@inproceedings{sun-etal-2025-decouplesearch,
    title = "{D}ecouple{S}earch: Decouple Planning and Search via Hierarchical Reward Modeling",
    author = "Sun, Hao  and
      Qiao, Zile  and
      Wang, Bo  and
      Chen, Guoxin  and
      Hou, Yingyan  and
      Jiang, Yong  and
      Xie, Pengjun  and
      Huang, Fei  and
      Zhang, Yan",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.222/",
    pages = "4465--4478",
    ISBN = "979-8-89176-332-6",
    abstract = "Retrieval-Augmented Generation (RAG) systems have emerged as a pivotal methodology for enhancing Large Language Models (LLMs) through the dynamic integration of external knowledge. To further improve RAG{'}s flexibility, Agentic RAG introduces autonomous agents into the workflow. However, Agentic RAG faces several challenges:(1) the success of each step depends on both high-quality planning and accurate search,(2) the lack of supervision for intermediate reasoning steps, and(3) the exponentially large candidate space for planning and searching.To address these challenges, we propose DecoupleSearch, a novel framework that decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding. Our approach constructs a reasoning tree, where each node represents planning and search steps. We leverage Monte Carlo Tree Search to assess the quality of each step. During inference, Hierarchical Beam Search iteratively refines planning and search candidates with dual value models. Extensive experiments across policy models of varying parameter sizes, demonstrate the effectiveness of our method."
}