TrustAgent: Towards Safe and Trustworthy LLM-based Agents

作者：Wenyue Hua, Xianjun Yang, Mingyu Jin, Zelong Li, Wei Cheng, Ruixiang Tang, Yongfeng Zhang · 单位：Department of Computer Science, Rutgers University, New Brunswick, Department of Computer Science, University of California, Santa Barbara · 会议/期刊：Findings of the Association for Computational Linguistics: EMNLP 2024 · 方向：测试内自进化 / 泛化能力 · 发布日期：2024-02-02