OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
- URL: http://arxiv.org/abs/2603.20278v1
- Date: Tue, 17 Mar 2026 20:10:12 GMT
- Title: OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
- Abstract summary: Training deep research agents requires long-horizon trajectories that interleave search, evidence aggregation, and multi-step reasoning.<n>Existing data collection pipelines typically rely on proprietary web APIs, making large-scale trajectory synthesis costly, unstable, and difficult to reproduce.<n>We present OpenResearcher, a reproducible pipeline that decouples one-time corpus bootstrapping from multi-turn trajectory synthesis.
- Score: 63.8655724265611
- License: http://creativecommons.org/licenses/by/4.0/
- 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.
Related papers
- G-ReAct: Graph-Guided Deep Search via Structure-State Co-Evolution [16.818086150132853]
$textbfG-ReAct is a reasoning framework for deep search.<n>It organizes reasoning as $textbfstate evolution over a fixed-topology query graph.<n>G-ReAct supports both training and inference.
arXiv Detail & Related papers (2026-08-02T15:43:37Z) - OpenSearch-VL: An Open Recipe for Frontier Multimodal Search Agents [50.79529228477821]
We introduce OpenSearch-VL, a fully open-source recipe for training frontier multimodal deep search agents with agentic reinforcement learning.<n>First, we curated a dedicated pipeline to construct high-quality training data through Wikipedia path sampling, fuzzy entity rewriting, and source-anchor visual grounding.<n>Besides, we design a diverse tool environment that unifies text search, image search, OCR, cropping, sharpening, super-resolution, and perspective correction.
arXiv Detail & Related papers (2026-05-06T17:50:38Z) - DeepResearch-9K: A Challenging Benchmark Dataset of Deep-Research Agent [63.52637950356965]
DeepResearch-9K is a large-scale, challenging dataset for deep-research scenarios.<n>DeepResearch-R1 is an open-source training framework for deep-research agents.
arXiv Detail & Related papers (2026-03-01T15:36:10Z) - Fathom-DeepResearch: Unlocking Long Horizon Information Retrieval and Synthesis for SLMs [7.3517692707289415]
We introduce Fathom-DeepResearch, an agentic system composed of two specialized models.<n>The first is Fathom-Search-4B, a DeepSearch model optimized for evidence-based investigation through live web search and targeted webpage querying.<n>The second is Fathom- Synthesizer-4B, trained from Qwen3-4B, which converts multi-turn DeepSearch traces into structured, citation-dense DeepResearch Reports.
arXiv Detail & Related papers (2025-09-28T22:58:11Z) - DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL [60.47878242100153]
We present DeepDive to advance deep search agents.<n>We propose a strategy to automatically synthesize complex, difficult, and hard-to-find questions from open knowledge graphs.<n>We apply end-to-end multi-turn reinforcement learning to enhance LLMs' long-horizon reasoning with deep search.
arXiv Detail & Related papers (2025-09-12T17:52:35Z) - Open Data Synthesis For Deep Research [17.22470203913576]
We formalize Deep Research tasks with verifiable answers as Hierarchical Constraint Satisfaction Problems.<n>Existing benchmarks (e.g., Natural Questions, HotpotQA) fail to capture this complexity.<n>We introduce InfoSeek, a scalable scalable complex Deep Research tasks.
arXiv Detail & Related papers (2025-08-30T06:02:56Z) - Benchmarking Deep Search over Heterogeneous Enterprise Data [73.55304268238474]
We present a new benchmark for evaluating a form of retrieval-augmented generation (RAG)<n>RAG requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources.<n>We build it using a synthetic data pipeline that simulates business across product planning, development, and support stages.
arXiv Detail & Related papers (2025-06-29T08:34:59Z) - SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis [94.33978856270268]
Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios.<n>Existing approaches face critical limitations that lack high-quality training trajectories and suffer from distributional mismatches.<n>This paper introduces SimpleDeepSearcher, a framework that bridges the gap through strategic data engineering rather than complex training paradigms.
arXiv Detail & Related papers (2025-05-22T16:05:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.