Tools for selective proactive as well as reactive information retrieval and knowledge discovery constitute some of the key enabling technologies for managing the data overload and translating recent advances in automated data acquisition, digital storage, computers and communications into fundamental advances in decision support, scientific discovery and related applications. The paper describes an implementation of intelligent, customizable mobile software agents for information retrieval and knowledge discovery from distributed data sources. These tools are part of the distributed knowledge network (DKN) toolbox that is being developed at the Iowa State University's Artificial Intelligence Laboratory. Experiments with retrieval of journal paper abstracts demonstrate the feasibility of using machine learning to design mobile intelligent agents for customized information retrieval. A similar approach has been successfully employed for knowledge discovery (using machine learning) from distributed data collections.