REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving — Paper

Abstract

Retrieval-augmented generation (RAG) improves knowledge-intensive large language model (LLM) applications by conditioning generation on retrieved documents, but longer contexts increase latency, key-value (KV) cache memory, and token cost. Post-retrieval compression can reduce this cost, yet existing compressors often operate independently for each query, rely on auxiliary models or rewriting, and introduce online overhead that can offset the benefit of shorter prompts. We revisit RAG compression from a data-mining perspective by aggregating historical query--document--model interactions into reusable evidence views. We first show that modern compressors have unstable gains over simple truncation and can add substantial inference-time latency. We then propose Reusable Evidence View Aggregation (REVA), a framework that mines the target generator's historical attention traces into a document-keyed, budget-agnostic score store. REVA maps token-level attention to readable word units, aggregates importance across repeated document accesses, and renders budget-specific plain-text views that preserve document order and the standard RAG interface. Across four representative benchmarks and modern LLMs, REVA improves generation quality by 1.0--5.8 points over existing advances, while reducing compression overhead by a factor of 5.3 to 15.6, adding less than 40 ms of latency.

Authors 6

Tuan Nguyen, Qiran Hu, Banruo Liu, Khoa D. Doan, Kok-Seng Wong, Fan Lai

Specification

Official page: arxiv.org/abs/2609.11209
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh
Arxiv announce type: cross
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh
arXiv id: 2609.11209
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh
Categories: cs.LG, cs.CL, cs.IR
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh
PDF: arxiv.org/pdf/2609.11209
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh
Primary category: cs.LG
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 50 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

50 min ago

Conflicts

None

No models linked to this paper yet.

Authors: Tuan Nguyen, Qiran Hu, Banruo Liu

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · Authors

1 claims · 1 propertiesShow all properties

Authorsauthors1

Claim history for Authors
Value	Valid from → to	Status	Source	Confidence	Extractor
Tuan Nguyen, Qiran Hu, Banruo Liu, Khoa D. Doan, Kok-Seng Wong, Fan Lai	11 Sept 2026 21:02 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
Property changedPaperREVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving
REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving: arxiv announce type changed from new to cross
Arxiv announce typenew→crossarxiv
rss.arxiv.org
11 Sept 2026
New paperPaperREVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving
New paper: REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.CL	feed	T1· Official	50 min ago	1
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.LG	feed	T1· Official	50 min ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.