ОСНОВИ ПРОЕКТУВАННЯ ІНТЕЛЕКТУАЛЬНИХ АГЕНТІВ:  ВІД АРХІТЕКТУРИ ДО МАТЕМАТИЧНИХ МОДЕЛЕЙ

M. V. Кrykhiskyi; Т. O. Vavryk; L. M. Hobyr

doi:10.32782/2521-6643-2025-2-70.27

M. V. Кrykhiskyi Ivano-Frankivsk National Technical University of Oil and Gas https://orcid.org/0009-0000-3285-4308
Т. O. Vavryk Ivano-Frankivsk National Technical University of Oil and Gas https://orcid.org/0000-0002-0612-0084
L. M. Hobyr Ivano-Frankivsk National Technical University of Oil and Gas https://orcid.org/0009-0007-3176-2314

DOI: https://doi.org/10.32782/2521-6643-2025-2-70.27

Keywords: intelligent agents, agent architecture, agent classification, sensors, actors

Abstract

Intelligent agents (IA) have become a central topic of modern research in the field of artificial intelligence. They are an important component of modern information technologies used to automate complex tasks such as data processing, decision-making, and adaptive learning. The development of intelligent agents is a complex, multifaceted process that includes the choice of architecture, the development of decision-making algorithms, and integration with the environment. Over the past decades, many new technologies and approaches have emerged that can significantly improve the effectiveness of agents in real-world applications. The article explores the conceptual foundations of intelligent agents, various approaches to their design, and key technologies that allow for the creation of autonomous and adaptive systems. The authors consider the general algorithm of the functioning of an intelligent agent, its main stages and architecture. An overview of the concept of intelligent agents is presented, including their basic properties, models of interaction with the environment and adaptive mechanisms. The main attention is paid to a universal algorithm that can be adapted to various applications in the field of artificial intelligence (AI). The article presents a mathematical basis for describing intelligent agents, which allows modeling their behavior, decision-making and interaction with the environment. The article presents a mathematical basis for describing intelligent agents, which allows modeling their behavior, decision-making and interaction with the environment. The main components of agents, their formalization through theoretical models and corresponding algorithms are considered. The mathematical description of agents is also considered, taking into account their properties, such as adaptability, autonomy and interaction with the environment. Mathematical analysis of intelligent agents is an important and rapidly developing area, covering a wide range of methods and techniques for modeling, analyzing and optimizing the behavior of intelligent agents.

References

1. Padgham L., Winikoff M. Developing Intelligent Agent Systems. A Practical Guide. Wiley, 2004. P. 225. DOI: 10.1002/0470861223
2. Saadi A., Maamri R., Sahnoun Z. Behavioral flexibility in Belief-Desire- Intention (BDI) architectures. Multiagent and Grid Systems. 2020. № 16(4). P. 343–377. DOI: https://doi.org/10.3233/MGS-200335
3. De Silva L. Meneguzzi F., Logan B. BDI Agent Architectures: A Survey, Proceedings of the Twenty- Ninth International Joint Conference on Artificial Intelligence Survey track. 2020, P. 4914–4921. DOI: https://doi.org/10.24963/ijcai.2020/684
4. Ekinci E., Halaç, T., Erdur C., Çetin Ö., Cakirlar I., Dikenelli O. Satisfying agent goals by executing different task semantics: HTN, OWL-S or plug one yourself. Autonomous Agents and Multi-Agent Systems. 2013. № 26(2). DOI: https://doi.org/10.1007/s10458-011-9185-2
5. Singh D., Sardina S., Padgham L., James G. Integrating Learning into a BDI Agent for Environments with Changing Dynamics. International Joint Conference on Artificial Intelligence. 2011. P. 2525–2530. DOI: https:// doi.org/10.5591/978-1-57735-516-8/IJCAI11-420
6. Zhang H., і Huang S. Y., A general framework for parallel BDI agents in dynamic environments. Web Intelligence and Agent Systems Journal. 2008. № 6(3). P. 327–351. DOI: https://doi.org/10.1109/IAT.2006.8
7. Germano R., Lakhmi C. J. Intelligent Agents. Theory and Applications. Springer Berlin, Heidelberg. 2004. P. 402. DOI: https://doi.org/10.1007/978-3-540-44401-5
8. Khosla R., Dillon T. Engineering Intelligent Hybrid Multi-Agent Systems. Springer New York. 1997. P. 410. DOI: https://doi.org/10.1007/978-1-4615-6223-8
9. Bryson, J. Cross-paradigm analysis of autonomous agent architecture. Journal of Experimental & Theoretical Artificial Intelligence. 2000. № 12(2). P. 165–189. DOI: https://doi.org/10.1080/095281300409829
10. Rumbell T., Barnden J., Denham S., Wennekers T. Emotions in autonomous agents: comparative analysis of mechanisms and functions. Auton Agent Multi-Agent Syst. 2012. № 25. P. 1–45. DOI: https://doi.org/10.1007/ s10458-011-9166-5
11. Cruz A., dos Santos A. V., Santiago R. H. N., Bedregal B. A Fuzzy Semantic for BDI Logic. Fuzzy Information and Engineering. 2021. № 13(2). P. 139-153. DOI: https://doi.org/10.1080/16168658.2021.1915455
12. Calegari R., Ciatto G., Mascardi, V., Omicini A. Logic-based technologies for multi-agent systems: a systematic literature review. Auton Agent Multi-Agent Syst. 2021. № 35(1). https://doi.org/10.1007/s10458-020-09478-3
13. Круглик В. С., Прокоф’єв Є. Г., Маринов, А. В. Аналіз можливостей використання інтелектуальних агентів в адаптивній системі електронного навчання. Педагогічні науки: теорія та практика. 2021. № 4. С. 295–302. Режим доступу: https://doi.org/10.26661/2786-5622-2021-4-44
14. Лопатто І. Ю., Говорущенко Т. О., Капустян М. В. Інтелектуальний агент верифікації врахування інформації предметної галузі в процесі розроблення програмних систем. Вісник Хмельницького національного університету. 2022. № 1. С. 116–119. URL: http://journals.khnu.km.ua/vestnik/?p=12131
15. Маринов А. В., Круглик В. С. Використання інтелектуальних програмних агентів для створення адаптивного середовища електронного навчання на базі lms moodle. Міжнародна науково-практична конференція «Цифрова трансформація та диджитал технології для сталого розвитку всіх галузей сучасної освіти, науки і практики». Zbiór prac_Tom 2. 2023. С. 306–308. URL: https://repo.btu.kharkov.ua/bitstream/123456789/29446/1/zbior_prac_tom_2__26012023-306-308.pdf
16. Noulamo T., Djimeli-Tsajio A., Kameugne R., Lienou, J. A Generic Intelligent Agent Design Approach Based on Artificial Neural Networks. World Journal of Engineering and Technology. 2023. № 11. С. 682–697. URL: 10.4236/wjet.2023.114046
17. Christie, S.H., Chopra, A. K., Singh, M. P. Mandrake: Multiagent Systems as a Basis for Programming Fault-Tolerant Decentralized Applications. Autonomous Agents and Multi-Agent Systems. 2022. № 36, A. № 16. DOI: https://doi.org/10.1007/s10458-021-09540-8
18. Latham N. Types of intelligent agent, 2024. URL: https://www.probecx.com/en-au/blog/types-of-intelligent-agent
19. Intelligent Agent, 2023. URL: https://www.larksuite.com/en_us/topics/ai-glossary/intelligent-agent
20. Harjyot K. What are AI Agents: Types, Benefits, Applications, and Examples. 2024. URL: https://www.signitysolutions.com/blog/ai-agents
21. Hiren Dhaduk. What is an AI Agent? Characteristics, Advantages, Challenges, Applications. 2023. URL: https://www.simform.com/blog/ai-agent/
22. Крихівський М. В., Крихівська С. М. Проблеми людино-машинної взаємодії в контексті штучного інтелекту. Збірник тез доповідей науково-практичної конференції «Інформаційні технології в освіті, техніці та промисловості». 2024. С. 176–177. URL: https://stlnau.in.ua/samoosvita/item/2024/iit241010.pdf

FOUNDATIONS OF INTELLIGENT AGENT DESIGN: FROM ARCHITECTURE TO MATHEMATICAL MODELING

Abstract

References