Key points are not available for this paper at this time.
There is a need for agent systems that can scale to real-world applications, yet retain the clean semantic underpinning of more formal agent frameworks. We describe the SRI Procedural Agent Realization Kit (SPARK), a new BDI agent framework that combines these two qualities. In contrast to most practical agent frameworks, SPARK has a clear, well-defined formal semantics that is intended to support reasoning techniques such as procedure validation, automated synthesis, and procedure repair. SPARK also provides a variety of capabilities such as introspection and meta-level reasoning to enable more sophisticated methods for agent control, and advisability techniques that support user directability. On the practical side, SPARK has several design constructs that support the development of large-scale agent applications. SPARK is currently being used as the agent infrastructure for a personal assistant system for a manager in an office environment.
Morley et al. (Mon,) studied this question.