Skip to content
AI Atlas
PaperActive

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents

arxiv.org/abs/2609.11390

quality89

Updated 2 h ago · first seen 11 Sept 2026

paper_01M294FQXNBV2WB4R7XBY4DTXM

Published
11 Sept 2026
T1 · 2 h ago
arXiv
2609.11390
T1 · 2 h ago
Category
cs.IR
T1 · 2 h ago

Abstract

State-of-the-art retrieval-augmented generation (RAG) methods exploit document structures to acquire sufficient evidence, but often incur substantial token costs. To reduce structural-context tokens without compromising high RAG accuracy, we present {\sf VikingRAG}, a directory-aware semantic data management system that tightly integrates semantic and structural access to support structural-context-efficient, evidence-gap-driven multi-round retrieval. To further reduce token overhead of multi-round interaction, we materialize agentic multi-round retrieval traces as experience edges, and reuse these edges for similar queries, avoiding repeated multi-round exploration. To additionally reduce token costs when agentic multi-round retrieval is unnecessary, we introduce an adaptive escalation strategy that answers from one-round experience-augmented retrieval when the evidence is sufficient, and invokes agentic multi-round retrieval only otherwise. Experiments on real datasets show that the base system {\sf VikingRAG} matches high accuracy of state-of-the-art methods while consuming only 11.6\%--51.9\% of their tokens. With retrieval-trace reuse and adaptive escalation, token costs drop to 5.1\%--32.5\% while maintaining competitive accuracy and practical document-storage performance, showing the utility of this work for emerging AI knowledge bases.

Authors 8

Peiyuan Gao, Gaoyuan Zhang, Haojie Qin, Yahui Sun, Qianyi Zhang, Yunhao Zhang, Zeyu Wang, Wei Lu

Specification

Official page

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Arxiv announce type
cross

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

arXiv id
2609.11390

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Categories
cs.IR, cs.AI, cs.CL, cs.DB, cs.LG

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

PDF

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Primary category
cs.IR

Source:arXiv (Atom API + RSS)T1observed 2 h agohigh

Published
11 Sept 2026

Source:arXiv (Atom API + RSS)T1observed 2 h 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

2 h ago

Conflicts

None