An Architecture for Information Retrieval Agents

Marina del Rey, CA 90292, USA {KNOBLOCK,ARENS}QISI.ED Abstract sources that are available to it. Given an information request, an agent identifies an appropriate set of With the vast number of information resources information sources, generates a plan to retrieve and available today, a critical problem is how to loprocess the data, uses knowledge about the data to recate, retrieve and process information. It would formulate the plan, and then executes it. This paper be impractical to build a single unified system that describes our approach to the issues of representation, combines all of these information resources. A communication, problem solving, and learning, and demore promising approach is to build specialized scribes how this approach supports multiple, collaboinformation retrieval agents that provide access rating information retrieval agents. to a subset of the information resources and can send requests to other information retrieval agents Representing the Knowledge of an when needed. In this paper we present an architecture for building such agents that addresses the Agent issues of representation, communication, problem Each information agent is specialized to a particular solving, and learning. We also describe how this area of expertise. This provides a modular organizaarchitecture supports agents that are modular, extion of the vast number of information sources and protensible, flexible and efficient, vides a clear delineation of the types of queries each agent can handle. In complex domains, the domain can be broken down into meaningful subparts and an Introduction information agent can be built for each subpart. With the current explosion of data, retrieving and inAn agent contains a model of its domain of expertise, tegrating information from various sources is a critical which provides the terminology for interacting with problem. We are addressing this problem by building agents, as well as models of all information sources information retrieval agents. This paper describes how that are available to that agent. Both the domain and these agents communicate with one another, model the information source models are expressed in the Loom information that is available from other agents, effiknowledge representation language’ [MacGregor, 1988, ciently retrieve information from other agents, and imMacGregor, 1990]. The domain model provides class prove their performance through experience, descriptions, subclass and superclass relationships, The architecture presented in this paper is based roles for each class, and other domain-specific inforon the SIMS information server, which was previmation. The information source models describe both ously described in [Arens et al., 1993]. This paper the contents of the information sources and the reinreviews the relevant details of SIMS, focusing on the tionship between those models and the domain model. aspects and features that support multiple collaborative agents. Each information agent is a separate SIMS Modeling the Domain server. Thus, each agent contains a detailed model of Each information agent is specialized to a single "apits domain of expertise and models of the information plication domain" and provides access to the available information sources within that domain. The largest *The research reported here was supported by Rome application domain that we have to date is a transLaboratory of the Air Force Systems Command and the Deportation planning domain, which involves information lense Advanced Research Projects Agency under contract no. F30602-91-C-0081. Views and conclusions contained in about the movement of personnel and materiel from this report are the authors’ and should not be interpreted one location to another using aircraft, ships, trucks, as representing the official opinion or policy of DARPA, RL, etc. the U.S. Government, or any person or agency connected The application domain models are defined using with them. a hierarchical terminological knowledge base (Loom)