---
title: "OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories"
source: arXiv
url: https://arxiv.org/abs/2605.04036
---

# OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories

**Authors**: Yuwen Du*, Rui Ye*#,†, Shuo Tang, Keduan Huang, Xinyu Zhu, Yuzhu Cai, Siheng Chen†  
**Affiliation**: Shanghai Jiao Tong University  
**arXiv**: 2605.04036v1 [cs.AI] | **Date**: 2026-05-05  

## Abstract

Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominated by industrial giants. The typical industry recipe involves a highly resource-intensive pipeline spanning pre-training, continual pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL). In this report, we show that when fueled with informative and high-difficulty trajectories, a simple SFT approach could be surprisingly powerful for training frontier search agents.

By introducing three simple data synthesis modifications: scaling knowledge graph size for richer exploration, expanding the tool set size for broader functionality, and strict low-step filtering, we establish a stronger baseline. Trained on merely 10.6k data points, our OpenSeeker-v2 achieves state-of-the-art performance across 4 benchmarks (30B-sized agents with ReAct paradigm): 46.0% on BrowseComp, 58.1% on BrowseComp-ZH, 34.6% on Humanity's Last Exam, and 78.0% on xbench, surpassing even Tongyi DeepResearch trained with heavy CPT+SFT+RL pipeline (43.4%, 46.7%, 32.9%, and 75.0%, respectively).

Notably, OpenSeeker-v2 represents the first state-of-the-art search agent within its model scale and paradigm to be developed by a purely academic team using only SFT.

**Code**: https://github.com/PolarSeeker/OpenSeeker  
**Model**: https://huggingface.co/PolarSeeker/OpenSeeker-v2-30B-SFT