<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="purkayastha-do-2026-dysas">
    <titleInfo>
        <title>DySAS: Dynamic State-Aware Student Simulation Beyond Static Personas</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Partha</namePart>
        <namePart type="given">Sarathi</namePart>
        <namePart type="family">Purkayastha</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Heejin</namePart>
        <namePart type="family">Do</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2026-10</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ehsan</namePart>
            <namePart type="family">Kamalloo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicolas</namePart>
            <namePart type="family">Gontier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nikolai</namePart>
            <namePart type="family">Rozanov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maryam</namePart>
            <namePart type="family">Hashemzadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Akhil</namePart>
            <namePart type="family">Arora</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Budapest, Hungary</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-485-9</identifier>
    </relatedItem>
    <abstract>Simulated students play a central role in training and evaluating AI tutor agents, yet most approaches rely on static personas or unconstrained generation and implicitly assume stationary behavior. Real student responses also depend on transient learner states such as affect, attention, and memory that evolve during interaction. We introduce DYSAS, a dynamic state-aware student-simulation framework with three tutoring-facing modules, Affect (A), Attention (T), and Memory (M). Their low, medium, and high levels form the discrete ATM27 state space. We operationalize this interface through Dynamic Learner States (DLS), a prefix-only representation inferred at each turn without future leakage and used to condition student generation. We evaluate static and dynamic variants on the Eedi benchmark across prompting, supervised fine-tuning, and preference optimization. No configuration wins every objective as each of correctness-state match, misconception behavior, social tone, lexical fidelity, and tutor-response compatibility favors different settings. We therefore present DYSAS as an audit mechanism within a multi-objective simulator-selection framework, not as a universally superior add-on.</abstract>
    <identifier type="citekey">purkayastha-do-2026-dysas</identifier>
    <location>
        <url>https://aclanthology.org/2026.realm-1.50/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>738</start>
            <end>763</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DySAS: Dynamic State-Aware Student Simulation Beyond Static Personas
%A Purkayastha, Partha Sarathi
%A Do, Heejin
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F purkayastha-do-2026-dysas
%X Simulated students play a central role in training and evaluating AI tutor agents, yet most approaches rely on static personas or unconstrained generation and implicitly assume stationary behavior. Real student responses also depend on transient learner states such as affect, attention, and memory that evolve during interaction. We introduce DYSAS, a dynamic state-aware student-simulation framework with three tutoring-facing modules, Affect (A), Attention (T), and Memory (M). Their low, medium, and high levels form the discrete ATM27 state space. We operationalize this interface through Dynamic Learner States (DLS), a prefix-only representation inferred at each turn without future leakage and used to condition student generation. We evaluate static and dynamic variants on the Eedi benchmark across prompting, supervised fine-tuning, and preference optimization. No configuration wins every objective as each of correctness-state match, misconception behavior, social tone, lexical fidelity, and tutor-response compatibility favors different settings. We therefore present DYSAS as an audit mechanism within a multi-objective simulator-selection framework, not as a universally superior add-on.
%U https://aclanthology.org/2026.realm-1.50/
%P 738-763

Markdown (Informal)

[DySAS: Dynamic State-Aware Student Simulation Beyond Static Personas](https://aclanthology.org/2026.realm-1.50/) (Purkayastha & Do, REALM 2026)

• DySAS: Dynamic State-Aware Student Simulation Beyond Static Personas (Purkayastha & Do, REALM 2026)

ACL

• Partha Sarathi Purkayastha and Heejin Do. 2026. DySAS: Dynamic State-Aware Student Simulation Beyond Static Personas. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 738–763, Budapest, Hungary. Association for Computational Linguistics.