# Introduction The decline of AI system performance is a fundamental problem to improve efficiency and reliability. Temporal knowledge graph reasoning is crucial for future AI applications. # Knowledge Distillation Framework To overcome this obstacle, we propose a knowledge distillation framework specifically tailored for temporal knowledge graph reasoning. Our approach leverages large language models as teacher models to guide the distillation process, enabling effective transfer of both structural and temporal reasoning capabilities to lightweight student models. # Integration with Public Knowledge Our framework integrates public knowledge on a large scale with task-specific temporal information, enhancing the student model's ability to model temporal dynamics while maintaining a compact and efficient architecture. # Experimental Results Extensive experiments on multiple publicly available benchmark datasets demonstrate that our method consistently outperforms strong baselines, achieving a favorable trade-off between reasoning accuracy, computational efficiency, and practical deployability. # Conclusion Our knowledge distillation framework for temporal knowledge graph reasoning offers a significant step forward in creating more efficient and reliable AI systems. By integrating public knowledge, our approach enables the student model to improve its ability to model temporal dynamics while maintaining a compact and efficient architecture.