Modern flying wing drones are manufactured to be lighter in weight in order to optimize energy consumption and extend operational endurance. As a result of this trend, these air vehicles become more flexible and exhibit instability problems such as flutter and limit-cycle oscillations (LCOs), which can lead to catastrophic failure. This work aims to present an adaptive controller based on the integration of the sliding mode controller and the radial basic function neural network (RBFNN) to remove these problems that occur on the flying wing and improve its performance. The strategy of the designed controller offers the possibility to estimate the dynamics of the nonlinear model, suppress the flutter phenomena, and enhance the flight behavior. The selected model demonstrates the pitch and plunge dynamics of the flying wing driven employing leading- and trailing edge control flaps (LEC and TEC) and subject to aerodynamic forces under the quasi-steady assumptions and nonlinearities in structural rigidity. Numerical simulations show the controller's ability to suppress LCOs in the subcritical flight speed range and maintain smooth wing flight stability despite uncertainties and environmental disturbances.