Leyline
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Leyline: KV Cache Directives for Agentic Inference
arXiv:2606.01065v1 Announce Type: new Abstract: Modern KV cache management assumes the chatbot workload: prompts arrive once and the cache grows append-only, so prefix caching and forward-only eviction are correct by construction. Agentic LLMs break this assumption. Their conversations evolve through policy-driven editing: failed tool calls are retried, stale outputs dropped, trajectories pivoted.