OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
2026-03-16 • Artificial Intelligence
Artificial IntelligenceComputation and Language
AI summaryⓘ
The authors developed OpenSeeker, the first fully open-source search agent that performs at a top level like those made by big companies. They created new methods to generate complex questions and clean up the learning process, allowing the model to learn effectively from a relatively small amount of synthetic data. OpenSeeker beats other open-source models and even some commercial ones on different tests. The authors have shared both the model and training data openly to help others research search agents more easily.
Large Language ModelsSearch AgentMulti-hop ReasoningQA SynthesisSynthetic DataSupervised Fine-Tuning (SFT)Trajectory DenoisingOpen-source AIBenchmarkingWeb Graph
Authors
Yuwen Du, Rui Ye, Shuo Tang, Xinyu Zhu, Yijun Lu, Yuzhu Cai, Siheng Chen
Abstract
Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet the development of high-performance search agents remains dominated by industrial giants due to a lack of transparent, high-quality training data. This persistent data scarcity has fundamentally hindered the progress of the broader research community in developing and innovating within this domain. To bridge this gap, we introduce OpenSeeker, the first fully open-source search agent (i.e., model and data) that achieves frontier-level performance through two core technical innovations: (1) Fact-grounded scalable controllable QA synthesis, which reverse-engineers the web graph via topological expansion and entity obfuscation to generate complex, multi-hop reasoning tasks with controllable coverage and complexity. (2) Denoised trajectory synthesis, which employs a retrospective summarization mechanism to denoise the trajectory, therefore promoting the teacher LLMs to generate high-quality actions. Experimental results demonstrate that OpenSeeker, trained (a single training run) on only 11.7k synthesized samples, achieves state-of-the-art performance across multiple benchmarks including BrowseComp, BrowseComp-ZH, xbench-DeepSearch, and WideSearch. Notably, trained with simple SFT, OpenSeeker significantly outperforms the second-best fully open-source agent DeepDive (e.g., 29.5% v.s. 15.3% on BrowseComp), and even surpasses industrial competitors such as Tongyi DeepResearch (trained via extensive continual pre-training, SFT, and RL) on BrowseComp-ZH (48.4% v.s. 46.7%). We fully open-source the complete training dataset and the model weights to democratize frontier search agent research and foster a more transparent, collaborative ecosystem.