README.md

---
license: mit
datasets:
- OffSeeker/DeepForge
language:
- en
- zh
base_model:
- Qwen/Qwen3-8B
tags:
- agent
---


# OffSeeker: Online Reinforcement Learning Is Not All You Need for Deep Research Agents

<a href="https://arxiv.org/abs/2601.18467"><b>Paper</b></a> | <a href="https://github.com/Ralph-Zhou/OffSeeker/tree/main"><b>Github</b></a>

<!-- [![Paper](https://img.shields.io/badge/Paper-arXiv-red.svg)](https://arxiv.org/abs/2601.18467) [![Model](https://img.shields.io/badge/🤗%20Model-OffSeeker--8B--DPO-blue.svg)](https://huggingface.co/OffSeeker/OffSeeker-8B-DPO) [![Dataset](https://img.shields.io/badge/🤗%20Dataset-DeepForge--QA-blue.svg)](https://huggingface.co/datasets/OffSeeker/DeepForge) [![License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE) -->

## 🌟 Abstract

We introduce a fully open-source suite designed for effective offline training. Our core contributions include DeepForge, a ready-to-use task synthesis framework that generates large-scale research queries without heavy preprocessing; and a curated collection of 66k QA pairs, 33k SFT trajectories, and 21k DPO pairs. Leveraging these resources, we train OffSeeker (8B), a model developed entirely offline. Extensive evaluations across six benchmarks show that OffSeeker not only leads among similar-sized agents but also remains competitive with 30B-parameter systems trained via heavy online RL.

![main_figure](https://raw.githubusercontent.com/Ralph-Zhou/OffSeeker/main/assets/main_results.jpg)


## 📊 Resources & Datasets


We are releasing our complete dataset to support the research community in offline agent training.

| Resource | Quantity | Description |
| :--- | :--- | :--- |
| **Research QA Pairs** | 66,000 | Complex questions requiring multi-hop search |
| **SFT Trajectories** | 33,000 | Step-by-step reasoning and tool-use paths |
| **DPO Pairs** | 21,000 | Preference pairs for refining agent behavior |
| **OffSeeker Model** | 8B | Competitive with 30B-parameter online RL models |

## 📖 Citation

If you find this work useful for your research, please cite our paper:

```bibtex
@article{zhou2026offseeker,
  title={OffSeeker: Online Reinforcement Learning Is Not All You Need for Deep Research Agents},
  author={Zhou, Yuhang and Zheng, Kai and Chen, Qiguang and Hu, Mengkang and Sun, Qingfeng and Xu, Can and Chen, Jingjing},
  journal={arXiv preprint arXiv:2601.18467},
  year={2026}
}
```