Image annotation is the natural language description for essential blobs within an Image. Many methodologies have recruited to reveal image semantics and represent it as annotation. Due to the exclusionary growth of number of images distributed over massive repositories, the task of manual annotation is tedious and over killing in term of times and efforts. This paper is presenting automatic annotation system based on the interaction between intelligent agents. Agent interaction is synonym to socialization behavior dominating Agent society. The presented system is exploiting knowledge evolution revenue due to the socialization to charge up the annotation process.