<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sanyal-etal-2025-investigating">
    <titleInfo>
        <title>Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval-Augmented Generation Across Learning Styles</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Debdeep</namePart>
        <namePart type="family">Sanyal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Agniva</namePart>
        <namePart type="family">Maiti</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Umakanta</namePart>
        <namePart type="family">Maharana</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Dhruv</namePart>
        <namePart type="family">Kumar</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ankur</namePart>
        <namePart type="family">Mali</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">C</namePart>
        <namePart type="given">Lee</namePart>
        <namePart type="family">Giles</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Murari</namePart>
        <namePart type="family">Mandal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Christos</namePart>
            <namePart type="family">Christodoulopoulos</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Tanmoy</namePart>
            <namePart type="family">Chakraborty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Carolyn</namePart>
            <namePart type="family">Rose</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Violet</namePart>
            <namePart type="family">Peng</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Suzhou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-332-6</identifier>
    </relatedItem>
    <abstract>Effective teaching necessitates adapting pedagogical strategies to the inherent diversity of students, encompassing variations in aptitude, learning styles, and personality, a critical challenge in education and teacher training. Large Language Models (LLMs) offer a powerful tool to simulate complex classroom dynamics, providing a controlled environment for exploring optimal teaching patterns. However, existing simulation frameworks often fall short by neglecting comprehensive student modeling beyond basic knowledge states and, more importantly, by lacking mechanisms for teachers to dynamically adapt their approach based on student feedback and collective performance. Addressing these limitations, we propose a simulation framework that integrates LLM-based diverse student agents with a self-evolving teacher agent. We use genetic algorithms to automatically tune and optimize the teacher’s pedagogical parameters based on simulated student performance, enabling the teacher agent to discover and refine teaching patterns tailored to specific class characteristics. Complementing this, we introduce Persona-RAG, a novel Retrieval-Augmented Generation method specifically designed for personalized knowledge retrieval in pedagogical contexts, allowing students to retrieve information as per their learning styles. We show how Persona-RAG remains competitive with standard RAG baselines in accurately retrieving relevant information while adding a touch of personalization for students. Crucially, we perform extensive experiments and highlight the different patterns learnt by the teacher agent while optimizing over classes with students of various learning styles. Our work presents a significant step towards creating adaptive educational technologies and improving teacher training through realistic, data-driven simulation.</abstract>
    <identifier type="citekey">sanyal-etal-2025-investigating</identifier>
    <location>
        <url>https://aclanthology.org/2025.emnlp-main.675/</url>
    </location>
    <part>
        <date>2025-11</date>
        <extent unit="page">
            <start>13359</start>
            <end>13400</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval-Augmented Generation Across Learning Styles
%A Sanyal, Debdeep
%A Maiti, Agniva
%A Maharana, Umakanta
%A Kumar, Dhruv
%A Mali, Ankur
%A Giles, C. Lee
%A Mandal, Murari
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F sanyal-etal-2025-investigating
%X Effective teaching necessitates adapting pedagogical strategies to the inherent diversity of students, encompassing variations in aptitude, learning styles, and personality, a critical challenge in education and teacher training. Large Language Models (LLMs) offer a powerful tool to simulate complex classroom dynamics, providing a controlled environment for exploring optimal teaching patterns. However, existing simulation frameworks often fall short by neglecting comprehensive student modeling beyond basic knowledge states and, more importantly, by lacking mechanisms for teachers to dynamically adapt their approach based on student feedback and collective performance. Addressing these limitations, we propose a simulation framework that integrates LLM-based diverse student agents with a self-evolving teacher agent. We use genetic algorithms to automatically tune and optimize the teacher’s pedagogical parameters based on simulated student performance, enabling the teacher agent to discover and refine teaching patterns tailored to specific class characteristics. Complementing this, we introduce Persona-RAG, a novel Retrieval-Augmented Generation method specifically designed for personalized knowledge retrieval in pedagogical contexts, allowing students to retrieve information as per their learning styles. We show how Persona-RAG remains competitive with standard RAG baselines in accurately retrieving relevant information while adding a touch of personalization for students. Crucially, we perform extensive experiments and highlight the different patterns learnt by the teacher agent while optimizing over classes with students of various learning styles. Our work presents a significant step towards creating adaptive educational technologies and improving teacher training through realistic, data-driven simulation.
%U https://aclanthology.org/2025.emnlp-main.675/
%P 13359-13400

Markdown (Informal)

[Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval-Augmented Generation Across Learning Styles](https://aclanthology.org/2025.emnlp-main.675/) (Sanyal et al., EMNLP 2025)

• Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval-Augmented Generation Across Learning Styles (Sanyal et al., EMNLP 2025)

ACL

• Debdeep Sanyal, Agniva Maiti, Umakanta Maharana, Dhruv Kumar, Ankur Mali, C. Lee Giles, and Murari Mandal. 2025. Investigating Pedagogical Teacher and Student LLM Agents: Genetic Adaptation Meets Retrieval-Augmented Generation Across Learning Styles. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 13359–13400, Suzhou, China. Association for Computational Linguistics.