@article{treaclethriftyreasoningviacontextaware, title = {Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning}, author = {Xuechen Zhang and Zijian Huang and Ege Onur Taga and Carlee Joe-Wong and Samet Oymak and Jiasi Chen}, year = {2024}, eprint = {2404.13082}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2404.13082v2}, }