<?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">managementranepa</journal-id><journal-title-group><journal-title xml:lang="ru">Управленческое консультирование</journal-title><trans-title-group xml:lang="en"><trans-title>Administrative Consulting</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">1726-1139</issn><issn pub-type="epub">1816-8590</issn><publisher><publisher-name>Russian Presidential Academy of National Economy and Public Administration. North-West Institute of Management.</publisher-name></publisher></journal-meta><article-meta><article-id custom-type="edn" pub-id-type="custom">XKGYNH</article-id><article-id custom-type="elpub" pub-id-type="custom">managementranepa-2951</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>ГОСУДАРСТВЕННОЕ И МУНИЦИПАЛЬНОЕ УПРАВЛЕНИЕ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>STATE AND MUNICIPAL ADMINISTRATION</subject></subj-group></article-categories><title-group><article-title>Границы применимости ИИ в государственном управлении: Память LLM-агентов vs память человека</article-title><trans-title-group xml:lang="en"><trans-title>Limits of Applicability of Artificial Intelligence in Public Administration: Memory of LLM-Based Agents vs. Human Memory</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Вейбер</surname><given-names>Е. Н.</given-names></name><name name-style="western" xml:lang="en"><surname>Veiber</surname><given-names>E. N.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Вейбер Евгения Николаевна - младший научный сотрудник, Российская академия наук.</p><p>Санкт-Петербург</p></bio><bio xml:lang="en"><p>Evgeniya N. Veiber - Junior Researcher.</p><p>Saint Petersburg</p></bio><email xlink:type="simple">vejber2013@gmail.com</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Грудинин</surname><given-names>М. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Grudinin</surname><given-names>M. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Грудинин Михаил Артёмович - стажер-исследователь, Российская академия наук.</p><p>Санкт-Петербург</p></bio><bio xml:lang="en"><p>Mikhail A. Grudinin - Trainee researcher.</p><p>Saint Petersburg</p></bio><email xlink:type="simple">st119027@student.spbu.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Тулупьева</surname><given-names>Т. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Tulupyeva</surname><given-names>T. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Тулупьева Татьяна Валентиновна - кандидат психологических наук, доцент, Почетный работник сферы образования РФ, советник проректора по науке, Российская академия народного хозяйства и государственной службы при Президенте Российской Федерации; ведущий научный сотрудник, лаборатория Прикладного искусственного интеллекта, Российская академия наук, Санкт-Петербургский ФИЦ.</p><p>Москва</p></bio><bio xml:lang="en"><p>Tatiana V. Tulupyeva - PhD in Psychology, Associate Professor, Honorary Worker of the Russian Federation in the Sphere of Education, Advisor to the Vice-Rector for Research, Russian Presidential Academy of NEPA; Leading researcher at the Laboratory of Applied Artificial Intelligence at the St. Petersburg Federal Research Center of the RAS.</p><p>Moscow</p></bio><email xlink:type="simple">tvt@dscs.pro</email><xref ref-type="aff" rid="aff-2"/></contrib><contrib contrib-type="author" corresp="yes"><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Вяткин</surname><given-names>А. А.</given-names></name><name name-style="western" xml:lang="en"><surname>Vyatkin</surname><given-names>A. A.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Вяткин Артём Андреевич - младший научный сотрудник, Российская академия наук.</p><p>Санкт-Петербург</p></bio><bio xml:lang="en"><p>Artem A. Vyatkin - Junior Researcher.</p><p>Saint Petersburg</p></bio><email xlink:type="simple">aav@dscs.pro</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Российская академия наук, Санкт-Петербургский Федеральный исследовательский центр</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Russian Academy of Sciences, Saint Petersburg Federal Research Center</institution><country>Russian Federation</country></aff></aff-alternatives><aff-alternatives id="aff-2"><aff xml:lang="ru"><institution>Российская академия наук, Санкт-Петербургский Федеральный исследовательский центр; Российская академия народного хозяйства и государственной службы при Президенте Российской Федерации</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Russian Academy of Sciences, Saint Petersburg Federal Research Center; Russian Presidential Academy of National Economy and Public Administration</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2026</year></pub-date><pub-date pub-type="epub"><day>29</day><month>04</month><year>2026</year></pub-date><volume>0</volume><issue>2</issue><fpage>54</fpage><lpage>67</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Вейбер Е.Н., Грудинин М.А., Тулупьева Т.В., Вяткин А.А., 2026</copyright-statement><copyright-year>2026</copyright-year><copyright-holder xml:lang="ru">Вейбер Е.Н., Грудинин М.А., Тулупьева Т.В., Вяткин А.А.</copyright-holder><copyright-holder xml:lang="en">Veiber E.N., Grudinin M.A., Tulupyeva T.V., Vyatkin A.A.</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.acjournal.ru/jour/article/view/2951">https://www.acjournal.ru/jour/article/view/2951</self-uri><abstract><p>В последние годы большие языковые модели и агентные системы на их основе рассматриваются как перспективный инструмент цифровой трансформации государственного управления. Однако практическая эффективность таких систем определяется не только качеством текстовой генерации в узком смысле (грамматической корректностью, связностью и общей осведомленностью модели), но и тем, насколько надежно они удерживают контекст, извлекают ранее полученные сведения и воспроизводят процедурные правила в условиях длительных управленческих процессов. Для государственных организаций это, как правило, особенно критично: управленческая деятельность опирается на устойчивую память о нормативных требованиях, организационных регламентах, фактах конкретных дел и их хронологии.</p><sec><title>Цель</title><p>Цель. Целью статьи является определение границ применимости в государственном управлении агентных систем, основанных на больших языковых моделях, на основе сравнительного анализа моделей памяти человека и архитектур памяти таких агентных систем.</p></sec><sec><title>Методы</title><p>Методы. В исследовании используется сравнительно-аналитический подход.</p><p>Рассматриваются базовые когнитивные модели человеческой памяти и выделяются ее характеристики, значимые для управленческой деятельности. Далее анализируются архитектурные механизмы хранения и извлечения информации в агентных системах, функционирующих на основе больших языковых моделей, как их функциональная аналогия.</p></sec><sec><title>Результаты</title><p>Результаты. Установлено, что агентные системы воспроизводят внешние функции памяти человека за счет сочетания кратковременного контекста и внешних хранилищ знаний. Одновременно выявлены принципиальные расхождения, связанные с отсутствием автобиографичности, хронологии опыта, встроенных механизмов ответственности и причинно-следственной верификации. Эти ограничения повышают риск искажения контекста и затрудняют проверку сгенерированных утверждений.</p></sec><sec><title>Выводы</title><p>Выводы. Сделан вывод о том, что на сегодняшний день агентные системы, основанные на больших языковых моделях, не могут использоваться для автономного принятия решений в ответственных управленческих процедурах. Вместе с тем они обладают значительным потенциалом как когнитивные ассистенты государственных служащих при обязательном человеческом контроле и сохранении персональной ответственности.</p></sec></abstract><trans-abstract xml:lang="en"><p>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.</p><sec><title>Purpose</title><p>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.</p></sec><sec><title>Methods</title><p>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.</p></sec><sec><title>Results</title><p>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.</p></sec><sec><title>Conclusions</title><p>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.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>искусственный интеллект</kwd><kwd>агентные системы</kwd><kwd>контекст</kwd><kwd>знания</kwd><kwd>ответственность</kwd></kwd-group><kwd-group xml:lang="en"><kwd>artificial intelligence</kwd><kwd>agent systems</kwd><kwd>context</kwd><kwd>knowledge</kwd><kwd>responsibility</kwd></kwd-group><funding-group><funding-statement xml:lang="ru">Статья выполнена в рамках научно-исследовательской работы по государственному заданию СПб ФИЦ РАН Mol_Lab (молодежная_лаб) № FFZF-2024-0003</funding-statement><funding-statement xml:lang="en">The article was carried out as part of the research the state order of SPC RAS no. FFZF-2024-0003</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">Кабанова Е. Е. Искусственный интеллект в государственном управлении: ключевые проблемы и перспективы применения // Russian Journal of Management. 2025. Т. 13, № 2. С. 1–14. DOI: 10.29039/2500-1469-2025-13-2-1-14</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Кирилловых А. А. Цифровое государство (digital state): организационно-правовые аспекты. Москва : Юрлитинформ, 2022. 184 с. ISBN 978-5-4396-2425-6.</mixed-citation><mixed-citation xml:lang="en">Kirillovykh A. A. Digital State: Organizational and Legal Aspects. Moscow: Yurlitinform, 2022. 184 p. (In Russ.). ISBN 978-5-4396-2425-6.</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Михальченкова Н. А. Искусственный интеллект в контексте публичного управления // Власть. 2021. Т. 29, № 5. С. 122–127. DOI: 10.31171/vlast.v29i5.8545</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Троян Н. А. Искусственный интеллект и его регулирование в сфере государственного управления: правовые аспекты // Мониторинг правоприменения. 2025. № 3. С. 59–65. EDN SNUECT</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Федорченко С. Н. Искусственный интеллект в сфере политики, медиапространства и государственного управления // Журнал политических исследований. 2020. Т. 4, № 2. С. 3–9. URL: https://naukaru.ru/ru/nauka/article/38587/view</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Федорченко С. Н. Цифровое государство и искусственный интеллект в публичном управлении : монография. Москва : Юрайт, 2021. 256 с. DOI: 10.33910/2707-0144-2021-3-1-7</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Черешнева И. А. Искусственный интеллект в государственном управлении и транспарентность: европейский опыт // Государственная служба (Public Administration). 2022. № 2 (136). С. 80–87. DOI: 10.22394/2070-8378-2022-24-2-80-87</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Atkinson R. C., Shiffrin R. M. Human memory: A proposed system and its control processes. In K. W. Spence &amp; 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</mixed-citation><mixed-citation xml:lang="en">Atkinson R. C., Shiffrin R. M. Human memory: A proposed system and its control processes. In K. W. Spence &amp; 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</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Loftus E. F. False Memories // American Psychologist. 1995. Vol. 50, No. 9. P. 720–725. DOI: 10.1037/0003-066X.50.9.720</mixed-citation><mixed-citation xml:lang="en">Loftus E. F. False Memories // American Psychologist. 1995. Vol. 50, No. 9. P. 720–725. DOI: 10.1037/0003-066X.50.9.720</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit22"><label>22</label><citation-alternatives><mixed-citation xml:lang="ru">Squire L. R. Mechanisms of Memory // Science. 1986. Vol. 232, No. 4758. P. 1612–1619. DOI: 10.1126/science.3086978</mixed-citation><mixed-citation xml:lang="en">Squire L. R. Mechanisms of Memory // Science. 1986. Vol. 232, No. 4758. P. 1612–1619. DOI: 10.1126/science.3086978</mixed-citation></citation-alternatives></ref><ref id="cit23"><label>23</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit24"><label>24</label><citation-alternatives><mixed-citation xml:lang="ru">Tulving E. Elements of Episodic Memory. Oxford: Oxford University Press, 1983. 351 p. URL: https://archive.org/details/elementsofepisod0000tulv</mixed-citation><mixed-citation xml:lang="en">Tulving E. Elements of Episodic Memory. Oxford: Oxford University Press, 1983. 351 p. URL: https://archive.org/details/elementsofepisod0000tulv</mixed-citation></citation-alternatives></ref><ref id="cit25"><label>25</label><citation-alternatives><mixed-citation xml:lang="ru">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/B978-0-12-702050-2.50008-4</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit26"><label>26</label><citation-alternatives><mixed-citation xml:lang="ru">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</mixed-citation><mixed-citation xml:lang="en">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</mixed-citation></citation-alternatives></ref><ref id="cit27"><label>27</label><citation-alternatives><mixed-citation xml:lang="ru">Zhong W., Yu S., Wu C., et al. MemoryBank: Enhancing Large Language Models with LongTerm Memory // Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, CA, USA: AAAI Press, 2024. URL: https://arxiv.org/abs/2305.10260.</mixed-citation><mixed-citation xml:lang="en">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.</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>
