Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lu, Rui, Hou, Zhenyu, Wang, Zihan, Zhang, Hanchen, Liu, Xiao, Li, Yujiang, Feng, Shi, Tang, Jie, Dong, Yuxiao
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.10446
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911209826025472
author Lu, Rui
Hou, Zhenyu
Wang, Zihan
Zhang, Hanchen
Liu, Xiao
Li, Yujiang
Feng, Shi
Tang, Jie
Dong, Yuxiao
author_facet Lu, Rui
Hou, Zhenyu
Wang, Zihan
Zhang, Hanchen
Liu, Xiao
Li, Yujiang
Feng, Shi
Tang, Jie
Dong, Yuxiao
contents Augmenting large language models (LLMs) with browsing tools substantially improves their potential as deep search agents to solve complex, real-world tasks. Yet, open LLMs still perform poorly in such settings due to limited long-horizon reasoning capacity with browsing tools and the lack of sufficiently difficult supervised data. To address these challenges, we present DeepDive to advance deep search agents. First, we propose a strategy to automatically synthesize complex, difficult, and hard-to-find questions from open knowledge graphs. Second, we apply end-to-end multi-turn reinforcement learning (RL) to enhance LLMs' long-horizon reasoning with deep search. To encourage diversity and reduce redundancy, we design a redundancy penalty that discourages repeated similar queries. Experiments show that DeepDive-32B achieves a new open-source competitive result on BrowseComp, outperforming WebSailor, DeepSeek-R1-Browse, and Search-o1. We demonstrate that multi-turn RL training improves deep search ability and significantly contributes to the performance improvements across multiple benchmarks. We observe that DeepDive enables test-time scaling of tool calls and parallel sampling. All datasets, models, and code are publicly available at https://github.com/THUDM/DeepDive.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10446
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL
Lu, Rui
Hou, Zhenyu
Wang, Zihan
Zhang, Hanchen
Liu, Xiao
Li, Yujiang
Feng, Shi
Tang, Jie
Dong, Yuxiao
Computation and Language
Augmenting large language models (LLMs) with browsing tools substantially improves their potential as deep search agents to solve complex, real-world tasks. Yet, open LLMs still perform poorly in such settings due to limited long-horizon reasoning capacity with browsing tools and the lack of sufficiently difficult supervised data. To address these challenges, we present DeepDive to advance deep search agents. First, we propose a strategy to automatically synthesize complex, difficult, and hard-to-find questions from open knowledge graphs. Second, we apply end-to-end multi-turn reinforcement learning (RL) to enhance LLMs' long-horizon reasoning with deep search. To encourage diversity and reduce redundancy, we design a redundancy penalty that discourages repeated similar queries. Experiments show that DeepDive-32B achieves a new open-source competitive result on BrowseComp, outperforming WebSailor, DeepSeek-R1-Browse, and Search-o1. We demonstrate that multi-turn RL training improves deep search ability and significantly contributes to the performance improvements across multiple benchmarks. We observe that DeepDive enables test-time scaling of tool calls and parallel sampling. All datasets, models, and code are publicly available at https://github.com/THUDM/DeepDive.
title DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL
topic Computation and Language
url https://arxiv.org/abs/2509.10446