用真实网页交互生成训练数据，让小模型也能高效完成深度搜索。
SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis
- 通过模拟真实网络搜索行为合成高质量训练数据
- 仅用871个样本微调即超越强化学习基线
- 适合需要低成本高效部署的深度搜索应用
检索增强生成（RAG）系统在需要多步推理和迭代检索的复杂深度搜索场景中提升了大语言模型的表现。然而，现有方法存在训练轨迹质量差、模拟环境分布不匹配以及真实部署计算成本过高等关键问题。本文提出SimpleDeepSearcher，一种轻量级但高效的框架，通过策略性数据工程而非复杂训练范式来弥合这一差距。我们通过在实时网络搜索环境中模拟真实用户交互，合成高质量训练数据，并采用多标准筛选策略优化输入输出质量。在五个跨领域基准上的实验表明，仅使用871个精选样本进行监督微调，性能显著优于基于强化学习的基线。本工作系统性解决了数据稀缺瓶颈，为高效深度搜索系统提供了可行路径。代码已开源：https://github.com/RUCAIBox/SimpleDeepSearcher。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。