{"ID":23475077,"CreatedAt":"2026-09-18T01:09:05.407443952Z","UpdatedAt":"2026-09-20T18:11:56.143995915Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2609.19827","arxiv_id":"2609.19827","title":"F$^{2}$DR: A Fine-Grained Full-Pipeline Reward Framework for DeepSearch Workflows","abstract":"With the widespread industrial deployment of Large Language Models (LLMs), DeepSearch has emerged as the dominant paradigm for resolving complex user queries. It typically operates through an iterative closed-loop workflow consisting of planning and reflection, information retrieval, and answer generation. However, existing reward models (RMs) and evaluation benchmarks are primarily designed for static single-turn tasks, failing to capture the full-pipeline complexity of DeepSearch workflows. To address this limitation, we propose F2DR, a fine-grained full-pipeline DeepSearch reward framework. F2DR evaluates DeepSearch workflows across three dimensions: Content, Trajectory, and Answer, enabling comprehensive process-level assessment. We further construct DeepSearch RM-Bench, a dedicated benchmark for evaluating RMs in DeepSearch scenarios. Extensive experiments demonstrate that F2DR achieves significantly higher evaluation consistency than self-evaluation-based baselines, while DeepSearch RM-Bench exhibits strong discriminative capability across existing open-source RMs. We will publicly release the complete DeepSearch RM-Bench dataset soon.","short_abstract":"With the widespread industrial deployment of Large Language Models (LLMs), DeepSearch has emerged as the dominant paradigm for resolving complex user queries. It typically operates through an iterative closed-loop workflow consisting of planning and reflection, information retrieval, and answer generation. However, exi...","url_abs":"https://arxiv.org/abs/2609.19827","url_pdf":"https://arxiv.org/pdf/2609.19827v1","authors":"[\"Bojian Xiong\",\"Wentao Ding\",\"Yujing Lu\",\"Shaowei Zhang\",\"Ling Shi\",\"Jing Liao\",\"Yan Wang\",\"Yueyang Zhang\",\"Long Xia\",\"Zhiyuan Sun\",\"Daiting Shi\",\"Jingzhou He\",\"Yuqi Ren\",\"Deyi Xiong\"]","published":"2026-09-17T07:32:54Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}