{"ID":2861309,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.14769","arxiv_id":"2511.14769","title":"Cluster-based Adaptive Retrieval: Dynamic Context Selection for RAG Applications","abstract":"Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by pulling in external material, document, code, manuals, from vast and ever-growing corpora, to effectively answer user queries. The effectiveness of RAG depends significantly on aligning the number of retrieved documents with query characteristics: narrowly focused queries typically require fewer, highly relevant documents, whereas broader or ambiguous queries benefit from retrieving more extensive supporting information. However, the common static top-k retrieval approach fails to adapt to this variability, resulting in either insufficient context from too few documents or redundant information from too many. Motivated by these challenges, we introduce Cluster-based Adaptive Retrieval (CAR), an algorithm that dynamically determines the optimal number of documents by analyzing the clustering patterns of ordered query-document similarity distances. CAR detects the transition point within similarity distances, where tightly clustered, highly relevant documents shift toward less pertinent candidates, establishing an adaptive cut-off that scales with query complexity. On Coinbase's CDP corpus and the public MultiHop-RAG benchmark, CAR consistently picks the optimal retrieval depth and achieves the highest TES score, outperforming every fixed top-k baseline. In downstream RAG evaluations, CAR cuts LLM token usage by 60%, trims end-to-end latency by 22%, and reduces hallucinations by 10% while fully preserving answer relevance. Since integrating CAR into Coinbase's virtual assistant, we've seen user engagement jump by 200%.","short_abstract":"Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by pulling in external material, document, code, manuals, from vast and ever-growing corpora, to effectively answer user queries. The effectiveness of RAG depends significantly on aligning the number of retrieved documents with query characteris...","url_abs":"https://arxiv.org/abs/2511.14769","url_pdf":"https://arxiv.org/pdf/2511.14769v1","authors":"[\"Yifan Xu\",\"Vipul Gupta\",\"Rohit Aggarwal\",\"Varsha Mahadevan\",\"Bhaskar Krishnamachari\"]","published":"2025-10-02T05:11:12Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\",\"cs.CL\",\"cs.LG\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}