Skip to content

Source paper

OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data

Yuwen Du, Rui Ye, Shuo Tang and 4 more

Yuwen Du, Rui Ye, Shuo Tang, Xinyu Zhu, Yijun Lu, Yuzhu Cai, Siheng Chen

arXiv 2603.15594 · 2026130 upvotes on Hugging Face

Research ideas from this paper (3)

Generated by AI. The paper’s authors did not write these.

AI summary

The paper introduces OpenSeeker, the first fully open-source search agent that achieves frontier-level performance comparable to proprietary industrial models. By open-sourcing both the high-quality training data and model weights, it aims to democratize the development of autonomous search agents.

How it works (AI summary)

The authors utilize a two-pronged synthesis approach: 'Fact-grounded scalable controllable QA synthesis' to reverse-engineer web graphs into complex multi-hop queries, and 'Denoised trajectory synthesis' using retrospective summarization to provide clean history contexts for the teacher model. The final agent is then trained via Supervised Fine-Tuning (SFT) on raw trajectories to intrinsically learn denoising.