@article{categoryawaresemanticcachingforheterogen, title = {Category-Aware Semantic Caching for Heterogeneous LLM Workloads}, author = {Chen Wang and Xunzhuo Liu and Yue Zhu and Alaa Youssef and Priya Nagpurkar and Huamin Chen}, year = {2025}, eprint = {2510.26835}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2510.26835}, }