Complex information needs in real-world search scenarios demand deep reasoning and knowledge synthesis across diverse sources, which traditional retrieval-augmented generation (RAG) pipelines struggle to address effectively. Current reasoning-based approaches suffer from a fundamental limitation: they use a single model to handle both high-level planning and detailed execution, leading to inefficient reasoning and limited scalability. In this paper, we introduce HiRA, a hierarchical framework that separates strategic planning from specialized execution. Our approach decomposes complex search tasks into focused subtasks, assigns each subtask to domain-specific agents equipped with external tools and reasoning capabilities, and coordinates the results through a structured integration mechanism. This separation prevents execution details from disrupting high-level reasoning while enabling the system to leverage specialized expertise for different types of information processing. Experiments on four complex, cross-modal deep search benchmarks demonstrate that HiRA significantly outperforms state-of-the-art RAG and agent-based systems. Our results show improvements in both answer quality and system efficiency, highlighting the effectiveness of decoupled planning and execution for multi-step information seeking tasks. Our code is available atthis https URL.
View on arXiv@article{jin2025_2507.02652,
title={ Decoupled Planning and Execution: A Hierarchical Reasoning Framework for Deep Search },
author={ Jiajie Jin and Xiaoxi Li and Guanting Dong and Yuyao Zhang and Yutao Zhu and Yang Zhao and Hongjin Qian and Zhicheng Dou },
journal={arXiv preprint arXiv:2507.02652},
year={ 2025 }
}