Paper 2603.20278
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
- Published
- Mar 2026
- Research lab
- Independent
- Citations
- 20
- GitHub
- 1.1K stars
01 In brief
Summary
OpenResearcher is a fully open pipeline for synthesizing long-horizon deep research trajectories.
It decouples one-time corpus bootstrapping from multi-turn trajectory synthesis, running the search-and-browse loop entirely offline over a 15M-document corpus using three browser primitives: search, open, and find.
Using GPT-OSS-120B as the teacher, it synthesizes over 97K trajectories, including many 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.
The offline environment enables controlled analysis, revealing insights into data filtering, agent configuration, and the relationship between retrieval success and final answer accuracy.
The pipeline, trajectories, model checkpoints, and offline search environment are released at the provided GitHub link.
02 From the paper
Abstract
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.