SCOUT-RAG: Scalable and Cost-Efficient Unifying Traversal for Agentic Graph-RAG over Distributed Domains

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Li, Longkun, Zou, Yuanben, Wu, Jinghan, Wen, Yuqing, Li, Jing, Qian, Hangwei, Tsang, Ivor
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912890220445696
author Li, Longkun
Zou, Yuanben
Wu, Jinghan
Wen, Yuqing
Li, Jing
Qian, Hangwei
Tsang, Ivor
author_facet Li, Longkun
Zou, Yuanben
Wu, Jinghan
Wen, Yuqing
Li, Jing
Qian, Hangwei
Tsang, Ivor
contents Graph-RAG improves LLM reasoning using structured knowledge, yet conventional designs rely on a centralized knowledge graph. In distributed and access-restricted settings (e.g., hospitals or multinational organizations), retrieval must select relevant domains and appropriate traversal depth without global graph visibility or exhaustive querying. To address this challenge, we introduce \textbf{SCOUT-RAG} (\textit{\underline{S}calable and \underline{CO}st-efficient \underline{U}nifying \underline{T}raversal}), a distributed agentic Graph-RAG framework that performs progressive cross-domain retrieval guided by incremental utility goals. SCOUT-RAG employs four cooperative agents that: (i) estimate domain relevance, (ii) decide when to expand retrieval to additional domains, (iii) adapt traversal depth to avoid unnecessary graph exploration, and (iv) synthesize the high-quality answers. The framework is designed to minimize retrieval regret, defined as missing useful domain information, while controlling latency and API cost. Across multi-domain knowledge settings, SCOUT-RAG achieves performance comparable to centralized baselines, including DRIFT and exhaustive domain traversal, while substantially reducing cross-domain calls, total tokens processed, and latency.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08400
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SCOUT-RAG: Scalable and Cost-Efficient Unifying Traversal for Agentic Graph-RAG over Distributed Domains
Li, Longkun
Zou, Yuanben
Wu, Jinghan
Wen, Yuqing
Li, Jing
Qian, Hangwei
Tsang, Ivor
Artificial Intelligence
Graph-RAG improves LLM reasoning using structured knowledge, yet conventional designs rely on a centralized knowledge graph. In distributed and access-restricted settings (e.g., hospitals or multinational organizations), retrieval must select relevant domains and appropriate traversal depth without global graph visibility or exhaustive querying. To address this challenge, we introduce \textbf{SCOUT-RAG} (\textit{\underline{S}calable and \underline{CO}st-efficient \underline{U}nifying \underline{T}raversal}), a distributed agentic Graph-RAG framework that performs progressive cross-domain retrieval guided by incremental utility goals. SCOUT-RAG employs four cooperative agents that: (i) estimate domain relevance, (ii) decide when to expand retrieval to additional domains, (iii) adapt traversal depth to avoid unnecessary graph exploration, and (iv) synthesize the high-quality answers. The framework is designed to minimize retrieval regret, defined as missing useful domain information, while controlling latency and API cost. Across multi-domain knowledge settings, SCOUT-RAG achieves performance comparable to centralized baselines, including DRIFT and exhaustive domain traversal, while substantially reducing cross-domain calls, total tokens processed, and latency.
title SCOUT-RAG: Scalable and Cost-Efficient Unifying Traversal for Agentic Graph-RAG over Distributed Domains
topic Artificial Intelligence
url https://arxiv.org/abs/2602.08400