arXiv：cs.AI· Liangyu Chen, Youpeng Ma, Yulong Ye, Zezhen Xiang, Tao Chen·· 6 小时前
RAG 系统配置问题研究：654 个真实案例的症状、根因与修复
Configuring RAG Systems: What Breaks, Where Originates, and How to Fix
AI 导读
一项大规模实证研究分析了来自 10 个 RAG 系统的 654 个真实配置问题，首次给出 RAG 配置问题在症状、根因、相关阶段和修复模式上的完整分类。研究发现多数症状出现在流水线早期或晚期，而根因所在阶段未必与症状阶段相同，并为从业者提供了 9 条关于测试、定位和修复配置问题的可操作建议。
正文
Abstract:Retrieval-Augmented Generation (RAG) has emerged as a dominant paradigm for improving Large Language Model (LLM) by intertwining it with other components, such as a vector/graph database. Therefore, the resulting RAG systems are often highly configurable, under which a non-trivial amount of failures are related to the configurations. However, there remains a lack of systematic understanding regarding the configuration issues for RAG systems. To bridge this gap, in this paper, we conduct the first large-scale empirical study of 654 real-world configuration issues collected from 10 diverse RAG systems. Drawing on this, we provide a complete categorization of the symptoms, root causes, relevant stages, and fix patterns of configuration issues for RAG systems, as well as several new observations. Our findings not only reveal the characteristics of configuration issues, but also strongly link them to the unique pipeline stages of RAG, e.g., we found that most symptoms can be observed at the early or late stage, while the stage of the root cause might not be at the same stage as where the symptom is identified. We also provide nine actionable insights to the practitioners on testing, localizing, and fixing the configuration issues for RAG systems.
| Comments: | 28 pages, 7 figures |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.18567 [cs.AI] |
| (or arXiv:2610.18567v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.18567 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Liangyu Chen [view email]
[v1]
Tue, 13 Oct 2026 15:37:27 UTC (361 KB)
来源：arXiv：cs.AI · arxiv.org