cs.CYMay 2, 2026

AI-Integrated Learning Management System for Middle School: A Longitudinal Study of Learning Outcomes Through High School and Beyond

Authors: Misan Paul Etchie, Taiwo Olutosin

Organizations: Northern Arizona University, Flagstaff, AZ, USA

Abstract

Middle school is a key window for building core academic skills and the learning routines students carry into later grades, yet many students still fall behind because help is often limited and comes too late, after they have already been stuck for a while. Learning Management Systems (LMSs) are now standard infrastructure for distributing materials, collecting work, assessing students' tasks, and recording grades, but in most deployments they still behave more like workflow tools than instructional supports. The result is the usual bottleneck: students keep practicing through confusion, teachers triage questions, and feedback that could have corrected the misunderstanding arrives after the misconception has already hardened. To address this gap, we propose an AI-integrated LMS for middle school instruction, paired with a longitudinal study design to test whether sustained, bounded AI support changes outcomes through high school and into post-high school pathways. The proposed platform adds policy-gated AI assistance to everyday coursework, delivering formative feedback and hinting, recommending spaced review and adaptive practice based on mastery, and providing teacher-facing dashboards that summarize misconception patterns and flag sustained struggle. Because the platform is intended for minors, the design is privacy-first, using data minimization, role-based access control, age-appropriate response constraints, and auditable logs of AI interactions. Beyond short-term performance, the evaluation plan links fine-grained learning traces (attempts, revisions, help-seeking, and pacing) to institutional outcomes where feasible, so we can separate tool adoption effects from longer-run changes in learning trajectories.

Explore similar work

CardsList
May 26, 2026cs.CL

Towards Just-in-Time Adaptive Feedback: Enhancing Student Learning via Knowledge-Grounded LLM

Educational interventions are effective tools for enhancing student learning. While Large Language Models (LLMs) allow for generating adaptive feedback at scale, current studies lack clear methodologies for providing Just-in-Time (JiT) feedback in authentic instructional settings. In this paper, we present a framework that provides adaptive feedback by grounding LLMs with domain-specific expert knowledge. Our approach collects written reasoning logic (strategy essays) from students, analyzes potential error types based on the content of that reasoning, and delivers non-intrusive feedback designed to clarify missing or incorrect concepts. We deploy this framework in a large-scale university course (N > 1000), where it improved student performance by over 80% compared to previous semesters. Lastly, we validate the framework's pedagogical utility by analyzing the learning trajectories; we demonstrate how iterative conversations with LLM facilitate shifting one's misconception to correct understanding.
Younghun Lee, Amir Bralin, Nobel Sanjay Rebello +1
Adaptive TestingFeedback LearningStudent
AskPDF
May 28, 2026cs.AI

Surfacing Isolated Learners with Outcome-Independent Mediation of Feedback between Teachers and Students Using AI

AI-augmented classrooms generate rich teacher and student feedback before graded outcomes become available, yet these signals can be difficult to translate into timely instructional decisions. We propose an interpretable decision layer: a transparent mechanism that ranks course topics requiring attention without using grades or post-hoc outcome labels. The approach combines three signals: student learning difficulty prevalence, disagreement between learner self-reports and observed difficulties, and unresolved teacher concerns. The output is a ranked set of topic priorities with per-topic decision records explaining each ranking. In one graduate CS course offering (n=5n=5 instructor interviews; n=279n=279 survey responses), prioritized topics aligned with instructor concerns (top-5 overlap 3/5; Spearman ρ=0.80ρ=0.80) and student-reported topic difficulty (ρ=0.46ρ=0.46, p=.048p=.048). Multi-signal integration also surfaced learners not identified through individual signal sources alone (AUC =0.96=0.96 vs. 0.910.91 for gap prevalence alone). Reflective thinking, help-seeking, and self-efficacy provided additional evidence that student behavioral signals align with learning-related constructs. While preliminary, these findings suggest that transparent coordination mechanisms may help support human-AI co-agency when feedback is incomplete.
Junsoo Park, Youssef Medhat, Htet Phyo Wai +2
LearnersFeedback LearningTeacherDecisionsCausal Mediation AnalysisRanking
AskPDF
Feb 14, 2026cs.CY

Arapai: An Offline-First LLM Architecture for Adaptive Learning in Low-Connectivity Environments

Artificial intelligence and large language models (LLMs) are transforming educational technology by enabling conversational tutoring, personalised explanations, and inquiry-driven learning. However, most AI-based learning systems rely on continuous internet connectivity and cloud-based computation, limiting their use in bandwidth-constrained environments. This paper presents Arapai, an offline-first large language model architecture designed for AI-assisted learning in low-connectivity settings. The system performs all inference locally using quantized language models and incorporates hardware-aware model selection to enable deployment on low-specification, CPU-only devices. By removing dependence on cloud infrastructure, the system provides curriculum-aligned explanations and structured academic support through natural-language interaction. To support learners at different educational stages, the system includes adaptive response levels that generate explanations at varying levels of complexity: Simple English, Lower Secondary, Upper Secondary, and Technical. The system was evaluated with 120 students and 9 instructors from secondary and tertiary institutions under limited-connectivity conditions. Results indicate stable operation on legacy hardware, acceptable response times of 1-3 seconds for typical queries, and positive user perceptions of its effectiveness in supporting self-directed learning.
Joseph Walusimbi, Ann Move Oguti, Joshua Benjamin Ssentongo +1
Online LearningArtificial Intelligence InfrastructureAdaptive LearningCurriculumAcademic Integrity
AskPDF