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

2025-05-22

AI Summary

Existing RAG systems face three key challenges in multi-step deep search: low-quality training data, distributional shift between simulated environments and real-world deployment, and high operational costs. This paper proposes a lightweight and efficient framework featuring the first data synthesis method grounded in authentic Web interactions, coupled with a multi-criteria trajectory filtering strategy to circumvent the high sample complexity and distribution mismatch inherent in reinforcement learning. Using only 871 carefully curated trajectories for supervised fine-tuning (SFT), our approach significantly outperforms RL-based baselines across five cross-domain deep search benchmarks. Our core contributions are: (1) establishing the first high-fidelity trajectory synthesis paradigm tailored to realistic web environments; (2) empirically validating the efficacy of SFT under extreme data scarcity; and (3) providing a practical, deployable pathway for deep search systems.

Technology Category

• Search and Optimization: Learning to Search
• Multiagent Systems: Multiagent Learning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

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.

Problem

• Addresses lack of high-quality training trajectories in RAG systems
• Reduces distributional mismatches in simulated search environments
• Minimizes computational costs for real-world deployment

Innovation

• Simulates realistic web search interactions for data
• Uses multi-criteria curation for diverse high-quality samples
• Achieves strong performance with minimal supervised fine-tuning