# Model Overview

### Description:
ToolOrchestrator-8B is an 8B open-weight model for complex agentic tasks such as Humanity's Last Exam, Tau²-Bench, and FRAMES.
Given a question-answering task, the model first interprets the question, reasons through it, invokes tools when necessary, and finally generates the answer.
It is trained using the Group Relative Policy Optimization (GRPO) algorithm on a diverse and comprehensive set of datasets.
Our model has achieved impressive results, outperforming Deepseek’s model by a large margin on a broad range of tasks including Humanity's Last Exam, Tau²-Bench, and FRAMES.

This model is for research and development only.

### License/Terms of Use
[NVIDIA License](LICENSE)

### Deployment Geography:
Global <br>

## Model Architecture:
**Architecture Type:** Dense decoder-only Transformer model <br>

**Network Architecture:** [Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) <br>

**This model was developed based on Qwen3-8B <br> 
** Number of model parameters 8B <br>


## Model Version(s):
1.0 <br>

### Training Dataset:
**Link:** 
| Dataset                      | Link                                                                                         | 
|---------------------------|-------------------------------------------------------------------------------------------|
| GeneralThought-430K  | [Link](https://huggingface.co/datasets/natolambert/GeneralThought-430K-filtered)                   |
| ToolScale           | [Link](https://huggingface.co/datasets/nvidia/ToolScale)                            |



## Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications.  When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. <br> 

Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://app.intigriti.com/programs/nvidia/nvidiavdp/detail).

## Citation
If you find this model useful, please cite:
```
@article{toolorchestra,
  title={ToolOrchestrator-8B: An 8B Open-Weight Model for Complex Agentic Tasks},
  author={Su, Hongjin and Diao, Shizhe and Lu, Ximing and Liu, Mingjie and Xu, Jiacheng and Dong, Xin and Fu, Yonggan and Belcak, Peter and Ye, Hanrong and Yin, Hongxu and Dong, Yi and Bakhturina, Evelina and Yu, Tao and Choi, Yejin and Kautz, Jan and Molchanov, Pavlo}
  journal={arXiv preprint arXiv:XXXX},
  year={2025}
}
```