{"ID":2898770,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.02652","arxiv_id":"2507.02652","title":"HiRA: A Hierarchical Reasoning Framework for Decoupled Planning and Execution in Deep Search","abstract":"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 at https://github.com/ignorejjj/HiRA.","short_abstract":"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 mode...","url_abs":"https://arxiv.org/abs/2507.02652","url_pdf":"https://arxiv.org/pdf/2507.02652v2","authors":"[\"Jiajie Jin\",\"Xiaoxi Li\",\"Guanting Dong\",\"Yuyao Zhang\",\"Yutao Zhu\",\"Yang Zhao\",\"Hongjin Qian\",\"Zhicheng Dou\"]","published":"2025-07-03T14:18:08Z","proceeding":"cs.AI","tasks":"[\"cs.AI\",\"cs.CL\",\"cs.IR\"]","methods":"[\"RAG\"]","has_code":false,"code_links":[{"ID":612430,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2898770,"paper_url":"https://arxiv.org/abs/2507.02652","paper_title":"HiRA: A Hierarchical Reasoning Framework for Decoupled Planning and Execution in Deep Search","repo_url":"https://github.com/ignorejjj/HiRA","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}