<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">mireabulletin</journal-id><journal-title-group><journal-title xml:lang="ru">Russian Technological Journal</journal-title><trans-title-group xml:lang="en"><trans-title>Russian Technological Journal</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2782-3210</issn><issn pub-type="epub">2500-316X</issn><publisher><publisher-name>RTU MIREA</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.32362/2500-316X-2026-14-5-85-93</article-id><article-id custom-type="edn" pub-id-type="custom">GBLESX</article-id><article-id custom-type="elpub" pub-id-type="custom">mireabulletin-1664</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>МАТЕМАТИЧЕСКОЕ МОДЕЛИРОВАНИЕ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>MATHEMATICAL MODELING</subject></subj-group></article-categories><title-group><article-title>Об агентно-ориентированном подходе к организации и разработке распределенных интеллектуальных систем</article-title><trans-title-group xml:lang="en"><trans-title>An agent-oriented approach to the organization and development of distributed intelligent systems</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-1979-5611</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Зайцев</surname><given-names>Е. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Zaytsev</surname><given-names>E. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Евгений Игоревич Зайцев, к. т. н., доцент</p><p>Институт кибербезопасности и цифровых технологий; кафедра КБ-14 «Цифровые технологии обработки данных»</p><p>119454; пр-т Вернадского, д. 78; Москва</p><p>Scopus Author ID 57218190023, ResearcherID ABA-4823-2020</p></bio><bio xml:lang="en"><p>Evgeniy I. Zaytsev, Cand. Sci. (Eng.), Associate Professor</p><p>Institute for Cybersecurity and Digital Technologies; Department of Digital Data Processing Technologies</p><p>119454; 78, Vernadskogo pr.; Moscow</p><p>Scopus Author ID 57218190023, ResearcherID ABA-4823-2020</p></bio><email xlink:type="simple">zajcev@mirea.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0001-8511-0978</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Нурматова</surname><given-names>Е. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Nurmatova</surname><given-names>E. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Елена Вячеславовна Нурматова, к. т. н., доцент</p><p>Институт кибербезопасности и цифровых технологий; кафедра КБ-3 «Разработка программных решений и системное программирование»</p><p>119454; пр-т Вернадского, д. 78; Москва</p><p>Scopus Author ID 57205460003, ResearcherID GQI-3212-2022</p></bio><bio xml:lang="en"><p>Elena V. Nurmatova, Cand. Sci. (Eng.), Associate Professor</p><p>Institute for Cybersecurity and Digital Technologies; Department of Software Development and System Programming</p><p>119454; 78, Vernadskogo pr.; Moscow</p><p>Scopus Author ID 57205460003, ResearcherID GQI-3212-2022</p></bio><email xlink:type="simple">nurmatova@mirea.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>МИРЭА – Российский технологический университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>MIREA – Russian Technological University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>08</day><month>10</month><year>2026</year></pub-date><volume>14</volume><issue>5</issue><fpage>85</fpage><lpage>93</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Зайцев Е.И., Нурматова Е.В., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Зайцев Е.И., Нурматова Е.В.</copyright-holder><copyright-holder xml:lang="en">Zaytsev E.I., Nurmatova E.V.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://www.rtj-mirea.ru/jour/article/view/1664">https://www.rtj-mirea.ru/jour/article/view/1664</self-uri><abstract><sec><title>   Цели</title><p>   Цели. Обоснование целесообразности и концептуализация агентно-ориентированного подхода к построению распределенных интеллектуальных систем, функционирующих в условиях неполноты исходных данных, высокой стохастичности и нестационарности внешней среды. Разработка формальных моделей агентов и методов их кооперации. Построение децентрализованной архитектуры, обеспечивающей адаптивность, масштабируемость и отказоустойчивость. Проектирование и реализация подсистемы распределенного хранения и обработки знаний.</p></sec><sec><title>   Методы</title><p>   Методы. Решение поставленных задач потребовало интеграции методов агентного моделирования, аппарата теории автоматов, марковских процессов принятия решений, нечеткой логики, искусственных нейронных сетей, алгоритмов многоагентного обучения с подкреплением, а также процедур экспертного оценивания, обеспечивающих верификацию и практическую адаптацию разработанных теоретических положений.</p></sec><sec><title>   Результаты</title><p>   Результаты. Разработана архитектура многоагентной интеллектуальной системы, основанная на кооперации автономных программных агентов, которая обеспечивает децентрализацию управления, слабую связанность компонентов и масштабируемость вычислительной инфраструктуры. Предложена формальная математическая модель интеллектуального агента, интегрирующая символьные методы представления и обработки знаний и нейросетевые алгоритмы. Разработана подсистема управления базой знаний, обеспечивающая динамическую реконфигурацию информационных потоков, адаптивную оптимизацию схем хранения и обработки данных, интеллектуальное кеширование, семантическую согласованность и поддержку немонотонного логического вывода на основе распределенных знаний. Реализована подсистема динамической балансировки вычислительной нагрузки на основе коалиции системных агентов-диспетчеров.</p></sec><sec><title>   Выводы</title><p>   Выводы. Агентно-ориентированная парадигма является эффективной методологической основой для построения распределенных интеллектуальных систем, предназначенных для решения задач в слабоформализуемых проблемных областях, характеризующихся неполнотой данных, неопределенностью и нестационарностью внешней среды. Децентрализация управления и распределенная организация базы знаний позволяют преодолеть фундаментальные ограничения монолитных интеллектуальных систем, а также обеспечить масштабируемость и высокую отказоустойчивость разрабатываемой системы. Реализованные в многоагентной интеллектуальной системе механизмы динамической оптимизации распределенной базы знаний и адаптивной балансировки вычислительной нагрузки позволяют не только решать интеллектуальные задачи, но и эффективно управлять собственными вычислительными и информационными ресурсами.</p></sec></abstract><trans-abstract xml:lang="en"><sec><title>   Objectives</title><p>   Objectives. The work set out to justify the expediency and provide a conceptualization of an agent-oriented approach to building distributed intelligent systems that operate under conditions of incomplete initial data, high stochasticity, and non-stationarity of the external environment. Formal models of agents and methods for their cooperation were developed as part of a decentralized architecture that ensures adaptability, scalability, and fault tolerance. A distributed knowledge storage and processing subsystem was designed and implemented.</p></sec><sec><title>   Methods</title><p>   Methods. In order to solve the problems, agent modeling methods were integrated with automata theory, Markov decision processes, fuzzy logic, artificial neural networks, multi-agent reinforcement learning algorithms, along with expert evaluation procedures to ensure the verification and practical adaptation of the developed theoretical provisions.</p></sec><sec><title>   Results</title><p>   Results. The developed multi-agent intelligent system architecture based on the cooperation of autonomous software agents provides decentralized control, weak coupling of components, and scalability of the computing infrastructure. The proposed formal mathematical model of an intelligent agent integrates symbolic knowledge representation methods and neural network algorithms. A distributed knowledge base management subsystem was developed to provide dynamic reconfiguration of information flows, adaptive optimization of data storage and processing schemes, intelligent caching, semantic consistency, and support for non-monotonic distributed knowledge-based inference. A dynamic load balancing subsystem was implemented based on a coalition of system software agents.</p></sec><sec><title>   Conclusions</title><p>   Conclusions. The described agent-oriented paradigm is an effective methodological basis for building distributed intelligent systems aimed at solving problems in poorly formalized problem domains characterized by incomplete data, uncertainty, and non-stationary external environments. Decentralized management and distributed knowledge base organization allow overcoming the fundamental limitations of monolithic intelligent systems which use the complete and consistent knowledge base and the monotonous logical inference, as well as ensuring the scalability and high fault tolerance of the developed system. The mechanisms of dynamic optimization of a distributed knowledge base and adaptive balancing of computational load implemented in a multi-agent intelligent system can be used not only to solve intelligent problems, but also to effectively manage their own computational and information resources.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>распределенная система</kwd><kwd>многоагентная система</kwd><kwd>программный агент</kwd><kwd>система представления и обработки знаний</kwd><kwd>многоагентное обучение с подкреплением</kwd></kwd-group><kwd-group xml:lang="en"><kwd>distributed system</kwd><kwd>multi-agent system</kwd><kwd>software agent</kwd><kwd>knowledge representation and processing system</kwd><kwd>multi-agent reinforcement learning</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Авторы не имеют финансовой заинтересованности в представленных материалах или методах</funding-statement><funding-statement xml:lang="en">The authors have no financial or proprietary interest in any material or method mentioned</funding-statement></funding-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">Зайцев Е.И., Нурматова Е.В. О подходе к управлению знаниями и разработке мультиагентной системы представления и обработки знаний. Russian Technological Journal. 2023;11(4):16–25. doi: 10.32362/2500-316X-2023-11-4-16-25</mixed-citation><mixed-citation xml:lang="en">Zaytsev E.I., Nurmatova E.V. Approach to knowledge management and the development of a multi-agent knowledge representation and processing system. Russian Technological Journal. 2023;11(4):16–25. doi: 10.32362/2500-316X-2023-11-4-16-25</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Zaytsev E.I., Nurmatova E.V. Increasing the performance of a multi-agent knowledge representation and processing system. Phys. Part. Nuclei. 2024;55:384–386. doi: 10.1134/S1063779624030948</mixed-citation><mixed-citation xml:lang="en">Zaytsev E.I., Nurmatova E.V. Increasing the performance of a multi-agent knowledge representation and processing system. Phys. Part. Nuclei. 2024;55:384–386. doi: 10.1134/S1063779624030948</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Nguyen T.T., Nguyen N.D., Nahavandi S. Deep Reinforcement Learning for Multiagent Systems : A Review of Challenges, Solutions, and Applications. IEEE Transactions on Cybernetics. 2020;50(9):3826–3839. doi: 10.1109/TCYB.2020.2977374</mixed-citation><mixed-citation xml:lang="en">Nguyen T.T., Nguyen N.D., Nahavandi S. Deep Reinforcement Learning for Multiagent Systems : A Review of Challenges, Solutions, and Applications. IEEE Transactions on Cybernetics. 2020;50(9):3826–3839. doi: 10.1109/TCYB.2020.2977374</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang K., Yang Z., Başar T. Multi-Agent Reinforcement Learning : A Selective Overview of Theories and Algorithms. In: Vamvoudakis K.G., Wan Y., Lewis F.L., Canseve D. (Eds.). Handbook of Reinforcement Learning and Control. Studies in Systems, Decision and Control. Springer; 2021. V. 325. P. 321–384. doi: 10.1007/978-3-030-60990-0_12</mixed-citation><mixed-citation xml:lang="en">Zhang K., Yang Z., Başar T. Multi-Agent Reinforcement Learning : A Selective Overview of Theories and Algorithms. In: Vamvoudakis K.G., Wan Y., Lewis F.L., Canseve D. (Eds.). Handbook of Reinforcement Learning and Control. Studies in Systems, Decision and Control. Springer; 2021. V. 325. P. 321–384. doi: 10.1007/978-3-030-60990-0_12</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Min Y., He J., Wang T., Gu Q. Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation. In: ICML’23 : Proceedings of the 40&lt;sup&gt;th&lt;/sup&gt; International Conference on Machine Learning. 2023. P. 24785–24811. arXiv preprint. arXiv:2305.06446. doi: 10.48550/arXiv.2305.06446</mixed-citation><mixed-citation xml:lang="en">Min Y., He J., Wang T., Gu Q. Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation. In: ICML’23 : Proceedings of the 40&lt;sup&gt;th&lt;/sup&gt; International Conference on Machine Learning. 2023. P. 24785–24811. arXiv preprint. arXiv:2305.06446. doi: 10.48550/arXiv.2305.06446</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Vasilev B., Gupta T., Peng B., Whiteson S. Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients. arXiv preprint. arXiv:2104.13446. 2021. doi: 10.48550/arXiv.2104.13446</mixed-citation><mixed-citation xml:lang="en">Vasilev B., Gupta T., Peng B., Whiteson S. Semi-On-Policy Training for Sample Efficient Multi-Agent Policy Gradients. arXiv preprint. arXiv:2104.13446. 2021. doi: 10.48550/arXiv.2104.13446</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Wang H., Liu Z., Yi J., Pu Z. Multiagent hierarchical cognition difference policy for multiagent cooperation. Algorithms. 2021;14(3):Article 98. doi: 10.3390/a14030098</mixed-citation><mixed-citation xml:lang="en">Wang H., Liu Z., Yi J., Pu Z. Multiagent hierarchical cognition difference policy for multiagent cooperation. Algorithms. 2021;14(3):Article 98. doi: 10.3390/a14030098</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Zeng S., Doan T.T., Romberg J. A two-time-scale stochastic optimization framework with applications in control and reinforcement learning. SIAM J. Optimization. 2024:34(1):946–976. doi: 10.1137/22M150277X</mixed-citation><mixed-citation xml:lang="en">Zeng S., Doan T.T., Romberg J. A two-time-scale stochastic optimization framework with applications in control and reinforcement learning. SIAM J. Optimization. 2024:34(1):946–976. doi: 10.1137/22M150277X</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Guo T., Chen X., Wang Y., Chang R., Pei S., Chawla N.V., Wiest O., Zhang X. Large Language Model based Multi-Agents: A Survey of Progress and Challenges. 2024. arXiv preprint. arXiv:2402.01680. doi: 10.48550/arXiv.2402.01680</mixed-citation><mixed-citation xml:lang="en">Guo T., Chen X., Wang Y., Chang R., Pei S., Chawla N.V., Wiest O., Zhang X. Large Language Model based Multi-Agents: A Survey of Progress and Challenges. 2024. arXiv preprint. arXiv:2402.01680. doi: 10.48550/arXiv.2402.01680</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Lim J., Vogel-Heuser B., Kovalenko I. Large Language Model-Enabled Multi-Agent Manufacturing Systems. arXiv preprint. arXiv:2406.01893. 2024. doi: 10.48550/arXiv.2406.01893</mixed-citation><mixed-citation xml:lang="en">Lim J., Vogel-Heuser B., Kovalenko I. Large Language Model-Enabled Multi-Agent Manufacturing Systems. arXiv preprint. arXiv:2406.01893. 2024. doi: 10.48550/arXiv.2406.01893</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Zhang Y., Sun R., Chen Y., Pfister T., Zhang R., Arik S. Chain of Agents: Large Language Models Collaborating on Long-Context Tasks. In: Advances in Neural Information Processing Systems. 2024;37. December 10–15, 2024. Vancouver, Canada. doi: 10.52202/079017-4202</mixed-citation><mixed-citation xml:lang="en">Zhang Y., Sun R., Chen Y., Pfister T., Zhang R., Arik S. Chain of Agents: Large Language Models Collaborating on Long-Context Tasks. In: Advances in Neural Information Processing Systems. 2024;37. December 10–15, 2024. Vancouver, Canada. doi: 10.52202/079017-4202</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Yang Y., Chai H., Shao S., Song Y., Qi S., Rui R., Zhang W. AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems. arXiv preprint. arXiv:2504.00587. 2025. doi: 10.48550/arXiv.2504.00587</mixed-citation><mixed-citation xml:lang="en">Yang Y., Chai H., Shao S., Song Y., Qi S., Rui R., Zhang W. AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems. arXiv preprint. arXiv:2504.00587. 2025. doi: 10.48550/arXiv.2504.00587</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Bai J., Mosbach S., Taylor C.J., Karan D., Lee K.F., Rihm S.D., Akroyd J., Lapkin A.A., Kraft M. A Dynamic Knowledge Graph Approach to Distributed Self-Driving Laboratories. Nat. Commun. 2024;15(1):Article 462. doi: 10.1038/s41467-023-44599-9</mixed-citation><mixed-citation xml:lang="en">Bai J., Mosbach S., Taylor C.J., Karan D., Lee K.F., Rihm S.D., Akroyd J., Lapkin A.A., Kraft M. A Dynamic Knowledge Graph Approach to Distributed Self-Driving Laboratories. Nat. Commun. 2024;15(1):Article 462. doi: 10.1038/s41467-023-44599-9</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Zhou W., Yan Y., Yang Q. DGRAG: Distributed Graph-based Retrieval-Augmented Generation for Edge-Cloud Systems. arXiv preprint. arXiv:2505.19847. 2025. doi: 10.48550/arXiv.2505.19847</mixed-citation><mixed-citation xml:lang="en">Zhou W., Yan Y., Yang Q. DGRAG: Distributed Graph-based Retrieval-Augmented Generation for Edge-Cloud Systems. arXiv preprint. arXiv:2505.19847. 2025. doi: 10.48550/arXiv.2505.19847</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
