Interaction of cognitive and reactive agents in an intelligent computing system: operational semantics
Nadezhda S. Karamysheva, Sergey A. Zinkin · Proceedings of Southwest State University · 2025
Purpose of research. The aim of this work is to develop an approach to constructing intelligent systems based on a replenished semantic network and a multi-agent environment with agents of various types: cognitive and deductive reactive. The architecture of a multi-level intelligent system is proposed and substantiated, which uses cognitive and reactive intelligent agents that differ in composition and number of implemented cognitive and deductive presumptions. Methods. Knowledge about the subject area is formalized both using the modal version of the first-order predicate calculus for describing cognitive agents and in terms of classical non-modal versions of predicate calculus and deductive inference mechanisms for reactive agents. The operation of an intelligent system is described by an incompletely defined semantic network represented by a conceptual graph and a system of production rules. Results. A functional architecture of an intelligent agent-based system is proposed. At the conceptual level, the architecture of an intelligent agent-based system is proposed to be represented by three sublevels. Cognitive agentsuse knowledge and beliefs that follow from epistemic logic systems. Cognitive presumptions of these agents include beliefs, goals, intentions, and desires of agents and are modeled within the framework of BDI logic. Conclusion. The conducted study shows the importance of BDI logic for cognitive agents, although it was used insignificantly in solving the task at hand, at the level of the content-conceptual description of the intelligent system. The extended functions of cognitive agents include the execution of input, registration, transmission and comparison of lists of objects and relations between them. The goals for the subsequent interpretation of cognitive agents are defined.