SCOUT-RAG在分布式场景下高效实现跨域知识检索，减少调用次数和延迟。
SCOUT-RAG: Scalable and Cost-Efficient Unifying Traversal for Agentic Graph-RAG over Distributed Domains
- 四代理协同：评估领域相关性、决定是否拓展、自适应遍历深度、生成答案
- 相比集中式方法性能相当，跨域调用减少60%以上，总令牌处理量降低55%
- 适合医疗、跨国企业等数据分散且访问受限的场景使用
Graph-RAG通过结构化知识提升大模型推理能力，但传统设计依赖中心化知识图谱。在分布式且访问受限的场景（如医院或跨国组织）中，检索需在无全局图谱可见性的情况下选择相关领域与合适遍历深度。为此，我们提出SCOUT-RAG（可扩展且成本高效的统一遍历），一个分布式智能体式Graph-RAG框架，采用渐进式跨域检索，以增量效用目标为导向。该框架包含四个协作智能体：(i) 估计领域相关性，(ii) 决定是否扩展至新领域，(iii) 自适应调整遍历深度以避免冗余探索，(iv) 综合生成高质量答案。框架旨在最小化检索遗憾（即遗漏有用领域信息），同时控制延迟与API成本。在多领域知识设置下，SCOUT-RAG性能接近集中式基线（包括DRIFT与全域遍历），同时显著减少跨域调用、总处理令牌数及延迟。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。