Summary: We investigate the problem of automatically learning to interact with information sources on the Internet. We report on ïShopBotï and ïILAï, two implemented agents that learn to use such resources. ShopBot learns how to extract information from online vendors using only minimal knowledge about product domains. Given the homepages of several online stores, ShopBot autonomously learns how to shop at those vendors. After its learning is complete, ShopBot is able to speedlily visit over a dozen software stores and CD vendors, extract product information, and summarize the results for the user. ILA learns to translate information from Internet sources into its own internal concepts. ILA builds a model of an information source that specifies the translation between the sourceïs output and ILAïs model of the world. We show that ILAïs learning is fast and accurate, requiring only a small number of queries per information source. (Provider: Leibiger)