根据查询复杂度动态分配计算资源，提升检索生成效率
SymRAG: Efficient Neuro-Symbolic Retrieval Through Adaptive Query Routing
- 通过实时评估查询难度与系统负载，自动选择符号、神经或混合路径
- 在两个数据集上保持97.6%~100%准确率，CPU利用率仅3.6%~6.2%
- 适合需要高效部署的复杂多跳推理场景，尤其适用于大模型应用
当前检索增强生成系统采用统一处理方式，导致简单查询也消耗与复杂多跳任务相当的资源。本文提出SymRAG框架，通过实时评估查询复杂度和系统负载，实现自适应查询路由，动态选择符号、神经或混合路径。该神经符号方法根据查询特征与系统状态调整计算路径，使资源分配与推理需求相匹配。在HotpotQA（多跳推理）和DROP（离散推理）数据集上，使用Llama-3.2-3B与Mistral-7B模型对2,000个查询进行评估，SymRAG达到97.6%~100.0%的精确匹配率，处理时间仅需0.985~3.165秒，CPU利用率低至3.6%~6.2%。关闭自适应路由后，处理时间增加169%~1151%，凸显其对复杂模型的重要性。结果表明，动态路由与自适应计算策略更有利于混合人工智能系统的可持续扩展。
原文摘要 · Abstract (English)
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.
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。