PlanGlow: Personalized Study Planning with an Explainable and Controllable LLM-Driven System

2025-04-16

AI Summary

Autonomous learners struggle to construct effective learning pathways, while existing LLM-based learning assistants suffer from poor explainability, low controllability, and hallucination risks. Method: We propose PlanGlow—the first LLM-driven learning planning system that deeply integrates controllability, explainability, and user-centered interaction. It employs fine-tuning and prompt engineering to optimize the underlying LLM, enabling users to iteratively co-design structured, personalized learning pathways with transparent decision rationales. Contribution/Results: Through a mixed-methods evaluation—including surveys, semi-structured interviews, within-subject experiments, and expert assessment using an educationally grounded framework—PlanGlow demonstrated statistically significant improvements in usability (+37%), explainability (+42%), and controllability (+39%) among 24 participants. Educational experts further validated that its generated learning plans meet pedagogical quality standards for real-world instructional practice.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Search and Optimization: Learning to Search
• Multiagent Systems: Multiagent Planning

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Personal development through self-directed learning is essential in today's fast-changing world, but many learners struggle to manage it effectively. While AI tools like large language models (LLMs) have the potential for personalized learning planning, they face issues such as transparency and hallucinated information. To address this, we propose PlanGlow, an LLM-based system that generates personalized, well-structured study plans with clear explanations and controllability through user-centered interactions. Through mixed methods, we surveyed 28 participants and interviewed 10 before development, followed by a within-subject experiment with 24 participants to evaluate PlanGlow's performance, usability, controllability, and explainability against two baseline systems: a GPT-4o-based system and Khan Academy's Khanmigo. Results demonstrate that PlanGlow significantly improves usability, explainability, and controllability. Additionally, two educational experts assessed and confirmed the quality of the generated study plans. These findings highlight PlanGlow's potential to enhance personalized learning and address key challenges in self-directed learning.

Problem

• Addressing transparency issues in AI-driven personalized learning plans
• Reducing hallucinated information in LLM-generated study plans
• Enhancing controllability and explainability in self-directed learning tools

Innovation

• LLM-based personalized study planning system
• User-centered controllable interactions
• Explainable AI for transparent learning plans