Search-augmented large language models (LLMs) excel at knowledge-intensive tasks by integrating external retrieval.
However, they often over-search – unnecessarily invoking search tool even when it does not improve response quality,
which leads to computational inefficiency and hallucinations by incorporating irrelevant context. In this work, we conduct a
systematic evaluation of over-searching across multiple dimensions, including query types, model categories, retrieval
conditions, and multi-turn conversations. Our finding shows: (i) search generally improves answer accuracy on…
However, they often over-search – unnecessarily invoking search tool even when it does not improve response quality,
which leads to computational inefficiency and hallucinations by incorporating irrelevant context. In this work, we conduct a
systematic evaluation of over-searching across multiple dimensions, including query types, model categories, retrieval
conditions, and multi-turn conversations. Our finding shows: (i) search generally improves answer accuracy on…