Recent research has made it possible to build information agents that retrieve and integrate information from the World Wide Web. Although there now exist solutions for modeling Web sources, query planning, and information extraction, less attention has been given to the problem of optimizing agent execution. In this paper, we describe Theseus, an efficient agent plan execution system. Through its pipelined, dataflow-based architecture, Theseus offers a high degree of parallelism and asynchronous information routing, features that can substantially improve performance. Theseus differs from prior work in reactive planning systems and parallel databases because it gathers information from the Web, a domain where information retrieval is a problem that is network-bound and is often based on interleaved data gathering and navigation. The Theseus plan language and architecture directly address these issues, resulting in a highperformance execution system.
Greg Barish, Dan DiPasquo, Craig A. Knoblock, Stev