发表机构
National University of Singapore; Georgetown University（新加坡国立大学; 乔治城大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文从IR视角指出RAG核心思想源于21世纪初的经典研究，提出将LLM视为旧QA架构的新接口层，其前期工作可指导下一代RAG设计，促进跨领域整合。
AI 中文摘要
检索增强生成（RAG）被广泛视为因大型语言模型（LLM）的局限性而诞生的新型范式，是将模型输出建立在外部知识基础上的机制。然而，从更广泛的历史背景来看，这一观点并不完整。本文认为，RAG的核心思想并非全新：整合检索与语言生成、知识增强、答案验证及迭代查询（或提示）优化等基础概念，早在21世纪初就已在信息检索（IR）和问答（QA）研究中得到研究与实现，远早于LLM的出现。我们通过系统追溯现代RAG与智能体RAG（Agentic RAG）的知识谱系，回溯其经典IR与QA前身，分析这种连续性未被认可的原因——包括领域碎片化、术语变迁以及快速发展领域特有的近因偏差。我们提出，不应将LLM视为检索增强智能的起源点，而应将其视为建立在数十年历史的QA架构之上的新接口层。这种重新定位不仅具有历史意义：通过将RAG置于IR研究的更长发展轨迹中，我们发掘出用户建模、答案验证和查询优化等未被充分利用的前期工作，这些工作可直接为下一代RAG设计提供参考，减少无意的重复研究，促进真正的跨领域整合。
英文摘要
Retrieval-Augmented Generation (RAG) is widely regarded as a novel paradigm born from the limitations of large language models (LLMs)--a mechanism to ground their outputs in external knowledge. This view, however, is incomplete when considered within a broader historical context. In this paper, we argue that the core ideas underlying RAG are not new: foundational concepts such as integrating retrieval and language generation, knowledge augmentation, answer verification, and iterative query (or prompt) refinement had already been studied and instantiated in information retrieval (IR) and question answering (QA) research dating back to the early 2000s, well before the emergence of LLMs. We make this case by systematically tracing the intellectual lineage of modern RAG and Agentic RAG back to their classical IR and QA antecedents, and examining why this continuity has gone under-recognized -- a consequence of community fragmentation, shifting terminology, and the recency bias endemic to fast-moving fields. Rather than treating LLMs as the origin point of retrieval-augmented intelligence, we propose viewing them as a new interface layer atop a decades-old QA architecture. This reframing is not merely historical: by situating RAG within the longer trajectory of IR research, we surface underutilized prior work -- on user modeling, answer validation, and query refinement -- that can directly inform next-generation RAG design, reducing unintentional rediscovery and fostering genuine cross-community integration.
