@article{towardsefficientmultillminference, title = {Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques}, author = {Adarsh Prasad Behera and Jaya Prakash Champati and Roberto Morabito and Sasu Tarkoma and James Gross}, year = {2025}, eprint = {2506.06579}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2506.06579v1}, }