Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning

TL;DR

SPLIT-RAG introduces a question-driven, multi-agent framework that partitions knowledge graphs into semantically coherent subgraphs, significantly improving retrieval efficiency and reasoning accuracy in large-scale RAG systems.

Contribution

The paper proposes a novel semantic graph partitioning method and multi-agent retrieval framework that enhances efficiency and reasoning in large knowledge graphs for RAG systems.

Findings

Significant reduction in retrieval latency.

Improved accuracy on complex multi-hop questions.

Effective hierarchical merging for answer consistency.

Abstract

Retrieval-Augmented Generation (RAG) systems empower large language models (LLMs) with external knowledge, yet struggle with efficiency-accuracy trade-offs when scaling to large knowledge graphs. Existing approaches often rely on monolithic graph retrieval, incurring unnecessary latency for simple queries and fragmented reasoning for complex multi-hop questions. To address these challenges, this paper propose SPLIT-RAG, a multi-agent RAG framework that addresses these limitations with question-driven semantic graph partitioning and collaborative subgraph retrieval. The innovative framework first create Semantic Partitioning of Linked Information, then use the Type-Specialized knowledge base to achieve Multi-Agent RAG. The attribute-aware graph segmentation manages to divide knowledge graphs into semantically coherent subgraphs, ensuring subgraphs align with different query types, while lightweight LLM agents are assigned to partitioned subgraphs, and only relevant partitions are activated during retrieval, thus reduce search space while enhancing efficiency. Finally, a hierarchical merging module resolves inconsistencies across subgraph-derived answers through logical verifications. Extensive experimental validation demonstrates considerable improvements compared to existing approaches.