Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning
cs.AI, cs.IR, cs.MA
Submitted: 2025-05-20
Updated: 2026-09-20
Comments: 18 pages, 4 figures
License: http://creativecommons.org/licenses/by/4.0/
The gist: 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.
Terminology
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.
Sources
- Retail-GPT: leveraging Retrieval Augmented Generation (RAG) for building E-commerce Chat Assistants
- S$^3$: Social-network Simulation System with Large Language Model-Empowered Agents
- Enabling Large Language Models to Generate Text with Citations
- Retrieval-Augmented Generation for Large Language Models: A Survey
- GPT in Game Theory Experiments
- GRAG: Graph Retrieval-Augmented Generation
- Inner Monologue: Embodied Reasoning through Planning with Language Models
- StructGPT: A General Framework for Large Language Model to Reason over Structured Data
- RAGAR, Your Falsehood Radar: RAG-Augmented Reasoning for Political Fact-Checking using Multimodal Large Language Models
- Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
- Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
- Graph-constrained Reasoning: Faithful Reasoning on Knowledge Graphs with Large Language Models
- Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback
- Key-Value Memory Networks for Directly Reading Documents
- Graph Retrieval-Augmented Generation: A Survey
- TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph
- PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
- Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
- Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
- The Web as a Knowledge-base for Answering Complex Questions
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection