Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning

TL;DR

HybridDeepSearcher introduces a structured hybrid search method combining parallel query expansion and explicit evidence aggregation, significantly enhancing reasoning capabilities and test-time search scaling in large reasoning models.

Contribution

It proposes a novel hybrid search strategy and a supervised dataset, HDS-QA, to improve reasoning depth and evidence coverage in large reasoning models.

Findings

Outperforms state-of-the-art on five benchmarks.

Achieves +15.9 F1 improvement on FanOutQA.

Demonstrates consistent performance gains with increased search steps.

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.