Advised by Professor Tim FInin, graduate students Guang Huang, Yang Yu and Xu Fei developed an agent that competed in an field of 30 entries implemented by teams from universities, research labs and companies from around the world. Each agent acted as a virtual computer manufacturer that interacted over the Internet with other software agents representing virtual suppliers of computer components and customers for the completed PCs.

The agents participated in rounds in which they compete for customer orders and for procurement of a variety of components over a period of several months. Each day customers issue requests for quotes and select from quotes submitted by the agents, based on delivery dates and prices. The agents are limited by the capacity of their simulated assembly lines and have to procure components from a set of eight suppliers. Four types of components are represented in the game: CPUs, motherboards, memory, and hard drives with several varieties of each type. Customer demand comes in the form of requests for quotes for different types of PCs, each requiring a different combination of components.

The UMBC agent competed in a series of qualifying and seeding rounds during June and July and, based on its performance, was invited to participate in the final contest held at Columbia University as part of the Third International Joint Conference on Autonomous Agents and Multi Agent Systems. The final showdown involved six agents that bought and sold for eight hours, simulating over eight years of business. The UMBC agent ended up making a profit of over $120 million dollars which, unfortunately, were simulated, as well.