In this work we propose a new adaptive algorithm for coop- erative spectrum sensing in dynamic environments where the channels are time varying. We assume a centralized spectrum sensing procedure based on the soft fusion of the signal energy levels measured at the sensors. The detection problem is posed as a composite hypothesis testing problem. The unknown pa- rameters are estimated by means of an adaptive clustering al- gorithm that operates over the most recent energy estimates re- ported by the sensors to the fusion center. The algorithm does not require all sensors to report their energy estimates, which makes it suited to be used with any sensor selection strategy (active sensing). Simulation results show the feasibility and ef- ficiency of the method in realistic slow-fading environments.