Making Evidence Actionable in Adaptive Learning Closing the Diagnostic Pedagogical Loop

TL;DR

This paper introduces a teacher-guided feedback system for adaptive learning that uses optimization techniques to improve intervention timing, diversity, and coverage, leading to more effective and equitable personalized education.

Contribution

It presents a novel optimization-based framework for converting diagnostic assessments into targeted microinterventions within adaptive learning systems, incorporating safeguards for coverage, diversity, and efficiency.

Findings

Gradient-based method reduces redundant coverage by 12 percentage points.

Full skill coverage achieved for nearly all students in simulations and real deployment.

Gradient-based approach offers more consistent difficulty alignment.

Abstract

Adaptive learning often diagnoses precisely yet intervenes weakly, producing help that is mistimed or misaligned. This study presents evidence supporting an instructor-governed feedback loop that converts concept-level assessment evidence into vetted microinterventions. The adaptive learning algorithm includes three safeguards: adequacy as a hard guarantee of gap closure, attention as a budgeted limit for time and redundancy, and diversity as protection against overfitting to a single resource. We formulate intervention assignment as a binary integer program with constraints for coverage, time, difficulty windows derived from ability estimates, prerequisites encoded by a concept matrix, and anti-redundancy with diversity. Greedy selection serves low-richness and tight-latency settings, gradient-based relaxation serves rich repositories, and a hybrid switches along a richness-latency frontier. In simulation and in an introductory physics deployment with 1204 students, both solvers achieved full skill coverage for nearly all learners within bounded watch time. The gradient-based method reduced redundant coverage by about 12 percentage points relative to greedy and produced more consistent difficulty alignment, while greedy delivered comparable adequacy at lower computational cost in resource-scarce environments. Slack variables localized missing content and guided targeted curation, sustaining sufficiency across student subgroups. The result is a tractable and auditable controller that closes the diagnostic pedagogical loop and enables equitable, load-aware personalization at the classroom scale.