{"ID":2878169,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.19113","arxiv_id":"2508.19113","title":"Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning","abstract":"Large reasoning models (LRMs) combined with retrieval-augmented generation (RAG) have enabled deep research agents capable of multi-step reasoning with external knowledge retrieval. However, we find that existing approaches rarely demonstrate test-time search scaling. Methods that extend reasoning through single-query sequential search suffer from limited evidence coverage, while approaches that generate multiple independent queries per step often lack structured aggregation, hindering deeper sequential reasoning. We propose a hybrid search strategy to address these limitations. We introduce HybridDeepSearcher, a structured search agent that integrates parallel query expansion with explicit evidence aggregation before advancing to deeper sequential reasoning. To supervise this behavior, we introduce HDS-QA, a novel dataset that guides models to combine broad parallel search with structured aggregation through supervised reasoning-query0retrieval trajectories containing parallel sub-queries. Across five benchmarks, HybridDeepSearcher significantly outperforms the state-of-the-art, improving F1 scores by +15.9 on FanOutQA and +9.2 on a subset of BrowseComp. Further analysis shows its consistent test-time search scaling: performance improves as additional search turns or calls are allowed, while competing methods plateau.","short_abstract":"Large reasoning models (LRMs) combined with retrieval-augmented generation (RAG) have enabled deep research agents capable of multi-step reasoning with external knowledge retrieval. However, we find that existing approaches rarely demonstrate test-time search scaling. Methods that extend reasoning through single-query...","url_abs":"https://arxiv.org/abs/2508.19113","url_pdf":"https://arxiv.org/pdf/2508.19113v3","authors":"[\"Dayoon Ko\",\"Jihyuk Kim\",\"Haeju Park\",\"Sohyeon Kim\",\"Dahyun Lee\",\"Yongrae Jo\",\"Gunhee Kim\",\"Moontae Lee\",\"Kyungjae Lee\"]","published":"2025-08-26T15:15:17Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"RAG\"]","has_code":false}