#natural language process...
Jun 2026
CacheWeaver: Cache-Aware Evidence Ordering for Efficient Grounded RAG Inference
CacheWeaver is presented, a lightweight prompt-layer method for cache-aware evidence ordering that keeps a prefix tree over recently served evidence sequences and uses a greedy walk to place the most reusable prefix first, while leaving the serving engine and retrieved evidence set unchanged.
Kai-Zhen Tan, Rong Gu, Mingyuan Li
· arXiv.org · 1 citation