Communication protocols in multi-agent systems: A development method and reference architecture

The meaning of a communicative act in a multi-agent system can be character ised at a number of different levels. We argue that only one level of meani ng is common across all applications: what we call the action-level semanti cs given by protocols or conversation policies. We define a general semanti c framework for specifying the semantics of a class of Agent Communication Languages (ACLs) based on protocols. We then introduce sACL, a small ACL, a nd show how the action-level semantics of this language can be integrated w ith an intentional semantics. This enables us to specify the meaning of an individual communicative act in the context of the conversation in which it occurs, and to customise sACL for different application domains. We descri be a development method for defining an ACL for a particular application, a nd give a reference architecture for the method using the Beliefs-Desires-I ntentions (BDI) agent architecture.