提出可训练的统一检索增强生成框架，支持单跳与多跳查询端到端处理。
Agent-UniRAG: A Trainable Open-Source LLM Agent Framework for Unified Retrieval-Augmented Generation Systems
- 设计分步决策的LLM代理框架，根据输入复杂度自动选择检索策略。
- 在多个基准测试中表现接近闭源大模型，小模型如Llama-3-8B亦有优异表现。
- 开源代码与合成数据集，适合研究者和开发者快速构建RAG系统。
本文提出一种基于大语言模型（LLM）代理的新方法，用于统一检索增强生成（RAG）系统。传统方法通常单独处理单跳或多跳查询，限制了在真实场景中的应用。为此，我们设计了可训练的Agent-UniRAG框架，能够根据输入复杂度分步解决任务，同时支持单跳与多跳查询的端到端处理。此外，我们构建了SynAgent-RAG合成数据集，使小型开源LLM（如Llama-3-8B）也能有效使用该框架。实验表明，在多个RAG基准上，其性能可媲美闭源大模型及更大规模的开源模型。相关代码与数据集已公开。
原文摘要 · Abstract (English)
This paper presents a novel approach for unified retrieval-augmented generation (RAG) systems using the recent emerging large language model (LLM) agent concept. Specifically, Agent LLM, which utilizes LLM as fundamental controllers, has become a promising approach to enable the interpretability of RAG tasks, especially for complex reasoning question-answering systems (e.g., multi-hop queries). Nonetheless, previous works mainly focus on solving RAG systems with either single-hop or multi-hop approaches separately, which limits the application of those approaches to real-world applications. In this study, we propose a trainable agent framework called Agent-UniRAG for unified retrieval-augmented LLM systems, which enhances the effectiveness and interpretability of RAG systems. The main idea is to design an LLM agent framework to solve RAG tasks step-by-step based on the complexity of the inputs, simultaneously including single-hop and multi-hop queries in an end-to-end manner. Furthermore, we introduce SynAgent-RAG, a synthetic dataset to enable the proposed agent framework for small open-source LLMs (e.g., Llama-3-8B). The results show comparable performances with closed-source and larger open-source LLMs across various RAG benchmarks. Our source code and dataset are publicly available for further exploitation.
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。