SRLAgent: Enhancing Self-Regulated Learning Skills through Gamification and LLM Assistance
Wentao Ge, Yuqing Sun, Ziyan Wang, Haoyue Zheng, Weiyang He, Piaohong Wang, Qianyu Zhu, Benyou Wang
2025-06-17
Summary
This paper talks about SRLAgent, a new system that helps college students improve how they manage their own learning by combining game-like features with assistance from large language models (LLMs). The system encourages students to set learning goals and gives them real-time feedback using AI to keep them motivated and on track.
What's the problem?
The problem is that many students find it hard to organize and control their own learning process, like setting clear goals, staying motivated, and knowing if they are making progress. Without good support, students can struggle to learn efficiently and feel overwhelmed or distracted.
What's the solution?
The solution was to create SRLAgent, which uses gamification to make learning more fun and engaging, while large language models provide personalized help and feedback as students work toward their goals. This combination lets the system interact with students in real time, guiding them, encouraging better study habits, and helping them stay focused on their learning tasks.
Why it matters?
This matters because improving self-regulated learning skills helps students become more independent and successful learners, which is important for college and life after school. Using AI and gamification together makes learning easier and more enjoyable, which can lead to better academic performance and lifelong learning habits.
Abstract
A gamified LLM-assisted system, SRLAgent, significantly improves self-regulated learning skills in college students through interactive, goal-setting, and real-time AI feedback.