Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning
Published in Under Review, 2025
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, previous methods that extend reasoning with single-query search steps struggle to scale to complex tasks demanding broad document exploration. We propose HybridDeepSearcher that dynamically integrates parallel and sequential search strategies to enable effective search scaling. To support training, we introduce HDS-QA, a novel dataset that seamlessly integrates broad parallel search with sequential search reasoning. Across all five benchmarks, our approach significantly outperforms the state-of-the-art, improving F1 scores by +15.9 on FanOutQA and +11.5 on a subset of BrowseComp.
Recommended citation: Anonymous Authors. (2025). "Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning." ICLR 2026 Conference Submission.
Download Paper