PAPPL: Personalized AI-Powered Progressive Learning Platform

Abstract: Engineering education has historically been constrained by rigid, standardized frameworks, often neglecting students' diverse learning needs and interests. While significant advancements have been made in online and personalized education within K-12 and foundational sciences, engineering education at both undergraduate and graduate levels continues to lag in adopting similar innovations. Traditional evaluation methods, such as exams and homework assignments, frequently overlook individual student requirements, impeding personalized educational experiences. To address these limitations, this paper introduces the Personalized AI-Powered Progressive Learning (PAPPL) platform, an advanced Intelligent Tutoring System (ITS) designed specifically for engineering education. It highlights the development of a scalable, data-driven tutoring environment leveraging cutting-edge AI technology to enhance personalized learning across diverse academic disciplines, particularly in STEM fields. PAPPL integrates core ITS components including the expert module, student module, tutor module, and user interface, and utilizes GPT-4o, a sophisticated LLM, to deliver context-sensitive and pedagogically sound hints based on students' interactions. The system uniquely records student attempts, detects recurring misconceptions, and generates progressively targeted feedback, providing personalized assistance that adapts dynamically to each student's learning profile. Additionally, PAPPL offers instructors detailed analytics, empowering evidence-based adjustments to teaching strategies. This study provides a fundamental framework for the progression of Generative ITSs scalable to all education levels, delivering important perspectives on personalized progressive learning and the wider possibilities of Generative AI in the field of education.

• The paper introduces PAPPL, an AI-powered platform that personalizes educational feedback to improve problem-solving efficiency in engineering.
• It employs a multi-module framework integrating GPT-4o for dynamic, context-aware adaptive learning strategies based on student performance.
• Experimental results demonstrate reduced attempts and question response time, alongside higher user satisfaction in pavement engineering.

PAPPL: Personalized AI-Powered Progressive Learning Platform

The paper "PAPPL: Personalized AI-Powered Progressive Learning Platform" (2508.14109) presents a novel educational technology designed to enhance engineering education by addressing its structural rigidity and lack of personalized learning experiences. PAPPL aims to overcome these constraints by utilizing advanced AI technologies to tailor educational feedback and thereby foster an adaptive learning environment.

Introduction and Objectives

The context of the study lies in the challenges faced by engineering education, which traditionally emphasizes standardized methods of evaluation that may not cater to individual learning needs. The paper underscores the limitation of traditional ITSs which often neglect dynamic feedback based on students' prior interactions. PAPPL is proposed as a solution to these challenges, highlighting its dual contributions: a multi-layered feedback core for personalized interaction and a versatile platform suitable for various subjects across all educational levels.

PAPPL Framework

The PAPPL platform is structured around a scalable and adaptive ITS, integrating cutting-edge AI technologies specifically LLMs like GPT-4o. This setup comprises several core components: the expert module encoding subject knowledge, the student module tracking educational progress, the tutor module constructing personalized instructional strategies, and the user interface facilitating human-computer interaction.

Figure 1

Figure 1: Component Design for PAPPL.

In PAPPL, the interactions are processed in the backend to ensure contextual relevance. The platform stores instructional content and learner-state data, analyzing students' responses to generate insightful, adaptive prompts. The effectiveness of GPT-4o is leveraged for delivering contextually relevant hints, fostering an interactive learning experience.

Experimental Study

The paper outlines an experimental study involving graduate students from UIUC and GWU. Participants were divided into two groups to evaluate PAPPL's impact on learning pavement engineering concepts—a topic they had no prior experience with. The PAPPL group's engagement with AI-driven feedback demonstrated improved problem-solving efficiency, corroborated by a higher success rate in identifying correct answers with fewer attempts.

Figure 2

Figure 2: Number of attempts made by each group during the case study.

Figure 3

Figure 3: Average time spent per question.

Observations from a detailed questionnaire highlighted the platform's effectiveness, engagement, adaptivity, and satisfaction. However, suggestions for improvement included enhancing prompt specificity and context sensitivity, particularly for complex question types.

Figure 4

Figure 4: Average user-experience scores across five dimensions (rescaled to a 10-point scale). Higher scores indicate a more positive user experience.

Implications for Future Research

PAPPL's integration of LLMs for generating adaptive educational feedback and personalized learning experiences is indicative of its potential to transform STEM education. However, several areas for improvement and exploration remain, including refining student profiling methodologies, advancing prompt engineering, enhancing accessibility, and conducting broader evaluations across diverse educational contexts.

Conclusion

In conclusion, the development and study of PAPPL represent significant progress toward more personalized and AI-driven educational platforms. This approach promises to deliver enriched learning experiences by dynamically adapting to individual student needs and facilitating a more effective educational process. Future research should focus on expanding the usability of the platform and further integrating advanced AI capabilities to maximize educational outcomes across various disciplines.