Due to the explosive growth of the WWW and the increasing amount of data available via the Internet, how to retrieve desired information from the Internet with high efficiency and good effectiveness is of great importance. In this paper, we propose an information retrieval model based on mobile agent technology. Theoretical analysis on the time complexity is also provided. Experiments are conducted on the performance of the proposed approach comparing with two existing approaches. Our approach well utilize mobile agents' inherent merits and provide useful tools for efficient information retrieval.