In an age of information overload, recommendation systems play an important role in providing personalized content to users. However, traditional recommendation systems often create filter bubbles, limiting the types of content users are exposed to. Based on the research presented in the article “Breaking the Filter Bubble: A Reinforcement Learning Framework for Controllable Recommender Systems”, this article proposes a new approach to further improve the controllability and diversity of recommendations. By using reinforcement learning techniques, the proposed framework aims to break the filter bubble by providing users with more diverse content recommendations while maintaining high recommendation accuracy. Extensive experiments on real-world datasets demonstrate the effectiveness of this approach in suppressing recommendation concentration and improving recommendation diversity. The results of this study contribute to the further development of controllable recommendation systems and provide insights into solving the filter bubble problem in recommendation systems.