Authors : Vladimir Rotkin

Volume/Issue : Volume 11 - 2026, Issue 8 - August

Google Scholar : https://tinyurl.com/5e4uzfrx

DOI : https://doi.org/10.38124/ijisrt/26aug1186

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : The rapid development of large language models and autonomous intelligent agents has significantly expanded the capabilities of natural language processing and decision support. However, practical implementation reveals fundamental limitations, particularly in tasks requiring computational robustness, reproducibility of results, and strict information consistency. These issues are particularly critical in fields such as engineering, geometry, and educational systems, where plausible but inaccurate responses ("hallucinations") and unstable behavior undermine system trust. This paper proposes a hybrid intelligent architecture with a deterministic core to address these challenges. Unlike fully autonomous systems, the proposed approach decouples functions: an adaptive agent handles user interaction and its interpretation, while a stationary deterministic core provides robust computation, logical consistency, and graphical display. The architecture introduces a clear distinction between the development phase, which allows for iterative improvement, and the operational phase, characterized by a fixed core that guarantees reproducible and verifiable results. By providing protocol-based interaction between the agent and the deterministic core, the system ensures that all generated output—text, computational, and graphical—remains consistent and adheres to the underlying domain model. This hybrid structure combines the flexibility of modern intelligent agents with the precision and reliability of formal deterministic models, offering a robust foundation for mission-critical intelligent applications.

Keywords : Hybrid Intelligent Architecture, Deterministic Core, Stationary Kernel, Intelligent Agent, Reproducibility of Results, Configurational Tasks, Geometric Problem Generator, Protocol-Based Interaction.

References :

1. Bubeck, S.; Chandrasekaran, V.; Eldan, R.; Gehrke, J.; Horvitz, E.; Kamar, E.; Lee, P.; Lee, Y. T.; Li, Y.; Lundberg, S.; Nori, H.; Palangi, H.; Ribeiro, M.; Zhang, Y. (2023). Sparks of Artificial General Intelligence: Early Experiments with GPT-4. arXiv:2303.12712. https://arxiv.org/abs/2303.12712
2. Ji, Z.; Lee, N.; Frieske, R.; Yu, T.; Su, D.; Xu, Y.; Ishii, E.; Bang, Y.; Chen, D.; Dai, W.; Chan, H. S.; Madotto, A.; Fung, P. (2023). Survey of Hallucination in Natural Language Generation. ACM Computing Surveys, 55(12), Article 248. https://arxiv.org/abs/2202.03629
3. OpenAI (2023). GPT-4 Technical Report. arXiv:2303.08774. https://arxiv.org/abs/2303.08774
4. Yao, S.; Zhao, J.; Yu, D.; Du, N.; Shafran, I.; Narasimhan, K.; Cao, Y. (2023). ReAct : Synergizing Reasoning and Acting in Language Models. ICLR. https://arxiv.org/abs/2210.03629
5. Schick, T.; Dwivedi-Yu, J.; Dessì, R.; et al. (2023). Toolformer : Language Models Can Teach Themselves to Use Tools. NeuroIPS. https://arxiv.org/abs/2302.04761
6. Shinn, N.; Cassano, F.; Labash, B.; Gopinath, A.; Narasimhan, K.; Yao, S. (2023). Reflexion : Language Agents with Verbal Reinforcement Learning. NeuroIPS. https://arxiv.org/abs/2303.11366
7. Amodei, D.; Olah, C.; Steinhardt, J.; Christiano, P.; Schulman, J.; Mané, D. (2016). Concrete Problems in AI Safety. arXiv:1606.06565. https://arxiv.org/abs/1606.06565
8. Russell, S. (2019). Human Compatible: Artificial Intelligence and the Problem of Control. Viking. https://doi.org/10.1007/978-3-030-86144-5_3
9. Mialon, G.; Dessì, R.; Lomeli, M.; et al. (2023). Augmented Language Models: A Survey. arXiv:2302.07842. https://arxiv.org/abs/2302.07842
10. Kaur, D.; Uslu, S.; Rittichier, K. J.; Durresi, A. (2022). Trustworthy Artificial Intelligence: A Review. ACM Computing Surveys, 55(2), Article 39. https://doi.org/10.1145/3491209
11. Jennings, N. R.; Wooldridge, M. J. (1998). Applications of Intelligent Agents. In: Agent Technology: Foundations, Applications, and Markets. Springer, Berlin, Heidelberg, pp. 3–28. http://eprints.soton.ac.uk/id/eprint/252188 .
12. Miller, T. (2019). Explanation in Artificial Intelligence: Insights from the Social Sciences. Artificial Intelligence, 267, 1–38. https://doi.org/10.1016/j.artint.2018.07.007
13. Rotkin, V.; Yavich, R.; Malev, S. (2018) Concept of AI Based Knowledge Generator. Journal of Education and e-Learning Research, Vol. 5, No. 4, pp. 235–241. https://doi.org/10.20448/journal.509.2018.54.235.241
14. Zvolinsky VP; Rotkin VM; Golovin VG; Matveeva NI (2017) Automation systems formation educational kontenta (in Russian) [Automated systems for the formation of educational content]. Scientific monograph. Publisher: VSAU, Volgograd, 120p. https://www.researchgate.net/publication/341788257_AUTOMATED_SYSTEMS_FOR_FORMATION_OF_EDUCATIONAL_CONTENT_AVTOMATIZIROVANNYE_SISTEMY_FORMIROVANIA_UCEBNOGO_KONTENTA
15. Rotkin, V. (2017) Methodology of immanent learning content. Scientific Israel - Technological Advantages, Vol. 19, No. 4. https://www.researchgate.net/publication/341786827_Methodology_of_immanent_learning_content
16. Yavich, R.; Malev, S.; Volinsky, I.; Rotkin, V. (2023) Configurable Intelligent Design Based on Hierarchical Simulation Models. Applied Sciences, 13(13), 7602. https://doi.org/10.3390/app13137602?urlappend=%3Futm_source%3Dresearchgate.net%26utm_medium%3Darticle
17. Yavich, R.; Rotkin, V.; Malev, S.; Zamir, E.; Kadrawi, O. (2021) Smart content creation for e-commerce. Patent US20210264366A1. https://patents.google.com/patent/US20210264366A1/en
18. Yavich, R; Malev, S; Rotkin, V. (2020) Triangle Generator for Online Mathematical E-learning. Higher Education Studies; Vol. 10, No. 3; 2020 ISSN 1925-4741 E-ISSN 1925-475X Published by Canadian Center of Science and Education. http://dx.doi.org/10.5539/hes.v10n3p72.