Home
Academic Team Ends Tech Giants' Monopoly with SFT; OpenSeeker-v2 Tops Search Agent Rankings
In the evolving landscape of large language models (LLMs), deep search capabilities have become the decisive advantage for advanced intelligent agents. Yet this arena has long been controlled by well-funded industry giants. Conventional development approaches typically depend on resource-heavy pipelines that encompass pre-training, continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL).
A team of academic researchers has recently unveiled their latest work, OpenSeeker-v2, fundamentally challenging this established view. According to their report, training on high-quality, high-difficulty task trajectories enables even a straightforward supervised fine-tuning (SFT) approach to produce a top-tier search agent.

The team outlined three key optimization strategies for data synthesis: first, scaling up the knowledge graph to create a broader exploration space; second, substantially expanding the toolkit repertoire to push functional limits; and finally, applying strict low-step filtering to guarantee the quality and efficiency of training data.
Experimental results reveal that OpenSeeker-v2 (with 30B parameters and a ReAct architecture), trained on merely 10,600 data points, exhibited commanding performance across four core benchmarks: it scored 46.0% on BrowseComp, 58.1% on BrowseComp-ZH, 34.6% on "Humanity's Last Exam", and 78.0% on xbench. These figures not only set new records but also comprehensively outperformed industry models that relied on heavy pipelines combining CPT, SFT, and RL—such as Tongyi DeepResearch.

Strikingly, this marks the first state-of-the-art (SOTA) search agent developed by an entirely academic team using only SFT, at the same model scale and architecture. The team has now open-sourced the model weights for OpenSeeker-v2. This breakthrough significantly lowers the R&D barrier for advanced search agents and offers a more accessible, lightweight development pathway for both the academic and open-source communities.
Paper: https://arxiv.org/pdf/2605.04036
Related article
ByteDance’s Seed launches global campus drive, offering virtual shares to win top large model talent
In the competitive landscape of large language models, securing top-tier talent remains the most critical strategic asset.On April 1st, ByteDance announced the launch of its Seed global campus recruitment initiative, part of its large model talent de
Suno to Watermark Songs Amid Legal Battles
Suno, the platform enabling users to generate AI-created music, has unveiled new features to label platform-produced tracks, restrict downloads, and update community standards to curb unauthorized replicas. These updates arrive as Suno confronts mult
Musk Admits Grok Build Leaked User Code, Promises to Erase All Historical Data
Elon Musk directly addressed the privacy controversy surrounding Grok Build, beginning with a simple "True" to confirm the incident's validity. He pledged that all user data previously uploaded to SpaceXAI would be permanently erased, stating, "not a
Related Special Topic Recommendations
Comments (0)
0/500
In the evolving landscape of large language models (LLMs), deep search capabilities have become the decisive advantage for advanced intelligent agents. Yet this arena has long been controlled by well-funded industry giants. Conventional development approaches typically depend on resource-heavy pipelines that encompass pre-training, continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL).
A team of academic researchers has recently unveiled their latest work, OpenSeeker-v2, fundamentally challenging this established view. According to their report, training on high-quality, high-difficulty task trajectories enables even a straightforward supervised fine-tuning (SFT) approach to produce a top-tier search agent.

The team outlined three key optimization strategies for data synthesis: first, scaling up the knowledge graph to create a broader exploration space; second, substantially expanding the toolkit repertoire to push functional limits; and finally, applying strict low-step filtering to guarantee the quality and efficiency of training data.
Experimental results reveal that OpenSeeker-v2 (with 30B parameters and a ReAct architecture), trained on merely 10,600 data points, exhibited commanding performance across four core benchmarks: it scored 46.0% on BrowseComp, 58.1% on BrowseComp-ZH, 34.6% on "Humanity's Last Exam", and 78.0% on xbench. These figures not only set new records but also comprehensively outperformed industry models that relied on heavy pipelines combining CPT, SFT, and RL—such as Tongyi DeepResearch.

Strikingly, this marks the first state-of-the-art (SOTA) search agent developed by an entirely academic team using only SFT, at the same model scale and architecture. The team has now open-sourced the model weights for OpenSeeker-v2. This breakthrough significantly lowers the R&D barrier for advanced search agents and offers a more accessible, lightweight development pathway for both the academic and open-source communities.
Paper: https://arxiv.org/pdf/2605.04036
ByteDance’s Seed launches global campus drive, offering virtual shares to win top large model talent
In the competitive landscape of large language models, securing top-tier talent remains the most critical strategic asset.On April 1st, ByteDance announced the launch of its Seed global campus recruitment initiative, part of its large model talent de
Suno to Watermark Songs Amid Legal Battles
Suno, the platform enabling users to generate AI-created music, has unveiled new features to label platform-produced tracks, restrict downloads, and update community standards to curb unauthorized replicas. These updates arrive as Suno confronts mult
Musk Admits Grok Build Leaked User Code, Promises to Erase All Historical Data
Elon Musk directly addressed the privacy controversy surrounding Grok Build, beginning with a simple "True" to confirm the incident's validity. He pledged that all user data previously uploaded to SpaceXAI would be permanently erased, stating, "not a











