View in EDS PDF Full Text

Agentic RAG for Personalized Learning: Design of an AI-Powered Learning Agent Using Open-Source Small Language Models

Saved in:
Bibliographic Details
Title: Agentic RAG for Personalized Learning: Design of an AI-Powered Learning Agent Using Open-Source Small Language Models
Language: English
Authors: Shilpi Taneja, Siddhartha Sankar Biswas, Bhavya Alankar, Harleen Kaur
Source: Electronic Journal of e-Learning. 2025 23(4):69-80.
Availability: Academic Conferences Limited. Curtis Farm, Kidmore End, Nr Reading, RG4 9AY, UK. Tel: +44-1189-724148; Fax: +44-1189-724691; e-mail: info@academic-conferences.org; Web site: https://academic-publishing.org/index.php/ejel/index
Peer Reviewed: Y
Page Count: 12
Publication Date: 2025
Document Type: Journal Articles
Reports - Research
Descriptors: Artificial Intelligence, Natural Language Processing, Open Educational Resources, Individualized Instruction, Computer Assisted Instruction, Technology Uses in Education, Educational Technology, Learning Strategies, Multimedia Instruction, Multimedia Materials
ISSN: 1479-4403
Abstract: This paper presents the design of a personalized learning agent powered by the Agentic RAG technique. The agent can interpret learners' queries and autonomously decide which tools should be used to generate the most suitable response. When the learner shares an Open Educational Resource (OER) they wish to learn from, the agent first breaks the content into smaller, manageable chunks. These chunks are then indexed sequentially to preserve the natural flow of the text. At the same time, chunks are also converted into vector embeddings that allow semantic retrieval. Depending on the learner's request, different tools are selected by the agent. For example, when the learner requests learning aids like summaries, quizzes, or flashcards, the agent invokes the corresponding tool. This tool passes the sequentially indexed chunks to a small language model to generate the output. For context-specific queries, another specialized tool that relies on vector indexing and retrieval-augmented generation (RAG), is invoked. Visual question answering is handled by a separate tool that leverages multimodal RAG using a multimodal small language model. This agentic setup improves the accuracy and relevance of responses generated by the agent. To test its agentic behaviour, we probed our agent with a diverse set of questions drawn from four different OERs. We thoroughly examined each response and tracked the tools that got invoked autonomously. We also compared the similarity of summaries produced by our agent against those generated by ChatGPT (GPT-4o) using BERT Score as the evaluation metric. Our findings indicate that the agent consistently selected the appropriate tools and the summaries generated by our agent showed close semantic similarity to those produced by GPT-4o, suggesting that the proposed approach can provide performance reasonably close to a state-of-the-art model. The agent being lightweight resides on learner's local machine and avoid dependence on cloud-based AI ensuring the privacy of learner's data. It is affordable as it entirely relies on open source frameworks and small models. As the agent provides personalized support to learners by answering their context-based queries and providing on-demand learning aids, it improves their engagement with the educational content. This research shows that designing agentic AI tools using open-source software to address diverse learning needs is technically and economically feasible as well as educationally valuable.
Abstractor: As Provided
Entry Date: 2025
Accession Number: EJ1489068
Database: ERIC
FullText Links:
  – Type: pdflink
    Url: https://content.ebscohost.com/cds/retrieve?content=AQICAHj0k_4E0hTGH8RJwT4gCJyBsGNe_WN95AvKlDbXJGqwxwFjxCyBWq6J9DxPEc5OamERAAAA4jCB3wYJKoZIhvcNAQcGoIHRMIHOAgEAMIHIBgkqhkiG9w0BBwEwHgYJYIZIAWUDBAEuMBEEDJJz1mAnV1bZgA0-PgIBEICBmrHRjcuGY3GbY-kF-r05gozRSeBpn1k5oWeLjjJMoemn8i36mpFQoum7LWTXnaviWdMNqV9WgU79AclIe6u7vPCNoktQsKZEU2v0Ubp89HHvcUF8kyg_a-Job1T9ek_fKcyfvDHXUDo9COzSxesRPGSBeOsZPs2gV9ffJCpwV2e4BCLqutePMrLCxL02QjvCgms1QQ2FBa5NncE=
Text:
  Availability: 0
CustomLinks:
  – Url: https://eric.ed.gov/contentdelivery/servlet/ERICServlet?accno=EJ1489068
    Name: ERIC Full Text
    Category: fullText
    Text: Full Text from ERIC
Header DbId: eric
DbLabel: ERIC
An: EJ1489068
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Agentic RAG for Personalized Learning: Design of an AI-Powered Learning Agent Using Open-Source Small Language Models
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Shilpi+Taneja%22">Shilpi Taneja</searchLink><br /><searchLink fieldCode="AR" term="%22Siddhartha+Sankar+Biswas%22">Siddhartha Sankar Biswas</searchLink><br /><searchLink fieldCode="AR" term="%22Bhavya+Alankar%22">Bhavya Alankar</searchLink><br /><searchLink fieldCode="AR" term="%22Harleen+Kaur%22">Harleen Kaur</searchLink>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="SO" term="%22Electronic+Journal+of+e-Learning%22"><i>Electronic Journal of e-Learning</i></searchLink>. 2025 23(4):69-80.
– Name: Avail
  Label: Availability
  Group: Avail
  Data: Academic Conferences Limited. Curtis Farm, Kidmore End, Nr Reading, RG4 9AY, UK. Tel: +44-1189-724148; Fax: +44-1189-724691; e-mail: info@academic-conferences.org; Web site: https://academic-publishing.org/index.php/ejel/index
– Name: PeerReviewed
  Label: Peer Reviewed
  Group: SrcInfo
  Data: Y
– Name: Pages
  Label: Page Count
  Group: Src
  Data: 12
– Name: DatePubCY
  Label: Publication Date
  Group: Date
  Data: 2025
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: Journal Articles<br />Reports - Research
– Name: Subject
  Label: Descriptors
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Natural+Language+Processing%22">Natural Language Processing</searchLink><br /><searchLink fieldCode="DE" term="%22Open+Educational+Resources%22">Open Educational Resources</searchLink><br /><searchLink fieldCode="DE" term="%22Individualized+Instruction%22">Individualized Instruction</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+Assisted+Instruction%22">Computer Assisted Instruction</searchLink><br /><searchLink fieldCode="DE" term="%22Technology+Uses+in+Education%22">Technology Uses in Education</searchLink><br /><searchLink fieldCode="DE" term="%22Educational+Technology%22">Educational Technology</searchLink><br /><searchLink fieldCode="DE" term="%22Learning+Strategies%22">Learning Strategies</searchLink><br /><searchLink fieldCode="DE" term="%22Multimedia+Instruction%22">Multimedia Instruction</searchLink><br /><searchLink fieldCode="DE" term="%22Multimedia+Materials%22">Multimedia Materials</searchLink>
– Name: ISSN
  Label: ISSN
  Group: ISSN
  Data: 1479-4403
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This paper presents the design of a personalized learning agent powered by the Agentic RAG technique. The agent can interpret learners' queries and autonomously decide which tools should be used to generate the most suitable response. When the learner shares an Open Educational Resource (OER) they wish to learn from, the agent first breaks the content into smaller, manageable chunks. These chunks are then indexed sequentially to preserve the natural flow of the text. At the same time, chunks are also converted into vector embeddings that allow semantic retrieval. Depending on the learner's request, different tools are selected by the agent. For example, when the learner requests learning aids like summaries, quizzes, or flashcards, the agent invokes the corresponding tool. This tool passes the sequentially indexed chunks to a small language model to generate the output. For context-specific queries, another specialized tool that relies on vector indexing and retrieval-augmented generation (RAG), is invoked. Visual question answering is handled by a separate tool that leverages multimodal RAG using a multimodal small language model. This agentic setup improves the accuracy and relevance of responses generated by the agent. To test its agentic behaviour, we probed our agent with a diverse set of questions drawn from four different OERs. We thoroughly examined each response and tracked the tools that got invoked autonomously. We also compared the similarity of summaries produced by our agent against those generated by ChatGPT (GPT-4o) using BERT Score as the evaluation metric. Our findings indicate that the agent consistently selected the appropriate tools and the summaries generated by our agent showed close semantic similarity to those produced by GPT-4o, suggesting that the proposed approach can provide performance reasonably close to a state-of-the-art model. The agent being lightweight resides on learner's local machine and avoid dependence on cloud-based AI ensuring the privacy of learner's data. It is affordable as it entirely relies on open source frameworks and small models. As the agent provides personalized support to learners by answering their context-based queries and providing on-demand learning aids, it improves their engagement with the educational content. This research shows that designing agentic AI tools using open-source software to address diverse learning needs is technically and economically feasible as well as educationally valuable.
– Name: AbstractInfo
  Label: Abstractor
  Group: Ab
  Data: As Provided
– Name: DateEntry
  Label: Entry Date
  Group: Date
  Data: 2025
– Name: AN
  Label: Accession Number
  Group: ID
  Data: EJ1489068
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=eric&AN=EJ1489068
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 69
    Subjects:
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Natural Language Processing
        Type: general
      – SubjectFull: Open Educational Resources
        Type: general
      – SubjectFull: Individualized Instruction
        Type: general
      – SubjectFull: Computer Assisted Instruction
        Type: general
      – SubjectFull: Technology Uses in Education
        Type: general
      – SubjectFull: Educational Technology
        Type: general
      – SubjectFull: Learning Strategies
        Type: general
      – SubjectFull: Multimedia Instruction
        Type: general
      – SubjectFull: Multimedia Materials
        Type: general
    Titles:
      – TitleFull: Agentic RAG for Personalized Learning: Design of an AI-Powered Learning Agent Using Open-Source Small Language Models
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Shilpi Taneja
      – PersonEntity:
          Name:
            NameFull: Siddhartha Sankar Biswas
      – PersonEntity:
          Name:
            NameFull: Bhavya Alankar
      – PersonEntity:
          Name:
            NameFull: Harleen Kaur
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-electronic
              Value: 1479-4403
          Numbering:
            – Type: volume
              Value: 23
            – Type: issue
              Value: 4
          Titles:
            – TitleFull: Electronic Journal of e-Learning
              Type: main
ResultId 1