@article{modelcascadingforcodereducinginference, title = {Model Cascading for Code: A Cascaded Black-Box Multi-Model Framework for Cost-Efficient Code Completion with Self-Testing}, author = {Boyuan Chen and Mingzhi Zhu and Brendan Dolan-Gavitt and Muhammad Shafique and Siddharth Garg}, year = {2024}, eprint = {2405.15842}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2405.15842v2}, }