Dep-Search: Learning Dependency-Aware Reasoning Traces with Persistent Memory

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yanming, Peng, Xinyue, Yan, Zixuan, Shen, Yanxin, Xu, Wenjie, Huang, Yuefeng, Wang, Xinyi, Cao, Jiannan, Yin, Jianwei, Zhang, Xuhong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917223960936448
author Liu, Yanming
Peng, Xinyue
Yan, Zixuan
Shen, Yanxin
Xu, Wenjie
Huang, Yuefeng
Wang, Xinyi
Cao, Jiannan
Yin, Jianwei
Zhang, Xuhong
author_facet Liu, Yanming
Peng, Xinyue
Yan, Zixuan
Shen, Yanxin
Xu, Wenjie
Huang, Yuefeng
Wang, Xinyi
Cao, Jiannan
Yin, Jianwei
Zhang, Xuhong
contents Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, particularly when augmented with search mechanisms that enable systematic exploration of external knowledge bases. The field has evolved from traditional retrieval-augmented generation (RAG) frameworks to more sophisticated search-based frameworks that orchestrate multi-step reasoning through explicit search strategies. However, existing search frameworks still rely heavily on implicit natural language reasoning to determine search strategies and how to leverage retrieved information across reasoning steps. This reliance on implicit reasoning creates fundamental challenges for managing dependencies between sub-questions, efficiently reusing previously retrieved knowledge, and learning optimal search strategies through reinforcement learning. To address these limitations, we propose Dep-Search, a dependency-aware search framework that advances beyond existing search frameworks by integrating structured reasoning, retrieval, and persistent memory through GRPO. Dep-Search introduces explicit control mechanisms that enable the model to decompose questions with dependency relationships, retrieve information when needed, access previously stored knowledge from memory, and summarize long reasoning contexts into reusable memory entries. Through extensive experiments on seven diverse question answering datasets, we demonstrate that Dep-Search significantly enhances LLMs' ability to tackle complex multi-hop reasoning tasks, achieving substantial improvements over strong baselines across different model scales.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18771
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Dep-Search: Learning Dependency-Aware Reasoning Traces with Persistent Memory
Liu, Yanming
Peng, Xinyue
Yan, Zixuan
Shen, Yanxin
Xu, Wenjie
Huang, Yuefeng
Wang, Xinyi
Cao, Jiannan
Yin, Jianwei
Zhang, Xuhong
Computation and Language
Artificial Intelligence
Information Retrieval
Large Language Models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks, particularly when augmented with search mechanisms that enable systematic exploration of external knowledge bases. The field has evolved from traditional retrieval-augmented generation (RAG) frameworks to more sophisticated search-based frameworks that orchestrate multi-step reasoning through explicit search strategies. However, existing search frameworks still rely heavily on implicit natural language reasoning to determine search strategies and how to leverage retrieved information across reasoning steps. This reliance on implicit reasoning creates fundamental challenges for managing dependencies between sub-questions, efficiently reusing previously retrieved knowledge, and learning optimal search strategies through reinforcement learning. To address these limitations, we propose Dep-Search, a dependency-aware search framework that advances beyond existing search frameworks by integrating structured reasoning, retrieval, and persistent memory through GRPO. Dep-Search introduces explicit control mechanisms that enable the model to decompose questions with dependency relationships, retrieve information when needed, access previously stored knowledge from memory, and summarize long reasoning contexts into reusable memory entries. Through extensive experiments on seven diverse question answering datasets, we demonstrate that Dep-Search significantly enhances LLMs' ability to tackle complex multi-hop reasoning tasks, achieving substantial improvements over strong baselines across different model scales.
title Dep-Search: Learning Dependency-Aware Reasoning Traces with Persistent Memory
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2601.18771