@article{agenerativecachingsystemforlarge, title = {A Generative Caching System for Large Language Models}, author = {Arun Iyengar and Ashish Kundu and Ramana Kompella and Sai Nandan Mamidi}, year = {2025}, eprint = {2503.17603}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2503.17603v1}, }