Query Reformulation

Query reformulation studies how to restate, expand, decompose, or clarify a question so search systems find useful evidence, especially in conversational search, retrieval-augmented generation, and agentic research. Approaches include language-model rewriting, multi-query generation, evidence-guided refinement, retriever-specific policies, and reinforcement learning, evaluated on benchmarks such as BEIR, conversational retrieval tasks, and multi-hop question answering. Rewriting can bridge vocabulary gaps and improve recall, but may also remove useful terms, drift from intent, or add cost; gains depend on the query, corpus, and retriever. Current work therefore explores adaptive selection, intent-preserving constraints, and feedback from retrieval or downstream answers, while the balance between broader coverage and faithful, efficient search remains open.