CoinRAG: Contextualized Information Nugget KV Cache Reuse for Long-Context RAG
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. This paper optimizes the Pareto frontier under low prefill latency constraints while maximizing accuracy by proposing CoinRAG…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
