Limits of Applicability of Artificial Intelligence in Public Administration: Memory of LLM-Based Agents vs. Human Memory

In recent years, large language models and agent systems based on them have been considered a promising tool for the digital transformation of public administration. However, the practical effectiveness of such systems is determined not only by the quality of text generation, including grammatical correctness, coherence, and general awareness, but also by their ability to reliably retain context, retrieve previously acquired information, and reproduce procedural rules within long-term managerial processes. For public organizations, this aspect is particularly critical, as administrative activity relies on stable memory of regulatory requirements, organizational rules, facts of specific cases, and their chronological order.

Purpose. The purpose of the article is to determine the limits of applicability of agent systems based on large language models in public administration through a comparative analysis of human memory models and the memory architectures of such systems.

Methods. The study employs a comparative analytical approach. Basic cognitive models of human memory are examined, and their characteristics relevant to managerial activity are identified. Subsequently, architectural mechanisms of information storage and retrieval in agent systems based on large language models are analyzed as a functional analogue of human memory.

Results. The analysis demonstrates that agent systems reproduce certain external functions of human memory through a combination of short-term contextual representations and external knowledge repositories. At the same time, fundamental differences are identified, including the absence of autobiographical memory, experiential chronology, embedded responsibility mechanisms, and causal verification. These limitations increase the risk of contextual distortion and complicate the validation of generated outputs.

Conclusions. It is concluded that, at present, agent systems based on large language models cannot be used for autonomous decision-making in responsible administrative procedures. Nevertheless, they show significant potential as cognitive assistants for public servants, provided that mandatory human oversight is maintained and personal responsibility for decisions is preserved.

1. Kabanova E. E. Artificial intelligence in public administration: key issues and prospects of application // Russian Journal of Management. 2025. Vol. 13, No. 2, P. 1–14. (In Russ.). DOI: 10.29039/2500-1469-2025-13-2-1-14

2. Kirillovykh A. A. Digital State: Organizational and Legal Aspects. Moscow: Yurlitinform, 2022. 184 p. (In Russ.). ISBN 978-5-4396-2425-6.

3. Mikhalchenkova N. A. Artificial intelligence in the context of public administration // Power [Vlast’]. 2021. Vol. 29, No. 5. P. 122–127. (In Russ.). DOI: 10.31171/vlast.v29i5.8545

4. Troyan N. A. Artificial intelligence and its regulation in public administration: legal aspects // Monitoring of Law Enforcement [Monitoring pravoprimeneniya]. 2025. No. 3. P. 59–65. (In Russ.). EDN SNUECT

5. Fedorchenko S. N. Artificial intelligence in politics, the media space and public administration // Journal of Political Research [Zhurnal politicheskikh issledovanii]. 2020. Vol. 4, No. 2. P. 3–9. (In Russ.). URL: https://naukaru.ru/ru/nauka/article/38587/view

6. Fedorchenko S. N. Digital State and Artificial Intelligence in Public Administration: Monograph. Moscow: Yurait, 2021. 256 p. (In Russ.). DOI: 10.33910/2707-0144-2021-3-1-7

7. Chereshneva I. A. Artificial intelligence in public administration and transparency: European experience. // Public Administration [Gosudarstvennaya sluzhba]. 2022. No. 2 (136). P. 80–87. (In Russ.). DOI: 10.22394/2070-8378-2022-24-2-80-87

8. Atkinson R. C., Shiffrin R. M. Human memory: A proposed system and its control processes. In K. W. Spence & J. T. Spence (Eds.), The Psychology of Learning and Motivation (Vol. 2, pp. 89–195). New York: Academic Press, 1968. DOI: 10.1016/S0079-7421(08)60422-3

9. Bartlett F. C. Remembering: A Study in Experimental and Social Psychology. Cambridge: Cambridge University Press, 1932. 317 p. URL: https://archive.org/details/rememberingstudy0000bart_u8n7

10. Bender E. M., Gebru T., McMillan-Major A., Shmitchell S. On the Dangers of Stochastic Parrots: Can Language Models Be Too Big? // Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (FAccT). New York, NY, USA: ACM, 2021. P. 610–623. DOI: 10.1145/3442188.3445922

11. Bommasani R., Hudson D. A., Adeli E., et al. On the Opportunities and Risks of Foundation Models. Stanford, CA, USA: Stanford Center for Research on Foundation Models (CRFM), Stanford University, 2021. 212 p. URL: https://arxiv.org/abs/2108.07258

12. Brown T. B., Mann B., Ryder N., et al. Language Models are Few-Shot Learners // Advances in Neural Information Processing Systems (NeurIPS). Red Hook, NY, USA: Curran Associates, Inc., 2020. Vol. 33. P. 1877–1901. URL: https://arxiv.org/abs/2005.14165

13. Burgess N. The hippocampus, space and viewpoints in episodic memory // Quarterly Journal of Experimental Psychology A. 2002. 55 (4), P. 1057–1080. DOI: 10.1080/02724980244000224

14. Cajueiro D. O., Celestino V. R. R. A comprehensive review of Artificial Intelligence regulation: Weighing ethical principles and innovation // Journal of Economy and Technology. 2026. Vol. 4. P. 77–91. DOI: 10.1016/j.ject.2025.07.001

15. Conway M. A., Pleydell-Pearce C. W. The Construction of Autobiographical Memories // Psychological Review. 2000. Vol. 107, No. 2. P. 261–288. DOI: 10.1037/0033-295X.107.2.261

16. Jia Z., Liu Q., Li H., et al. Evaluating the Long-Term Memory of Large Language Models // Findings of the Association for Computational Linguistics (ACL). 2025. 18 p. URL: https://arxiv.org/abs/2402.03300

17. Lewis P., Perez E., Piktus A., et al. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks // Advances in Neural Information Processing Systems (NeurIPS). Red Hook, NY, USA: Curran Associates, Inc., 2020. Vol. 33. P. 9459–9474. URL: https://arxiv.org/abs/2005.11401

18. Loftus E. F. False Memories // American Psychologist. 1995. Vol. 50, No. 9. P. 720–725. DOI: 10.1037/0003-066X.50.9.720

19. Park J. S., O’Brien J., Cai C. J., Morris M. R., Liang P., Bernstein M. S. Generative Agents: Interactive Simulacra of Human Behavior // arXiv.org. 2023. 32 p. URL: https://arxiv.org/abs/2304.03442

20. Petroni F., Rocktäschel T., Riedel S., Lewis P., Bakhtin A., Wu Y., Miller A. Language Models as Knowledge Bases? // Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Hong Kong: Association for Computational Linguistics, 2019. P. 2463–2473. DOI: 10.18653/v1/D19-1250

21. Schacter D. L. The Seven Sins of Memory: Insights from Psychology and Cognitive Neuroscience // American Psychologist. 1999. Vol. 54, No. 3. P. 182–203. DOI: 10.1037/0003-066X.54.3.182

22. Squire L. R. Mechanisms of Memory // Science. 1986. Vol. 232, No. 4758. P. 1612–1619. DOI: 10.1126/science.3086978

23. Squire L. R., Zola S. M. Structure and Function of Declarative and Nondeclarative Memory Systems // Proceedings of the National Academy of Sciences of the United States of America. 1996. Vol. 93, No. 24. P. 13515–13522. DOI: 10.1073/pnas.93.24.13515

24. Tulving E. Elements of Episodic Memory. Oxford: Oxford University Press, 1983. 351 p. URL: https://archive.org/details/elementsofepisod0000tulv

25. Tulving E. Episodic and Semantic Memory // Organization of Memory / Eds. E. Tulving, W. Donaldson. New York: Academic Press, 1972. P. 381–403. DOI: 10.1016/B978-0-12-7020502.50008-4

26. Vaswani A., Shazeer N., Parmar N., et al. Attention Is All You Need // Advances in Neural Information Processing Systems (NeurIPS). Red Hook, NY, USA: Curran Associates, Inc., 2017. Vol. 30. P. 5998–6008. URL: https://arxiv.org/abs/1706.03762

27. Zhong W., Yu S., Wu C., et al. MemoryBank: Enhancing Large Language Models with Long-Term Memory // Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, CA, USA: AAAI Press, 2024. URL: https://arxiv.org/abs/2305.10260.