Unsaturated soil has complicated mechanical properties, such as stress path and suction history dependencies, due to the influence of the depositional environment and its own structure. To describe the complex behavior of unsaturated soils, a path-dependence aware LSTM-based framework is proposed, where the initial stress state of the soil sample is used as the initial network parameters. Compared with the LSTM model, this framework demonstrates faster training convergence and better prediction accuracy. This framework was used to simulate the mechanical behavior of unsaturated soils under complex loading paths where both stress and suction change simultaneously and is not limited to suction-controlled triaxial shear tests. The predictions using both synthetic data from the Barcelona basic model (BBM) and experimental data from Pearl clay and Nanyang expansive soil and unsaturated sand-bentonite mixtures show that the LSTM-based framework can predict phenomena such as wetting collapse, stress path dependence, strain softening, and strain hardening in unsaturated soils.