Architecture of Reflexive-active Systems of Artificial Heterogeneous Intelligent Agents

• Published in: 2023 5th International Conference on Control Systems, Mathematical Modeling, Automation and Energy Efficiency (SUMMA) pp. 274 - 278
• Main Author: Listopad, Sergey
• Format: Conference Proceeding
• Language: English
• Published: IEEE 08.11.2023
• Subjects: Cognition; Collective intelligence; Energy efficiency; Heuristic algorithms; hybrid intelligent multi-agent system; Mathematical models; Process control; Protocols; reflection; reflexive-active system of artificial heterogeneous intelligent agents; team of specialists
• DOI: 10.1109/SUMMA60232.2023.10349610

The paper proposes the typical model and the functional structure of reflexive-active systems of artificial heterogeneous intelligent agents within the multi-agent approach to the construction of distributed artificial intelligence systems. Reflexive-active systems of artificial heterogeneous intelligent agents are characterized by the dynamic composition and structure of agent connections, which are formed during the joint problem solving as a result of modeling each other's reflexive positions. Thus, self-organization of the system is ensured with the involvement of currently relevant versions of agents that implement modern information and intelligent technologies, and the formation of a collective subject relevant to the problem posed. The development of such systems for solving practical problems will make it possible to obtain new theoretical, methodological and technological knowledge about collective intelligence, increase the relevance of these systems to real teams of specialists, and also verify knowledge about collective processes and effects in small groups.