SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Shuang, Song, Huatong, Wang, Yuhao, Ren, Ruiyang, Jiang, Jinhao, Zhang, Junjie, Bai, Fei, Deng, Jia, Zhao, Wayne Xin, Liu, Zheng, Fang, Lei, Wang, Zhongyuan, Wen, Ji-Rong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909831243235328
author Sun, Shuang
Song, Huatong
Wang, Yuhao
Ren, Ruiyang
Jiang, Jinhao
Zhang, Junjie
Bai, Fei
Deng, Jia
Zhao, Wayne Xin
Liu, Zheng
Fang, Lei
Wang, Zhongyuan
Wen, Ji-Rong
author_facet Sun, Shuang
Song, Huatong
Wang, Yuhao
Ren, Ruiyang
Jiang, Jinhao
Zhang, Junjie
Bai, Fei
Deng, Jia
Zhao, Wayne Xin
Liu, Zheng
Fang, Lei
Wang, Zhongyuan
Wen, Ji-Rong
contents Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios requiring multi-step reasoning and iterative information retrieval. However, existing approaches face critical limitations that lack high-quality training trajectories or suffer from the distributional mismatches in simulated environments and prohibitive computational costs for real-world deployment. This paper introduces SimpleDeepSearcher, a lightweight yet effective framework that bridges this gap through strategic data engineering rather than complex training paradigms. Our approach synthesizes high-quality training data by simulating realistic user interactions in live web search environments, coupled with a multi-criteria curation strategy that optimizes the diversity and quality of input and output side. Experiments on five benchmarks across diverse domains demonstrate that SFT on only 871 curated samples yields significant improvements over RL-based baselines. Our work establishes SFT as a viable pathway by systematically addressing the data-scarce bottleneck, offering practical insights for efficient deep search systems. Our code is available at https://github.com/RUCAIBox/SimpleDeepSearcher.
format Preprint
id arxiv_https___arxiv_org_abs_2505_16834
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
Sun, Shuang
Song, Huatong
Wang, Yuhao
Ren, Ruiyang
Jiang, Jinhao
Zhang, Junjie
Bai, Fei
Deng, Jia
Zhao, Wayne Xin
Liu, Zheng
Fang, Lei
Wang, Zhongyuan
Wen, Ji-Rong
Computation and Language
Artificial Intelligence
Information Retrieval
Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios requiring multi-step reasoning and iterative information retrieval. However, existing approaches face critical limitations that lack high-quality training trajectories or suffer from the distributional mismatches in simulated environments and prohibitive computational costs for real-world deployment. This paper introduces SimpleDeepSearcher, a lightweight yet effective framework that bridges this gap through strategic data engineering rather than complex training paradigms. Our approach synthesizes high-quality training data by simulating realistic user interactions in live web search environments, coupled with a multi-criteria curation strategy that optimizes the diversity and quality of input and output side. Experiments on five benchmarks across diverse domains demonstrate that SFT on only 871 curated samples yields significant improvements over RL-based baselines. Our work establishes SFT as a viable pathway by systematically addressing the data-scarce bottleneck, offering practical insights for efficient deep search systems. Our code is available at https://github.com/RUCAIBox/SimpleDeepSearcher.
title SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2505.16834