研究

有关技术细节，请查阅我们的技术报告和研究论文。

• AutoGen: 通过多智能体对话框架实现下一代LLM应用。Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Shaokun Zhang, Erkang Zhu, Beibin Li, Li Jiang, Xiaoyun Zhang和Chi Wang。ArXiv 2023。

@inproceedings{wu2023autogen,
      title={AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework},
      author={Qingyun Wu and Gagan Bansal and Jieyu Zhang and Yiran Wu and Shaokun Zhang and Erkang Zhu and Beibin Li and Li Jiang and Xiaoyun Zhang and Chi Wang},
      year={2023},
      eprint={2308.08155},
      archivePrefix={arXiv},
      primaryClass={cs.AI}
}

• 大型语言模型生成推理的成本效益超参数优化。Chi Wang, Susan Xueqing Liu, Ahmed H. Awadallah。AutoML'23。

@inproceedings{wang2023EcoOptiGen,
    title={Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference},
    author={Chi Wang and Susan Xueqing Liu and Ahmed H. Awadallah},
    year={2023},
    booktitle={AutoML'23},
}

• 使用GPT-4解决具有挑战性的数学问题的实证研究。Yiran Wu, Feiran Jia, Shaokun Zhang, Hangyu Li, Erkang Zhu, Yue Wang, Yin Tat Lee, Richard Peng, Qingyun Wu, Chi Wang。ArXiv预印本arXiv:2306.01337 (2023)。

@inproceedings{wu2023empirical,
    title={An Empirical Study on Challenging Math Problem Solving with GPT-4},
    author={Yiran Wu and Feiran Jia and Shaokun Zhang and Hangyu Li and Erkang Zhu and Yue Wang and Yin Tat Lee and Richard Peng and Qingyun Wu and Chi Wang},
    year={2023},
    booktitle={ArXiv preprint arXiv:2306.01337},
}

• EcoAssistant: 更经济、更准确地使用LLM助手。Jieyu Zhang, Ranjay Krishna, Ahmed H. Awadallah, Chi Wang。ArXiv预印本arXiv:2310.03046 (2023)。

@inproceedings{zhang2023ecoassistant,
    title={EcoAssistant: Using LLM Assistant More Affordably and Accurately},
    author={Zhang, Jieyu and Krishna, Ranjay and Awadallah, Ahmed H and Wang, Chi},
    year={2023},
    booktitle={ArXiv preprint arXiv:2310.03046},
}

• 朝着更好的人机对齐：评估LLM驱动应用中的任务效用。Negar Arabzadeh, Julia Kiseleva, Qingyun Wu, Chi Wang, Ahmed Awadallah, Victor Dibia, Adam Fourney, Charles Clarke。ArXiv预印本arXiv:2402.09015 (2024)。

@misc{Kiseleva2024agenteval,
      title={朝着更好的人机对齐：评估LLM驱动应用中的任务效用},
      author={Negar Arabzadeh and Julia Kiseleva and Qingyun Wu and Chi Wang and Ahmed Awadallah and Victor Dibia and Adam Fourney and Charles Clarke},
      year={2024},
      eprint={2402.09015},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

• 无需修改语言模型的训练语言模型代理. 张少坤，张洁宇，刘佳乐，宋林鑫，王驰，Ranjay Krishna，吴庆云。ICML'24。

@misc{zhang2024agentoptimizer,
      title={无需修改语言模型的训练语言模型代理},
      author={张少坤 and 张洁宇 and 刘佳乐 and 宋林鑫 and 王驰 and Ranjay Krishna and 吴庆云},
      year={2024},
      booktitle={ICML'24},
}

• AutoDefense: 防范越狱攻击的多代理LLM防御. 曾一帆，吴一然，张晓，王华政，吴庆云。ArXiv预印本 arXiv:2403.04783 (2024).

@misc{zeng2024autodefense,
      title={AutoDefense: 防范越狱攻击的多代理LLM防御},
      author={曾一帆 and 吴一然 and 张晓 and 王华政 and 吴庆云},
      year={2024},
      eprint={2403.04783},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}

• StateFlow: 通过状态驱动的工作流增强LLM任务求解. 吴一然，岳天威，张少坤，王驰，吴庆云。ArXiv预印本 arXiv:2403.11322 (2024).

@misc{wu2024stateflow,
        title={StateFlow: 通过状态驱动的工作流增强LLM任务求解},
        author={吴一然 and 岳天威 and 张少坤 and 王驰 and 吴庆云},
        year={2024},
        eprint={2403.11322},
        archivePrefix={arXiv},
        primaryClass={cs.CL}
}