针对金融领域术语复杂问题，设计多智能体增强检索生成系统
Retrieval Augmented Generation (RAG) for Fintech: Agentic Design and Evaluation
- 用多个专用智能体分步处理查询重构、关键词分解和术语解析
- 在85组问答数据上，检索准确率与相关性优于传统RAG基线
- 适合需要高精度金融知识问答的智能客服或投研系统使用
检索增强生成（RAG）系统在金融科技等专业领域常受限于领域本体复杂、术语密集及缩写繁多，影响检索与合成效果。本文提出一种面向金融领域的多智能体RAG架构，通过模块化管道实现智能查询重写、基于关键词提取的迭代子查询分解、上下文感知的缩写解析以及基于交叉编码器的上下文重排序。我们在一个来自企业金融知识库的85组问题-答案-参考三元组数据集上评估该方法，结果表明，相较于标准RAG基线，该系统在检索精确率和相关性上均有提升，尽管延迟有所增加。研究显示，结构化的多智能体方法为复杂领域下的检索鲁棒性提供了有效路径。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems often face limitations in specialized domains such as fintech, where domain-specific ontologies, dense terminology, and acronyms complicate effective retrieval and synthesis. This paper introduces an agentic RAG architecture designed to address these challenges through a modular pipeline of specialized agents. The proposed system supports intelligent query reformulation, iterative sub-query decomposition guided by keyphrase extraction, contextual acronym resolution, and cross-encoder-based context re-ranking. We evaluate our approach against a standard RAG baseline using a curated dataset of 85 question--answer--reference triples derived from an enterprise fintech knowledge base. Experimental results demonstrate that the agentic RAG system outperforms the baseline in retrieval precision and relevance, albeit with increased latency. These findings suggest that structured, multi-agent methodologies offer a promising direction for enhancing retrieval robustness in complex, domain-specific settings.
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。