Modern information retrieval (IR) is no longer consumed primarily by humans but increasingly by large language models (LLMs) via retrieval-augmented generation (RAG) and agentic search. Unlike human users, LLMs are constrained by limited attention budgets and are uniquely vulnerable to noise; misleading or irrelevant information is no longer just a nuisance, but a direct cause of hallucinations and reasoning failures. In this perspective paper, we argue that denoising-maximizing usable evidence density and verifiability within a context window-is becoming the primary bottleneck across the full information access pipeline. We conceptualize this paradigm shift through a four-stage framework of IR challenges: from inaccessible to undiscoverable, to misaligned, and finally to unverifiable. Furthermore, we provide a pipeline-organized taxonomy of signal-to-noise optimization techniques, spanning indexing, retrieval, context engineering, verification, and agentic workflow. We also present research works on information denoising in domains that rely heavily on retrieval such as lifelong assistant, coding agent, deep research, and multimodal understanding.

翻译：现代信息检索（IR）的消费主体已不再主要是人类，而越来越多地是通过检索增强生成（RAG）和智能体搜索（agentic search）服务于大语言模型（LLM）。与人类用户不同，LLM受限于有限的注意力预算，且对噪声具有独特的敏感性；误导性或无关的信息不再是单纯令人困扰的问题，而是直接导致幻觉和推理失败的原因。在本观点论文中，我们认为去噪——即在上下文窗口内最大化可用证据密度与可验证性——正成为贯穿整个信息获取流程的主要瓶颈。我们通过一个包含四阶段的信息检索挑战框架来概念化这一范式转变：从不可获取（inaccessible）到不可发现（undiscoverable），再到不匹配（misaligned），最终到不可验证（unverifiable）。此外，我们提供了一种基于流水线组织的信号-噪声优化技术分类法，涵盖索引、检索、上下文工程、验证与智能体工作流。我们还介绍了在高度依赖检索的领域（如终身助手、编码智能体、深度研究和多模态理解）中，关于信息去噪的研究工作。