@article{agentmemorybelowthepromptpersistentq4kvc,
  title = {Agent Memory Below the Prompt: Persistent Q4 KV Cache for Multi-Agent LLM Inference on Edge Devices},
  author = {Yakov Pyotr Shkolnikov},
  year = {2026},
  eprint = {2603.04428},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.04428},
}