The success of artificial intelligence (AI) models has been limited by the requirement of large amounts of high-quality training data, which is just the opposite of the situation in most drug discovery pipelines. Active learning (AL) is a subfield of AI that focuses on algorithms that select the data they need to improve their models. Here, we propose a two-phase AL pipeline and apply it to the prediction of drug oral plasma exposure. In phase I, the AL-based model demonstrated a remarkable capability to sample informative data from a noisy data set, which used only 30% of the training data to yield a prediction capability with an accuracy of 0.856 on an independent test set. In phase II, the AL-based model explored a large diverse chemical space (855K samples) for experimental testing and feedback. Improved accuracy and new highly confident predictions (50K samples) were observed, which suggest that the model's applicability domain has been significantly expanded.