LLM-Oriented Information Retrieval: A Denoising-First Perspective
For researchers and practitioners in RAG and agentic search, this paper reframes IR challenges around LLM vulnerabilities to noise, but it is a conceptual perspective without empirical results.
This perspective paper argues that denoising—maximizing usable evidence density and verifiability within a context window—is the primary bottleneck in LLM-oriented IR, and proposes a four-stage framework and taxonomy of signal-to-noise optimization techniques. No concrete numbers are provided.
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.