A Survey of Query Optimization in Large Language Models

arXiv:2412.17558v2 Announce Type: replace Abstract: Query Optimization (QO) has become essential for enhancing Large Language Model (LLM) effectiveness, particularly in Retrieval-Augmented Generation (RAG) systems where query quality directly determines retrieval and response performance. This survey provides a systematic analysis of query optimization techniques with three contributions. \textit{First}, we introduce the \textbf{Query Optimization Lifecycle (QOL) Framework}, a five-phase pipeline covering Intent Recognition, Query Transformation, Retrieval Execution, Evidence Integration, and Response Synthesis. \textit{Second}, we propose a \textbf{Query Complexity Taxonomy} that classifies queries along two dimensions: evidence type (explicit vs.\ implicit) and evidence quantity (single vs.\ multiple), establishing principled mappings to optimization strategies. \textit{Third}, we analyze four atomic operations: \textbf{Query Expansion}, \textbf{Query Decomposition}, \textbf{Query Disambiguation}, and \textbf{Query Abstraction}, covering over 90 representative methods. We further examine evaluation methodologies, identify gaps in benchmarks, and discuss open challenges including process reward models, efficiency optimization, and multi-modal query handling. This survey offers both a structured foundation for research and actionable guidance for practitioners.