{"ID":5438637,"CreatedAt":"2026-07-01T01:17:58.482524686Z","UpdatedAt":"2026-07-03T04:20:05.427450767Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31156","arxiv_id":"2606.31156","title":"One Retrieval to Cover Them All: Co-occurrence-Aware Knowledge Base Reorganization for Session-Level RAG","abstract":"RAG systems retrieve documents optimized for answering one query at a time. Yet enterprise users arrive with sessions, that is, coherent episodes of related questions that span semantically distant parts of the knowledge base. We show that a single retrieval call over a standard knowledge base covers only 41% of a user's session-level information need. To close this gap, we reorganize the KB offline using co-occurrence-aware clustering and expand retrieval candidates through cluster neighborhoods at query time. On WixQA (6,221 enterprise support articles), our method raises single-query session coverage to 58% (+17% absolute; 95% CI: [14.1, 20.4]), reduces retrieval calls to 70% coverage by 34%, and compresses the KB to 20% of its original size, all consistently across four embedding models and six functional domains. We argue that session-level coverage, not single-query recall, should be the primary metric for enterprise RAG evaluation.","short_abstract":"RAG systems retrieve documents optimized for answering one query at a time. Yet enterprise users arrive with sessions, that is, coherent episodes of related questions that span semantically distant parts of the knowledge base. We show that a single retrieval call over a standard knowledge base covers only 41% of a user...","url_abs":"https://arxiv.org/abs/2606.31156","url_pdf":"https://arxiv.org/pdf/2606.31156v1","authors":"[\"Shivam Ratnakar\",\"Yixuan Zhu\",\"Cecilia Cheng\",\"Chaya Vijayakumar\"]","published":"2026-06-30T05:35:10Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}