<?xml version="1.0" encoding="UTF-8"?>
<article article-type="research-article" dtd-version="1.3" xml:lang="ru" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:noNamespaceSchemaLocation="https://metafora.rcsi.science/xsd_files/journal3.xsd">
  <front>
    <journal-meta>
      <journal-id journal-id-type="publisher-id">moitvivt</journal-id>
      <journal-title-group>
        <journal-title xml:lang="ru">Моделирование, оптимизация и информационные технологии</journal-title>
        <trans-title-group xml:lang="en">
          <trans-title>Modeling, Optimization and Information Technology</trans-title>
        </trans-title-group>
      </journal-title-group>
      <issn pub-type="epub">2310-6018</issn>
      <publisher>
        <publisher-name>Издательство</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="doi">10.26102/2310-6018/2026.53.2.008</article-id>
      <article-id pub-id-type="custom" custom-type="elpub">2199</article-id>
      <title-group>
        <article-title xml:lang="ru">Агентный подход к интеллектуальному поиску в библиотечных системах</article-title>
        <trans-title-group xml:lang="en">
          <trans-title>Agent-based approach to intelligent search in library systems</trans-title>
        </trans-title-group>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0009-0002-1702-591X</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Рзянкин</surname>
              <given-names>Илья Сергеевич</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Rzyankin</surname>
              <given-names>Ilya Sergeevich</given-names>
            </name>
          </name-alternatives>
          <email>i-rzyankin@yandex.ru</email>
          <xref ref-type="aff">aff-1</xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0002-4383-2830</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Барышев</surname>
              <given-names>Руслан Александрович</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Baryshev</surname>
              <given-names>Ruslan Aleksandrovich</given-names>
            </name>
          </name-alternatives>
          <email>r_baryshev@bk.ru</email>
          <xref ref-type="aff">aff-2</xref>
        </contrib>
        <contrib contrib-type="author">
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Гучко</surname>
              <given-names>Алексей Андреевич</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Guchko</surname>
              <given-names>Aleksey Andreevich</given-names>
            </name>
          </name-alternatives>
          <email>against61@gmail.com</email>
          <xref ref-type="aff">aff-3</xref>
        </contrib>
      </contrib-group>
      <aff-alternatives id="aff-1">
        <aff xml:lang="ru">Сибирский федеральный университет</aff>
        <aff xml:lang="en">Siberian Federal University</aff>
      </aff-alternatives>
      <aff-alternatives id="aff-2">
        <aff xml:lang="ru">Сибирский федеральный университет</aff>
        <aff xml:lang="en">Siberian Federal University</aff>
      </aff-alternatives>
      <aff-alternatives id="aff-3">
        <aff xml:lang="ru">Независимый исследователь</aff>
        <aff xml:lang="en">Independent Researcher</aff>
      </aff-alternatives>
      <pub-date pub-type="epub">
        <day>01</day>
        <month>01</month>
        <year>2026</year>
      </pub-date>
      <volume>1</volume>
      <issue>1</issue>
      <elocation-id>10.26102/2310-6018/2026.53.2.008</elocation-id>
      <permissions>
        <copyright-statement>Copyright © Авторы, 2026</copyright-statement>
        <copyright-year>2026</copyright-year>
        <license license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/">
          <license-p>This work is licensed under a Creative Commons Attribution 4.0 International License</license-p>
        </license>
      </permissions>
      <self-uri xlink:href="https://moitvivt.ru/ru/journal/article?id=2199"/>
      <abstract xml:lang="ru">
        <p>В статье исследуется применение агентного подхода Retrieval-Augmented Generation (Agentic RAG) в задачах интеллектуального поиска по библиотечным фондам. Объектом исследования является архитектура Agentic RAG, объединяющая методы извлечения информации, агентное планирование и механизмы самооценки промежуточных результатов. Рассматриваемая проблема связана с ограничениями классического Retrieval-Augmented Generation при обработке сложных тематических и контекстных запросов в условиях семантически насыщенных библиотечных данных. В отличие от традиционного RAG, агентная архитектура позволяет итеративно уточнять стратегию поиска, адаптироваться к контексту запроса и пересматривать промежуточные результаты. Методология исследования основана на разработке программного прототипа Agentic RAG и его экспериментальном сравнении с классическим RAG на корпусе реальных данных университетской библиотеки, включающем библиографические метаданные, аннотации и фрагменты полных текстов. Для оценки эффективности использованы количественные метрики информационного поиска (Precision@k, Recall@k, MRR, nDCG) и экспертная оценка релевантности итоговых ответов. Результаты демонстрируют устойчивое превосходство Agentic RAG по показателям точности, полноты и качества ранжирования, особенно при обработке сложных запросов. При этом интерпретация выводов ограничена выбранным набором метрик и параметрами экспериментального корпуса. Практическая значимость заключается в возможности внедрения агентной архитектуры в библиотечно-информационные системы без радикальной перестройки инфраструктуры.</p>
      </abstract>
      <trans-abstract xml:lang="en">
        <p>The article explores the application of an agent-based Retrieval-Augmented Generation (Agentic RAG) approach to intelligent search tasks in library collections. The object of the study is the Agentic RAG architecture, which integrates information retrieval mechanisms with agent-based planning and self-evaluation of intermediate results. The addressed problem concerns the limitations of classical Retrieval-Augmented Generation in handling complex thematic and contextual queries within semantically rich library data environments. Unlike traditional RAG pipelines, the agent-based architecture enables iterative refinement of search strategies, adaptive decision-making, and reassessment of intermediate outcomes. The research methodology is based on the development of a software prototype implementing Agentic RAG and its experimental comparison with a classical RAG baseline using a real university library corpus comprising bibliographic metadata, annotations, and full-text fragments. The evaluation framework includes standard information retrieval metrics (Precision@k, Recall@k, MRR, nDCG) as well as expert-based assessment of answer relevance. The results demonstrate a consistent superiority of Agentic RAG in terms of retrieval accuracy, recall, and ranking quality, particularly for complex queries. However, the interpretation of findings is constrained by the selected evaluation metrics and the characteristics of the experimental corpus. The practical significance lies in the potential integration of agent-based architectures into library information systems without requiring substantial infrastructural changes.</p>
      </trans-abstract>
      <kwd-group xml:lang="ru">
        <kwd>агентный поиск</kwd>
        <kwd>Retrieval-Augmented Generation</kwd>
        <kwd>библиотечные информационные системы</kwd>
        <kwd>интеллектуальный поиск</kwd>
        <kwd>семантический поиск</kwd>
        <kwd>нейросетевые технологии</kwd>
        <kwd>агентные архитектуры</kwd>
      </kwd-group>
      <kwd-group xml:lang="en">
        <kwd>agent-based search</kwd>
        <kwd>Retrieval-Augmented Generation</kwd>
        <kwd>library information systems</kwd>
        <kwd>intelligent search</kwd>
        <kwd>semantic search</kwd>
        <kwd>neural network technologies</kwd>
        <kwd>agent architectures</kwd>
      </kwd-group>
      <funding-group>
        <funding-statement xml:lang="ru">Исследование выполнено без спонсорской поддержки.</funding-statement>
        <funding-statement xml:lang="en">The study was performed without external funding.</funding-statement>
      </funding-group>
    </article-meta>
  </front>
  <back>
    <ref-list>
      <title>References</title>
      <ref id="cit1">
        <label>1</label>
        <mixed-citation xml:lang="ru">Каптерев А.И., Тикунова И.П. Отражение библиотечной проблематики в региональных стратегиях цифровой трансформации субъектов РФ. Научные и технические библиотеки. 2025;(3):161–180. https://doi.org/10.33186/1027-3689-2025-3-161-180</mixed-citation>
      </ref>
      <ref id="cit2">
        <label>2</label>
        <mixed-citation xml:lang="ru">Тикунова И.П. Цифровизация как тренд библиотечного развития. Труды ГПНТБ СО РАН. 2021;(3):31–37. https://doi.org/10.20913/2618-7575-2021-3-31-37</mixed-citation>
      </ref>
      <ref id="cit3">
        <label>3</label>
        <mixed-citation xml:lang="ru">Bevara R.V.K., Lund B.D., Mannuru N.R., et al. Prospects of Retrieval Augmented Generation (RAG) for Academic Library Search and Retrieval. Information Technology and Libraries. 2025;44(2). https://doi.org/10.5860/ital.v44i2.17361</mixed-citation>
      </ref>
      <ref id="cit4">
        <label>4</label>
        <mixed-citation xml:lang="ru">Singh A., Ehtesham A., Kumar S., Khoei T.T. Agentic retrieval-augmented generation: A survey on agentic RAG. arXiv. URL: https://doi.org/10.48550/arXiv.2501.09136 [Accessed 16th November 2025].</mixed-citation>
      </ref>
      <ref id="cit5">
        <label>5</label>
        <mixed-citation xml:lang="ru">Lewis P., Perez E., Piktus A., et al. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv. URL: https://doi.org/10.48550/arXiv.2005.11401 [Accessed 16th November 2025].</mixed-citation>
      </ref>
      <ref id="cit6">
        <label>6</label>
        <mixed-citation xml:lang="ru">Gao Y., Xiong Y., Gao X., et al. Retrieval-augmented generation for large language models: A survey. arXiv. URL: https://doi.org/10.48550/arXiv.2312.10997 [Accessed 26th November 2025].</mixed-citation>
      </ref>
      <ref id="cit7">
        <label>7</label>
        <mixed-citation xml:lang="ru">Aytar A.Y., Kaya K., Kilic K. A Retrieval-Augmented Generation Framework for Academic Literature Navigation in Data Science. arXiv. URL: https://arxiv.org/html/2412.15404v1 [Accessed 26th November 2025].</mixed-citation>
      </ref>
      <ref id="cit8">
        <label>8</label>
        <mixed-citation xml:lang="ru">Barnett S., Kurniawan S., Thudumu S., Brannelly Z., Abdelrazek M. Seven Failure Points When Engineering a Retrieval Augmented Generation System. In: Proceedings of the IEEE/ACM 3rd International Conference on AI Engineering – Software Engineering for AI (CAIN '24), 14–15 April 2024, Lisbon, Portugal. New York: Association for Computing Machinery; 2024. P. 194–199. https://doi.org/10.1145/3644815.3644945</mixed-citation>
      </ref>
      <ref id="cit9">
        <label>9</label>
        <mixed-citation xml:lang="ru">Mazumder J., Mukhopadhyay P. Designing Question-Answer Based Search System in Libraries: Application of Open Source Retrieval Augmented Generation (RAG) Pipeline. Journal of Information and Knowledge. 2024;61(5):255–260. https://doi.org/10.17821/srels/2024/v61i5/171583</mixed-citation>
      </ref>
      <ref id="cit10">
        <label>10</label>
        <mixed-citation xml:lang="ru">Schneider F., Ahmadi N.B., Ahmadi N.B., et al. CollEX – A Multimodal Agentic RAG System Enabling Interactive Exploration of Scientific Collections. In: Proceedings of the 1st Workshop on Multimodal Augmented Generation via Multimodal Retrieval (MAGMaR 2025), 01 August 2025, Vienna, Austria. Association for Computational Linguistics; 2025. P. 18–39. https://doi.org/10.18653/v1/2025.magmar-1.2</mixed-citation>
      </ref>
      <ref id="cit11">
        <label>11</label>
        <mixed-citation xml:lang="ru">Nagori A., Casonatto R.A., Gautam A., Cheruvu A.M.S., Kamaleswaran R. Open-Source Agentic Hybrid RAG Framework for Scientific Literature Review. arXiv. URL: https://arxiv.org/abs/2508.05660 [Accessed 29th November 2025].</mixed-citation>
      </ref>
      <ref id="cit12">
        <label>12</label>
        <mixed-citation xml:lang="ru">Chu Zh., Wang Sh., Xie J., et al. LLM agents for education: Advances and applications. arXiv. URL: https://arxiv.org/abs/2503.11733 [Accessed 30th November 2025].</mixed-citation>
      </ref>
      <ref id="cit13">
        <label>13</label>
        <mixed-citation xml:lang="ru">Maheshwari H., Tenneti S., Nakkiran A. CiteFix: Enhancing RAG Accuracy Through Post-Processing Citation Correction. arXiv. URL: https://doi.org/10.48550/arXiv.2504.15629 [Accessed 21st November 2025].</mixed-citation>
      </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>