Metraipolis › archive › dc_84aabda330b0

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents — arXiv:2609.11390

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11390
License (as archived)
CC0-1.0
Archived
2026-10-16T05:27:02.153Z
SHA-256 of the archived text
56cc37d600dfdc609e29c7a9cfb0664db73974c16d8e482653f826f060459293
Stable URL of this page
https://metraipolis.com/documento/dc_84aabda330b0

How to cite

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents — arXiv:2609.11390 — arXiv (en), https://arxiv.org/abs/2609.11390 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_84aabda330b0 (Metraipolis archive dc_84aabda330b0, sha256 56cc37d600dfdc609e29c7a9cfb0664db73974c16d8e482653f826f060459293)
BibTeX
@misc{dc84aabda330b0,
  title = {VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents — arXiv:2609.11390},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11390},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_84aabda330b0; sha256 56cc37d600dfdc609e29c7a9cfb0664db73974c16d8e482653f826f060459293},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11390. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI).
Categorie arXiv: Information Retrieval (cs.IR) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Databases (cs.DB); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.11390 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T05:17:52.159Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).