SRLAgent: Enhancing Self-Regulated Learning Skills through Gamification and LLM Assistance

2025-06-11

AI Summary

To address low learning efficacy stemming from undergraduates’ weak self-regulated learning (SRL) abilities, this study develops an adaptive learning system grounded in Zimmerman’s three-phase SRL model, integrating gamification mechanisms with real-time large language model (LLM) support. Innovatively, the system embeds LLM-driven dynamic scaffolding within a closed-loop gamified SRL training framework, enabling synergistic delivery of personalized feedback, metacognitive prompts, and behavioral reinforcement. A controlled experiment demonstrates that the intervention group exhibits statistically significant improvement in SRL competence (p < .001, Cohen’s d = 0.234) and significantly higher engagement than the control group. This work provides the first systematic empirical validation of AI-augmented gamified interventions for fostering metacognitive development in undergraduate learners, offering a scalable, technology-mediated pathway for cultivating SRL capacity.

Technology Category

• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Machine Learning: Reinforcement Learning
• Multiagent Systems: Multiagent Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Self-regulated learning (SRL) is crucial for college students navigating increased academic demands and independence. Insufficient SRL skills can lead to disorganized study habits, low motivation, and poor time management, undermining learners ability to thrive in challenging environments. Through a formative study involving 59 college students, we identified key challenges students face in developing SRL skills, including difficulties with goal-setting, time management, and reflective learning. To address these challenges, we introduce SRLAgent, an LLM-assisted system that fosters SRL skills through gamification and adaptive support from large language models (LLMs). Grounded in Zimmermans three-phase SRL framework, SRLAgent enables students to engage in goal-setting, strategy execution, and self-reflection within an interactive game-based environment. The system offers real-time feedback and scaffolding powered by LLMs to support students independent study efforts. We evaluated SRLAgent using a between-subjects design, comparing it to a baseline system (SRL without Agent features) and a traditional multimedia learning condition. Results showed significant improvements in SRL skills within the SRLAgent group (p<.001, Cohens d = 0.234) and higher engagement compared to the baselines. This work highlights the value of embedding SRL scaffolding and real-time AI support within gamified environments, offering design implications for educational technologies that aim to promote deeper learning and metacognitive skill development.

Problem

• Addressing insufficient self-regulated learning skills in students
• Overcoming challenges in goal-setting and time management
• Enhancing engagement and learning through gamification and AI

Innovation

• LLM-assisted gamification for SRL skills
• Real-time feedback with AI scaffolding
• Interactive game-based learning environment