graduate student from 01.01.2023 until now
Saransk, Saransk, Russian Federation
employee
UDC 338.45
UDC 621.039
Procurement activities in the nuclear industry are critically important for the safety and stability of nuclear facilities. Errors at the procurement stage can lead to economic losses and increased risks to nuclear and radiation safety. In the context of digitalization and the development of artificial intelligence, the implementation of intelligent agent systems capable of automating routine processes and supporting decision-making is highly relevant. This article analyzes the feasibility of using agent systems, considers requirements for their deployment and the LLM models applied, and identifies potential areas of application and sources of financial benefit. Special attention is given to the “human-in-the-loop” principle, local deployment of systems, and compliance with the regulatory framework of the Russian Federation. The results show that the integration of intelligent agents can increase operational efficiency, reduce costs, and lower risks while ensuring compliance with safety requirements.
intelligent agents, procurement activities, nuclear industry, artificial intelligence, LLM models, digitalization, automation, risk management.
1. Federal'nyy zakon ot 05.04.2013 № 44 FZ «O kontraktnoy sisteme v sfere zakupok tovarov, rabot, uslug dlya obespecheniya gosudarstvennyh i municipal'nyh nuzhd» [Elektronnyy resurs]. - URL: http://www.consultant.ru/document/cons_doc_LAW_144624/ (data obrascheniya: 28.12.2025).
2. Federal'nyy zakon ot 27.07.2006 № 152 FZ «O personal'nyh dannyh» (poslednyaya redakciya) [Elektronnyy resurs]. - URL: https://www.consultant.ru/document/cons_doc_LAW_61801/ (data obrascheniya: 28.12.2025).
3. Federal'nyy zakon ot 26.07.2017 № 187 FZ «O bezopasnosti kriticheskoy informacionnoy infrastruktury Rossiyskoy Federacii» (poslednyaya redakciya) [Elektronnyy resurs] // Konsul'tantPlyus. - URL: https://www.consultant.ru/document/cons_doc_LAW_220885/ (data obrascheniya: 28.12.2025).
4. Federal'nyy zakon ot 18.07.2011 № 223 FZ «O zakupkah tovarov, rabot, uslug otdel'nymi vidami yuridicheskih lic» [Elektronnyy resurs]. - URL: https://www.consultant.ru/document/cons_doc_LAW_116964/ (data obrascheniya: 28.12.2025).
5. Edinyy otraslevoy standart zakupok atomnoy otrasli [Elektronnyy resurs]. - Rosenergoatom. - URL: https://www.rosenergoatom.ru/upload/iblock/b97/b979013c3f737b9151424975f9b40785.doc (data obrascheniya: 28.12.2025).
6. Zakupki doverili robotu // Strana Rosatom [Elektronnyy resurs]. - 2020. - URL: https://strana-rosatom.ru/2020/11/09/zakupki-doverili-robotu-rosatom-pr/(data obrascheniya: 28.12.2025).
7. AI agents in procurement // IBM [Elektronnyy resurs]. – URL: https://www.ibm.com/think/topics/ai-agents-in-procurement#:~:text=The%20procurement%20landscape%20is%20at,their%20supply%20chain%20operations%20workflows (data obrascheniya: 28.12.2025).
8. Danilov G. et al. Predicting the length of stay in neurosurgery with RuGPT-3 language model //Advances in Informatics, Management and Technology in Healthcare. – IOS press, 2022. – S. 555-558.
9. GigaChat - neyroset' ot Sbera [Elektronnyy resurs]. - Oficial'nyy sayt. - URL: https://gigachatsber.ru/ (data obrascheniya: 28.12.2025).
10. Gurtu A., Johny J. Supply chain risk management: Literature review //Risks. – 2021. – T. 9. – №. 1. – S. 16.
11. Iuvara A. Supply chain for the nuclear industry: how AI can help [Elektronnyy resurs]. - 2025. - URL: https://www.ai-nuclear.com/supply-chain-for-the-nuclear-industry-how-ai-can-help#:~:text=Second%2C%20and%20quite%20understandably%2C%20the,in%20order%20to%20be%20credible (data obrascheniya: 28.12.2025).
12. Kazakov M. et al. WebNLG-interno: Utilizing FRED-t5 to address the RDF-to-text problem (WebNLG 2023) //Proceedings of the Workshop on Multimodal, Multilingual Natural Language Generation and Multilingual WebNLG Challenge (MM-NLG 2023). – 2023. – S. 67-72.
13. Roy P., Pritam. Revolutionizing Supply Chain Management with AI Agents on DataBricks // International Journal of Computer Science Engineering and Information Technology. - 2025. - 11. - P. 3135–3141. - DOI:https://doi.org/10.32628/CSEIT25112710.
14. Touvron H. et al. Llama: Open and efficient foundation language models //arXiv preprint arXiv:2302.13971. – 2023.
15. Xu L. et al. On implementing autonomous supply chains: A multi-agent system approach //Computers in Industry. – 2024. – T. 161. – S. 104120.
16. Yang A. et al. Qwen3 technical report //arXiv preprint arXiv:2505.09388. – 2025.
17. YandexGPT - generativnaya neyroset' ot Yandeksa [Elektronnyy resurs]. - Oficial'naya stranica Yandex GPT v Yandeks.Brauzere. - URL: https://browser.yandex.ru/g/yandexgpt (data obrascheniya: 28.12.2025).
