Conceptual model of a multi-agent innovative investment system using neurocognitive architectures
- Authors: Aigumov A.A.1, Pshenokova I.A.1,2
-
Affiliations:
- Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences
- Kabardino-Balkarian State University named after Kh.M. Berbekov
- Issue: Vol 27, No 5 (2025)
- Pages: 13-25
- Section: System analysis, management and information processing, statistics
- Submitted: 13.11.2025
- Published: 20.11.2025
- URL: https://journals.rcsi.science/1991-6639/article/view/351222
- DOI: https://doi.org/10.35330/1991-6639-2025-27-5-13-25
- EDN: https://elibrary.ru/FQOGOO
- ID: 351222
Cite item
Full Text
Abstract
The relevance of this study stems from the need to develop effective tools for managing innovative investment processes in a highly uncertain market environment. Traditional research approaches, such as econometric modeling or system dynamics, often encounter difficulties in describing the adaptive behavior of agents and unpredictable collective effects. Therefore, there is a need for tools that allow for more realistic simulation of the behavior of investment market participants in all its complexity.
Aim. The study is to develop and test a multi-agent model to evaluate the effectiveness of various innovative investment scenarios and identify optimal strategies for market participants.
Methods. This paper uses simulation and multi-agent modeling as the primary research methods.
Results. This article presents a multi-agent simulation model of an innovative investment system for analyzing interactions between investment market participants. Simulation experiments demonstrate that the developed model is able to replicate the dynamics of innovation system development, evaluate the effectiveness of various investment strategies, predict market participant behavior, and determine optimal parameters for interactions between agents.
Conclusions. Future studies propose expanding the model to include a more detailed classification of investors and projects, integration with real data, and additional learning and collective investment mechanisms. The developed model can serve as a basis for creating practical decision-making tools for innovative investment and contribute to improving the efficiency of investment activities.
About the authors
A. A. Aigumov
Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences
Email: arrrslan@mail.ru
Postgraduate Student of the Department of Мulti-Аgent Intellectual Robotics Systems of the Scientific and Educational Center
Russian Federation, 2, Balkarov street, Nalchik, 360010, RussiaI. A. Pshenokova
Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences; Kabardino-Balkarian State University named after Kh.M. Berbekov
Author for correspondence.
Email: pshenokova_inna@mail.ru
ORCID iD: 0000-0003-3394-7682
SPIN-code: 3535-2963
Candidate of Physical and Mathematical Sciences, Head of the Research Center “Intellectual Integrated Information and Management Systems”
Russian Federation, 2, Balkarov street, Nalchik, 360010, Russia; 173, Chernyshevsky street, Nalchik, 360004, RussiaReferences
- Esikova T.N., Vakhrusheva S.V. Modeling of the agent environment in the development of a multi-agent system using large-scale infrastructure projects. Vestnik SibGUTI. 2019. No. 3. Pp. 63-69. EDN: BVMADR. (In Russian)
- Furchi A., Lippi M., Carpio R.F. Gasparri A. Route optimization in precision agriculture settings: A multi-Steiner TSP formulation. IEEE Trans. Autom. Sci. Eng. 2023. No. 20. Pp. 2551-2568.
- Gong T., Zhu L., Yu F.R., Tang T. Edge intelligence in intelligent transportation systems: a survey. IEEE Trans. Intell. Transp. Syst. 2023. No. 24. Pp. 8919-8944.
- Wang H., Wang C., Zhou K. et al. TEBChain: A trusted and efficient blockchain-based data sharing scheme in UAV-assisted IoV for disaster rescue. IEEE Trans. Netw. Serv. Manag. 2024. No. 21. Pp. 4119-4130.
- Liu Z., Qiu C., Zhang Z. Sequence-to-sequence multi-agent reinforcement learning for multi-uav task planning in 3D dynamic environment. Appl. Sci. No. 12. 2022. P. 12181.
- Russell S., Norvig P. Iskusstvennyy intellekt: sovremennyy podkhod [Artificial Intelligence: A Modern Approach]. 2nd edition. Moscow: Vil'yams, 2016. 1408 p. (In Russian)
- Bonabeau E. Agent-based modeling: methods and techniques for simulating human systems. Proceedings of the National Academy of Sciences of the United States of America. 2002. No. 99(3). Pp. 7280-7287.
- Liu J., Dong J. A multi-agent simulation of investment choice in the P2P lending market with bankruptcy risk. Journal of Simulation. 2020. No. 16. Pp. 1-15. doi: 10.1080/17477778.2020.1759386
- Kostka A., Chudziak J.A. Towards cognitive synergy in LLM-based multi-agent systems: integrating theory of mind and critical evaluation. arXiv preprint arXiv:2507.21969. 2025. doi: 10.48550/arXiv.2507.21969
- Borodulin I.V. An increase in the accuracy of large language models using extended search generation. Science Bulletin. Vol. 3. No. 3(72). 2024. Pp. 400-405. (In Russian)
- Xiao Y. et al. TradingAgents: Multi-agents LLM financial trading framework. arXiv preprint arXiv:2412.20138. 2024.
- Dwarakanath K., Vyetrenko S., Tavallali P., Balch T. ABIDES-Economist: Agent-based simulation of economic systems with learning agents. arXiv preprint arXiv:2402.09563. 2024
- Souissi M.A., Bensaid K., Ellaia R. Multi-agent modeling and simulation of a stock market. Investment Management & Financial Innovations. 2018. Vol. 15. No. 4. P. 123.
- Locatelli M., Pellegrini L., Accardo D. et al. People flow management in a healthcare facility through crowd simulation and agent-based modeling methods. Journal of Physics: Conference Series. 2023. No. 2600. doi: 10.1088/1742-6596/2600/14/142007
- Huang Y., Zhou Ch., Cui K., Lu X. A multi-agent reinforcement learning framework for optimizing financial trading strategies based on TimesNet. Expert Systems with Applications. 2024. Vol. 237. P. 121502.
- Paul J. Multi-agent systems for collaborative investment strategy design. 2024.
- Nagoev Z.V. Intellektika, ili Myshleniye v zhivykh i iskusstvennykh sistemakh [Intelligence, or thinking in living and artificial systems]. Nalchik: Izd-vo KBNTS RAN, 2013. 211 p. (In Russian)
- Nagoev Z.V. Multiagenic existential displays and functions. News of the Kabardino-Balkarian Scientific Center of the RAS. 2013. No. 4. Pp. 63-71. EDN: QZTFLX (In Russian)
- Nagoev Z., Pshenokova I., Nagoeva O., Sundukov Z. Learning algorithm for an intelligent decision making system based on multi-agent neurocognitive architectures. Cognitive Systems Research. 2021. Vol. 66. Pp. 82-88. doi: 10.35330/1991-6639-2020-3-95-23-31
- Bzhikhatlov K., Nagoeva O., Anchokov M., Makoeva D. Methods and algorithms (modeling of reasoning) to synthesize intellectual behavior of autonomous mobile robots and program complexes based on received reasoning models. In: Samsonovich A.V., Liu T. (eds) Biologically Inspired Cognitive Architectures 2024. BICA 2024. Studies in Computational Intelligence. 2024. Vol. 477. Springer, Cham. doi: 10.1007/978-3-031-76516-2_7
- Pshenokova I.A., Nagoeva O.V., Apshev A.Z., Ennes A.Z. Formation of dynamic causal dependencies in the management of the behavior of an intellectual agent based on the formalism of multiagenic neurocognitive architectures. News of the Kabardino-Balkarian Scientific Center of the RAS. 2022. No. 5(109). Pp. 73-80. doi: 10.35330/1991-6639-2022-5-109-73-80. (In Russian)
Supplementary files


