Retrieving information from heterogeneous database systems involves a complex process and remains a challenging research area. We propose a cognitively guided approach for developing an information-retrieval agent that takes the user's information request, identifies relevant information sources, and generates a multidatabase access plan. Our work is distinctive in that the agent design is based on an empirical study of how human experts retrieve information from multiple, heterogeneous database systems. To improve on empirically observed information-retrieval capabilities, the design incorporates mathematical models and algorithmic components. These components optimize the set of information sources that need to be considered to respond to a user query and are used to develop efficient multidatabase-access plans. This agent design, which integrates cognitive and mathematical models, has been implemented using Soar, a knowledge-based architecture.

The formulation of mathematical programming models1 is a knowledge-intensive task requiring the ability to access and apply multiple sources of knowledge. These include knowledge about the domain-specific characteristics of the problem whose mathematical model is to be developed, knowledge about how to construct mathematical programming models, and knowledge about the computational characteristics of available solvers [1, 6, 7, 10, 12, 181. Representing these various types of knowledge has been central to the development of the mathematical model formulation system (MFS) [9] built within the Soar [81 architecture.2 In this article we will describe our approach to constructing MFS. We follow a methodology more generally used for building intelligent systems, one of specifying the required processing of knowledge as a series of models at successively lower levels of abstraction [2]