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

TL;DR

OpenResearcher introduces a fully offline, reproducible pipeline for synthesizing long-horizon research trajectories using GPT-OSS-120B, enabling controlled analysis and significant improvements in research agent accuracy.

Contribution

The paper presents a novel offline pipeline that decouples data collection from trajectory synthesis, allowing reproducible, large-scale research trajectory generation and analysis.

Findings

Synthesized over 97K research trajectories with GPT-OSS-120B.

Fine-tuned a 30B model achieving 54.8% accuracy on BrowseComp-Plus.

Revealed practical insights into research pipeline design and retrieval success.

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.