The rapid changing business environment of high-tech asset intensive enterprises such as semiconductor manufacturing constantly drives production managers to look for better solutions to improve the manufacturing process. Simulation, though identified to be the most appropriate technique to generate and test out possible execution plans, suffers from long cycle-time in the process of model update, analysis and verification. It is thus very difficult to carry out prompt "what-if" analysis to respond to abrupt changes in these systems. Symbiotic simulation systems have been proposed as a way of solving this problem by having the simulation and the physical system interact in a mutually beneficial manner. In this paper, we describe our work in developing a prototype proof-of-concept symbiotic simulation system that employs software agents in the monitoring, optimization and control of a semiconductor assembly and test operation. Categories and Subject Descriptors H.4.2 [Informa...