SymRAG: Efficient Neuro-Symbolic Retrieval Through Adaptive Query Routing

TL;DR

SymRAG introduces an adaptive query routing framework that dynamically selects symbolic, neural, or hybrid processing pathways based on query complexity and system load, significantly improving efficiency in neuro-symbolic retrieval systems.

Contribution

This paper presents SymRAG, a novel neuro-symbolic retrieval framework that employs real-time adaptive routing to optimize resource use and accuracy across diverse query types.

Findings

Achieves 97.6--100.0% exact match accuracy on benchmark datasets.

Reduces CPU utilization to 3.6--6.2%, significantly lowering resource consumption.

Disabling adaptive routing increases processing time by 169--1151%.

Abstract

Current Retrieval-Augmented Generation systems use uniform processing, causing inefficiency as simple queries consume resources similar to complex multi-hop tasks. We present SymRAG, a framework that introduces adaptive query routing via real-time complexity and load assessment to select symbolic, neural, or hybrid pathways. SymRAG's neuro-symbolic approach adjusts computational pathways based on both query characteristics and system load, enabling efficient resource allocation across diverse query types. By combining linguistic and structural query properties with system load metrics, SymRAG allocates resources proportional to reasoning requirements. Evaluated on 2,000 queries across HotpotQA (multi-hop reasoning) and DROP (discrete reasoning) using Llama-3.2-3B and Mistral-7B models, SymRAG achieves competitive accuracy (97.6--100.0% exact match) with efficient resource utilization (3.6--6.2% CPU utilization, 0.985--3.165s processing). Disabling adaptive routing increases processing time by 169--1151%, showing its significance for complex models. These results suggest adaptive computation strategies are more sustainable and scalable for hybrid AI systems that use dynamic routing and neuro-symbolic frameworks.