@article{howmuchcachedoesreasoningneeddepthcachet,
  title = {How Much Cache Does Reasoning Need? Depth-Cache Tradeoffs in KV-Compressed Transformers},
  author = {Xiao Wang},
  year = {2026},
  eprint = {2604.17935},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.17935},
}