In nowadays easy to produce and publish information society, filtering services have to be able to simultaneously search in many potentially relevant and highly dynamic distributed sources. Ignoring a necessity to address information retrieval tasks in both distributed and dynamic enough manner is a major drawback for many existed search engines which try to survive the ongoing information explosion. The essence of a proposed solution for performing distributed filtering is in both installing filtering communities around information sources and setting a comprehensive cooperation mechanism, which both takes care about the dynamics of each particular source and tries to improve itself during a runtime. The applicability of the presented cooperation among communities is illustrated in a system serving as intelligent personal information assistant (PIA). Experimental results show that integrated cooperation mechanisms manage to enlarge the average user satisfaction for more than 10% while increasing the average duration of filtering for less than 4 seconds.