Abstract
The multi-agent systems approach promises significant benefits to distributed systems engineering, such as enhanced interoperability, scalability, and reconfigurability. Moreover, the teamwork of multiple agents can unite the capabilities of individual agents to solve problems of greater complexity than those solved by the individual agents. This paper presents a framework for effective teamwork of BDI (Belief-Desire-Intention)-based agents. The framework is built on JAM derived from PRS (Procedural Reasoning System), which is an intelligent agent architecture based on BDI theories. The framework extends the single agent capabilities of JAM and creates a teamwork infrastructure to effectively unite multiple agents? capabilities to solve problems collaboratively.