CoinRAG：面向长上下文 RAG 的信息碎片 KV cache 复用方法

View PDF HTML (experimental)

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. This paper optimizes the Pareto frontier under low prefill latency constraints while maximizing accuracy by proposing CoinRAG (Contextualized Information Nugget KV Cache Reuse for Long-Context RAG). The name metaphorically reflects our core mechanism: much like assembling small tokens (or "coins") to accumulate a larger value, CoinRAG compositionally reuses offline-computed, fine-grained nugget caches to form a learned contextual representation efficiently in a more semantically relevant but compact manner. Specifically, instead of full-chunk encoding, CoinRAG identifies query-relevant semantic units within retrieved chunks through two-stage retrieval and seamlessly assembles their sliced KV representations with a chunk-level context. CoinRAG can be integrated with CacheBlend's selective recomputation for further accuracy gains under the same latency budget. Extensive evaluations on LongBench multi-hop question answering tasks demonstrate that CoinRAG substantially shortens the active context and outperforms the other baselines with a new Pareto frontier and an average 5.3% relative improvement in answer quality (F1) under a standard fast prefill latency budget.

Subjects:	Computation and Language (cs.CL); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Machine Learning (cs.LG)
Cite as:	arXiv:2608.07458 [cs.CL]
	(or arXiv:2608.07458v2 [cs.CL] for this version)
	https://doi.org/10.48550/arXiv.2608.07458 arXiv-issued DOI via DataCite

Submission history

From: Gyuwan Kim [view email]
[v1] Fri, 7 Aug 2026 17:51:49 UTC (166 KB)
[v2] Fri, 23 Oct 2026 22:00:37 UTC (190 KB)