collaborative_agent_bench

This dataset is released as part of [SWEET-RL: Training Multi-Turn LLM Agents on
Collaborative Reasoning Tasks](https://arxiv.org/abs/2503.15478) research project.

Please refer to our [project materials](https://github.com/facebookresearch/sweet_rl) here for training and evaluation details.

## Citation
If you use data, model, or code from this work, please cite with the following BibTex entry:
```bibtex
@misc{zhou2025sweetrltrainingmultiturnllm,
title={SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks},
author={Yifei Zhou and Song Jiang and Yuandong Tian and Jason Weston and Sergey Levine and Sainbayar Sukhbaatar and Xian Li},
year={2025},
eprint={2503.15478},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2503.15478},
}
```

## License
The data is licensed under CC-by-NC. This data is an output from Llama 3.1, and subject to the Llama 3.1 license (https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE).
Use of the data to train, fine tune, or otherwise improve an AI model, which is distributed or made available, shall also include "Llama" at the beginning of any such AI model name.

本数据集作为[SWEET-RL：面向协作推理任务的多轮大语言模型（Large Language Model，LLM）智能体训练](https://arxiv.org/abs/2503.15478)研究项目的一部分发布。

请参阅我们的[项目资料](https://github.com/facebookresearch/sweet_rl)以获取训练与评估的详细信息。

## 引用
若您使用本项目的数据、模型或代码，请按照以下BibTex条目进行引用：
bibtex
@misc{zhou2025sweetrltrainingmultiturnllm,
title={SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks},
author={Yifei Zhou and Song Jiang and Yuandong Tian and Jason Weston and Sergey Levine and Sainbayar Sukhbaatar and Xian Li},
year={2025},
eprint={2503.15478},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2503.15478},
}

## 许可证
本数据集采用CC-by-NC（知识共享署名-非商业性使用）许可证进行授权。本数据集为Llama 3.1的生成输出，因此同时受限于Llama 3.1许可证（https://huggingface.co/meta-llama/Llama-3.1-8B/blob/main/LICENSE）。
若使用本数据集训练、微调或以其他方式改进人工智能模型并进行分发或公开提供，则此类人工智能模型的名称需以"Llama"作为开头。