mlsanityData to 7 Oct 2026

FinCacheServe: Dependency-Consistent Answer Reuse for Cost-Efficient RAG Serving over Mutable Enterprise Documents

arXiv 2607.26076 ↗First posted 14 Jul 2026cs.IR cs.AIcited by 0

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Retrieval-augmented generation services over mutable enterprise documents repeatedly execute semantically equivalent analysis requests. Answer reuse can remove GPU-bound generation work, yet response caches require dependency consistency when filings, evidence chunks, and tool outputs change. FinCacheServe treats each generated answer as a serving object indexed by enterprise intent and guarded by document versions, evidence fingerprints, tool fingerprints, model identity, and decoding configuration. A vLLM implementation evaluates SEC-derived financial-document workloads with Qwen2.5 models. On a 2,230-request hosted 7B trace, FinCacheServe skips 53.27% of LLM calls with zero observed dependency-stale outputs. Across three hosted 32B operator-suite seeds, it skips 53.31% of 544 requests, compared with 38.97% for versioned semantic caching and 22.43% for grounded-style reuse. Capacity, backend, and SLO replays show oracle-bounded cache management, 100k-entry transactional metadata behavior, and 44.30% lower estimated Wh per dependency-fresh 2s-SLO success than versioned semantic caching.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 9 of its 22 references that are in the map. First posted on arXiv 14 Jul 2026.

Builds on

9 of 22 references.

Closest ancestors · 1

Same direction, newest first

  1. 2026Grounded Cache Routing for Retrieval-Augmented Generation: When Is It Safe to Reuse an Answer?26 May

Other references · 8

  1. 2017Billion-scale similarity search with GPUscited by 2,477
  2. 2021FinQA: A Dataset of Numerical Reasoning over Financial Datacited by 552
  3. 2023FinanceBench: A New Benchmark for Financial Question Answeringcited by 261
  4. 2024CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusioncited by 211
  5. 2025Semantic Caching for Low-Cost LLM Serving: From Offline Learning to Online Adaptationcited by 12
  6. 2025ContextPilot: Fast Long-Context Inference via Context Reusecited by 8
  7. 2025AdaptCache: KV Cache Native Storage Hierarchy for Low-Delay and High-Quality Language Model Servingcited by 4
  8. 2026Asynchronous Verified Semantic Caching for Tiered LLM Architecturescited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation
  2. 2026PCR: A Prefetch-Enhanced Cache Reuse System for Low-Latency RAG Serving
  3. 2026Request Order Matters: Cache-History Sensitivity in Selective KV-Cache Reuse for Rolling Agents
  4. 2026KVShareArena: KV-Cache Reuse Across Contexts and Model Checkpoints
  5. 2026Sparse Prefix Caching for Hybrid and Recurrent LLM Serving
  6. 2024Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks
  7. 2026From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation
  8. 2026Risk-Constrained Freshness-Aware Semantic Caching for Open-Web Retrieval-Augmented LLMs