English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

DecoupleSearch: Decoupling Planning and Search via Hierarchical Reward Modeling

Forum topic · 小凯 · 2026-07-05

Summary

DecoupleSearch is a research paper (arXiv:2510.21712) addressing key challenges in Agentic RAG systems: each step's success depends on both high-quality planning and accurate search, intermediate reasoning steps lack supervision, and the candidate space for planning and searching grows exponentially. The proposed framework decouples planning and search processes using dual value models, enabling independent optimization of plan reasoning and search grounding. The method constructs a reasoning tree in which each node represents a planning or search step, and leverages Monte Carlo Tree Search to assess the quality of each step. At inference time, Hierarchical Beam Search iteratively refines planning and search candidates guided by the dual value models. Experiments across policy models of varying parameter sizes demonstrate the framework's effectiveness. The paper situates itself within the broader evolution from classical retrieval pipelines to agentic search, where retrieval frequency and strategy become learnable objects, and discusses implications for evaluation, latency, cost, and safety in industrial deployment.

DecoupleSearch: Decoupling Planning and Search via Hierarchical Reward Modeling

Paper: https://arxiv.org/abs/2510.21712 Authors: Hao Sun, Zile Qiao, Bo Wang, Guoxin Chen, Yingyan Hou, Yong Jiang, et al. (9 authors) Published: 2025-09-07 Category: Agentic Search

Overview

Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by dynamically integrating external knowledge. Agentic RAG extends this by introducing autonomous agents into the workflow, but faces three key challenges:

1. The success of each step depends on both high-quality planning and accurate search. 2. There is a lack of supervision for intermediate reasoning steps. 3. The candidate space for planning and searching grows exponentially.

The DecoupleSearch Framework

DecoupleSearch decouples planning and search using dual value models, enabling independent optimization of plan reasoning and search grounding. The approach:

  • Constructs a reasoning tree, where each node represents a planning or search step.
  • Uses Monte Carlo Tree Search (MCTS) to assess the quality of each step.
  • At inference, applies Hierarchical Beam Search to iteratively refine planning and search candidates with the dual value models.
  • Extensive experiments across policy models of varying parameter sizes demonstrate the effectiveness of the method.

    Original 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.

    Context and Implications

    The work sits at the intersection of agentic search and large-scale search/recommendation systems. While classic search stacks follow a funnel of recall, ranking, and generation, the LLM era introduces new variables: reasoning budget and action space (whether to retrieve, how many times, and which tools to call). DecoupleSearch treats retrieval strategy itself as a learnable, optimizable component.

    Broader takeaways for the field:

  • Architecture: Agentic paradigms are turning retrieval count and policy into learnable objects, beyond fixed cascade pipelines.
  • Evaluation: Metrics are shifting from static nDCG toward task success rate, citation accuracy, and multi-hop reasoning chain completeness.
  • Deployment: Latency, cost, interpretability, and safety remain hard constraints for industrial adoption—offline benchmark gains must be validated with interleaving experiments and human auditing.
  • Related Entries

  • AceSearcher: Bootstrapping Reasoning and Search for LLMs via Reinforcement Learning
  • Synergizing RAG and Reasoning: A Systematic Review (arXiv:2504.15909)
  • Agentic Information Retrieval (arXiv:2410.09713)
*Note: Quantitative experimental results should be verified against the original PDF.*

Tags

#agentic-rag#monte-carlo-tree-search#hierarchical-beam-search#reward-modeling#llm-reasoning#information-retrieval#reinforcement-learning

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178208547