A Hit Rate Is a Retention Policy: Prefix-Cache Reuse in Agentic Coding Traces Compounds the Workload With the Server's Eviction Rule and the Harness's Invalidations, Which Serving Assumptions the Traces Actually Break, and the Rent-or-Buy Rule That Prices the Turn Boundary

APA

Mahendrakar, P. (2026). A Hit Rate Is a Retention Policy: Prefix-Cache Reuse in Agentic Coding Traces Compounds the Workload With the Server's Eviction Rule and the Harness's Invalidations, Which Serving Assumptions the Traces Actually Break, and the Rent-or-Buy Rule That Prices the Turn Boundary [Preprint]. Life of Research. https://doi.org/10.5281/zenodo.23519028

Copy APA

BibTeX

@misc{lor1222026,
  title        = {A Hit Rate Is a Retention Policy: Prefix-Cache Reuse in Agentic Coding Traces Compounds the Workload With the Server's Eviction Rule and the Harness's Invalidations, Which Serving Assumptions the Traces Actually Break, and the Rent-or-Buy Rule That Prices the Turn Boundary},
  author       = {Pranay Mahendrakar},
  year         = {2026},
  publisher    = {Life of Research},
  doi          = {10.5281/zenodo.23519028},
  url          = {https://lifeofresearch.com/preprints/122},
  keywords     = {LLM serving, KV cache, prefix caching, coding agents, workload characterization, cache retention, ski rental, context compaction},
  note         = {LOR-00122}
}

Copy BibTeX More on the record page