OpenResearcher：實現長週期深度研究軌跡合成的全開源流程

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

March 17, 2026

作者: Zhuofeng Li, Dongfu Jiang, Xueguang Ma, Haoxiang Zhang, Ping Nie, Yuyu Zhang, Kai Zou, Jianwen Xie, Yu Zhang, Wenhu Chen

cs.AI

摘要

訓練深度研究智能體需要能夠交錯進行搜尋、證據匯總與多步驟推理的長程軌跡。然而現有的資料收集流程通常依賴專有網路API，導致大規模軌跡合成成本高昂、穩定性差且難以重現。我們提出OpenResearcher——一個可重現的流程，將一次性語料庫引導建置與多輪軌跡解耦，並透過三種明確的瀏覽器基礎操作（搜尋、開啟、查找）在包含1,500萬份文件的語料庫中完全離線執行「搜尋-瀏覽」循環。使用GPT-OSS-120B作為教師模型，我們合成了超過9.7萬條軌跡，其中包含大量工具調用次數達100+的長程軌跡。基於30B-A3B骨幹模型對這些軌跡進行監督式微調後，在BrowseComp-Plus上達到54.8%的準確率，相較基礎模型提升34.0個百分點，同時在BrowseComp、GAIA和xbench-DeepSearch基準上保持競爭力。由於環境完全離線且具備全流程監測機制，該系統還支持可控分析：我們的研究揭示了深度研究管道設計的實用洞察，包括資料過濾策略、智能體配置選擇，以及檢索成功率與最終答案準確性的關聯。我們已於https://github.com/TIGER-AI-Lab/OpenResearcher 開源此流程、合成軌跡、模型檢查點及離線搜尋環境。

English

Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning. However, existing data collection pipelines typically rely on proprietary web APIs, making large-scale trajectory synthesis costly, unstable, and difficult to reproduce. We present OpenResearcher, a reproducible pipeline that decouples one-time corpus bootstrapping from multi-turn trajectory synthesis and executes the search-and-browse loop entirely offline using three explicit browser primitives: search, open, and find, over a 15M-document corpus. Using GPT-OSS-120B as the teacher model, we synthesize over 97K trajectories, including a substantial long-horizon tail with 100+ tool calls. Supervised fine-tuning a 30B-A3B backbone on these trajectories achieves 54.8\% accuracy on BrowseComp-Plus, a +34.0 point improvement over the base model, while remaining competitive on BrowseComp, GAIA, and xbench-DeepSearch. Because the environment is offline and fully instrumented, it also enables controlled analysis, where our study reveals practical insights into deep research pipeline design, including data filtering strategies, agent configuration choices, and how retrieval success relates to final answer accuracy. We release the pipeline, synthesized trajectories, model checkpoints, and the offline search environment at https://github.com/TIGER-AI-Lab/OpenResearcher.