Intelligent Agents for Web-based Tasks: An Advice-Taking Approach

We present and evaluate an implemented system with which to rapidly and easily build intelligent software agents for Web-based tasks. Our design is centered around two basic functions: ScoreThisLink and ScoreThisPage .I f given highly accurate such functions, standard heuristic search would lead to ecient retrieval of useful information. Our approach allows users to tailor our system’s behavior by providing approximate advice about the above functions. This advice is mapped into neural network implementations of the two functions. Subsequent reinforcements from the Web (e.g., dead links) and any ratings of retrieved pages that the user wishes to provide are, respectively, used to rene the link- and pagescoring functions. Hence, our architecture provides an appealing middle ground between nonadaptive agent programming languages and systems that solely learn user preferences from the user’s ratings of pages. We describe our internal representation of Web pages, the major predicates in our advice language, how advice is mapped into neural networks, and the mechanisms for rening advice based on subsequent feedback. We also present a case study where we provide some simple advice and specialize our general-purpose system into a \home-page nder". An empirical study demonstrates that our approach leads to a more eective home-page nder than that of a leading commercial Web search site.