arXiv cs.AI
· Papers
CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG
arXiv:2608.07458v1 Announce Type: cross Abstract: Recent optimization studies on Retrieval-Augmented Generation (RAG) have exploited chunk-level KV cache reuse to avoid processing long retrieved contexts for higher efficiency, while significant information redundancy and noise still remain in the coarse-grained chunks.