catalysts, confirming their high catalytic activity with limiting potentials of -0.11, -0.34, and -0.46 eV, respectively, which are significantly lower than those of pure Cu catalysts. The results showcase the exceptional predictive prowess of AL, providing a valuable reference for the design of CO2RR catalysts.