Despite offering remarkable advantages as solvents, double salt ionic liquids (DSILs) have been scarcely studied for extractive dearomatization from hydrocarbons as well as many other applications, thus urging a theoretical guidance method. In this work, a systematic framework combining the rational screening-validation and mechanistic analysis is proposed for tailoring DSILs for the o-xylene/n-octane separation. From an initial pool of commercially available ionic liquids (ILs), key thermodynamic properties of paired DSILs are predicted by COSMO-RS while their important physical properties are estimated from those of corresponding parent ILs (retrieved from experimental database or predicted by a deep learning model). Promising DSILs are tested by liquid-liquid equilibrium experiments, wherein the ion ratio-effect is also evaluated. The mechanism underlying the tunability of DSIL thermodynamic properties is disclosed by means of quantum chemistry calculation and molecular dynamics simulation. This work can be a valuable reference for guiding the design of DSILs for diverse applications.