We present an approach to a Genetic Information Retrieval Agent Filter (GIR
AF) for documents from the Internet using a genetic algorithm (GA) with fuz
zy set genes to learn the user's information needs. The population of chrom
osomes with fixed length represents such user's preferences. Each chromosom
e is associated with a fitness that may be considered the system's belief i
n the hypothesis that the chromosome, as a query, represents the user's inf
ormation needs. In a chromosome, every gene characterizes documents by a ke
yword and an associated occurrence frequency, represented by a certain type
of a fuzzy subset of the set of positive integers. Based on the user's eva
luation of the documents retrieved by the chromosome, compared to the score
s computed by the system, the fitness of the chromosomes is adjusted. A pro
totype of GIRAF has been developed and tested. The results of the test are
discussed, and some directions for further works are pointed out.