An internal agent architecture incorporating standard reasoning components and standards-based agent communication

This paper discusses a general architecture for intelligent software agents. It can be used to construct agents that engage in high-level reasoning by employing standard reasoning engines as plug-in components, while communicating with other agents by means of the standard FIPA-based communication protocols. The approach discussed uses internal micro-agents and declarative goals to form a hierarchical internal agent architecture. It has been implemented and tested with three high-level formal reasoning system components that are used in conjunction with an existing agent platform, OPAL, which supports the FIPA (Foundation for Intelligent Physical Agents) communication standards.