Search and Filter

Alignagent: Adaptive Learner Intelligence For Gap Identification And Next-Step Guidance

Date

AI Overview

Why it matters

Personalized learning systems remain fragmented across knowledge tracing, diagnostic modeling, and resource recommendation, rarely integrating them into a cohesive adaptive cycle that provides meaningful feedback before advancing to subsequent topics.

Study at a glance
  • Question: Can a multi-agent AI system accurately identify student skill gaps and recommend personalized learning resources?
  • Setting and data: Two undergraduate computer science courses at Florida Polytechnic University, Summer 2025, 25 total students.
  • Method: System development and model evaluation comparing predictions to instructor-graded exams.
  • AI tools: ALIGNAgent, GPT-4o, Claude 3.5 Sonnet, LLaMA 3, Llama 3.3
Key findings
  • A multi-agent system powered by GPT-4o achieved 0.87 to 0.90 precision and 0.84 to 0.87 F1 scores in estimating students' topic-level knowledge proficiency against actual exam performance.
  • GPT-4o outperformed Claude 3.5 Sonnet and LLaMA 3.3 across all metrics, showing a 7 to 12 percent advantage in recall.
  • For difficulty labeling of assessment questions, GPT-4o achieved the highest precision (0.81 and 0.88 across courses), aligning closely with instructor-assigned difficulty ratings.

Summary drafted with AI from the full paper and may contain errors. See the full paper for details.

Personalized learning systems have emerged as a promising approach to enhance student outcomes by tailoring educational content, pacing, and feedback to individual needs. However, most existing systems remain fragmented, specializing in either knowledge tracing, diagnostic modeling, or resource recommendation, but rarely integrating these components into a cohesive adaptive cycle. In this paper, we propose ALIGNAgent (Adaptive Learner Intelligence for Gap Identification and Next-step guidance), a multi-agent educational framework designed to deliver personalized learning through integrated knowledge estimation, skill-gap identification, and targeted resource recommendation.ALIGNAgent begins by processing student quiz performance, gradebook data, and learner preferences to generate topic-level proficiency estimates using a Skill Gap Agent that employs concept-level diagnostic reasoning to identify specific misconceptions and knowledge deficiencies. After identifying skill gaps, the Recommender Agent retrieves preference-aware learning materials aligned with diagnosed deficiencies, implementing a continuous feedback loop where interventions occur before advancing to subsequent topics. Extensive empirical evaluation on authentic datasets from two undergraduate computer science courses demonstrates ALIGNAgent's effectiveness, with GPT-4o-based agents achieving precision of 0.87-0.90 and F1 scores of 0.84-0.87 in knowledge proficiency estimation validated against actual exam performance.