# Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?

arXiv: https://arxiv.org/abs/2605.27494 · HTML: https://mlsanity.com/paper/2605.27494/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation.
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 26 May 2026.

## Placed in

- Retrieval-augmented generation / [Generation and context integration](https://mlsanity.com/rag/generation-and-context-integration/)

## Builds on (most cited first, 24 of 24)

- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [RAGTruth: A Hallucination Corpus for Developing Trustworthy Retrieval-Augmented Language Models](https://mlsanity.com/paper/2401.00396/) (2023)
- [ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2311.09476/) (2023)
- [RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentation](https://mlsanity.com/paper/2310.04408/) (2023)
- [CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion](https://mlsanity.com/paper/2405.16444/) (2024)
- [LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference](https://mlsanity.com/paper/2510.09665/) (2025)
- [RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2407.11005/) (2024)
- [RAGCache: Efficient Knowledge Caching for Retrieval-Augmented Generation](https://mlsanity.com/paper/2404.12457/) (2024)
- [TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text](https://mlsanity.com/paper/2410.07590/) (2024)
- [RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation](https://mlsanity.com/paper/2408.08067/) (2024)
- [MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2501.03468/) (2025)
- [EPIC: Efficient Position-Independent Caching for Serving Large Language Models](https://mlsanity.com/paper/2410.15332/) (2024)
- [Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks](https://mlsanity.com/paper/2412.15605/) (2024)
- [Provence: efficient and robust context pruning for retrieval-augmented generation](https://mlsanity.com/paper/2501.16214/) (2025)
- [PISCO: Pretty Simple Compression for Retrieval-Augmented Generation](https://mlsanity.com/paper/2501.16075/) (2025)
- [ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models](https://mlsanity.com/paper/2506.22791/) (2025)
- [From Similarity to Vulnerability: Key Collision Attack on LLM Semantic Caching](https://mlsanity.com/paper/2601.23088/) (2026)
- [Rethinking Soft Compression in Retrieval-Augmented Generation: A Query-Conditioned Selector Perspective](https://mlsanity.com/paper/2602.15856/) (2026)
- [PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving](https://mlsanity.com/paper/2603.23049/) (2026)
- [QVCache: A Query-Aware Vector Cache](https://mlsanity.com/paper/2602.02057/) (2026)

## Built on by (most cited first, 1 of 1)

- [FinCacheServe: Dependency-Consistent Answer Reuse for Cost-Efficient RAG Serving over Mutable Enterprise Documents](https://mlsanity.com/paper/2607.26076/) (2026)

## Abstract (arXiv)

Modern retrieval-augmented generation(RAG) deployments increasingly rely on caching to reduce token cost and time-to-first-token(TTFT). Prefix-level KV reuse is now standard in serving stacks such as vLLM, and chunk-level and position-independent reuse have been pushed further by recent systems(RAGCache, TurboRAG, CacheBlend, EPIC, ContextPilot, PCR, LMCache). Output-level semantic answer caches, by contrast, remain fragile: similar prompts can map to different correct answers, retrieved evidence drifts as the corpus is updated, and adversarial collision attacks have been shown to hijack cached responses. We argue that the right framing for cached answer reuse is not how to reuse faster but when reuse is safe. We propose GroundedCache, an evidence-validated cache router that admits a cached answer only when 4 cheap gates simultaneously hold: query similarity, retrieved-evidence overlap, source-version validity, and lexical (or judge-based) support of the cached answer by the freshly retrieved evidence. We build a six-regime workload that stress-tests cache safety rather than only hit rate, and introduce an operator-facing metric, the unsafe-served rate (USR), fraction of all queries that received a wrong cached answer. Across 2 datasets and 12,000 real-LLM generations(Qwen2.5-7B-Instruct on vLLM with Automatic Prefix Caching), GroundedCache drives USR to 0.0% on every HotpotQA regime(vs. 15-35% under naive caching) and to 1.5% on mtRAG document drift(vs. 51.5%), a 34x reduction on the design-point adversarial regime and 3-10x reductions across the other mtRAG regimes, while end-to-end p50 latency stays within 1.04-1.07x of a no-cache RAG baseline. A per-gate ablation isolates the lexical support gate as the load-bearing safety mechanism on both datasets, with the remaining gates providing defense-in-depth at near-zero cost. We release the implementation, workload, and evaluation harness.