The emergence of LLM-based agents has garnered considerable attention, yet their trustworthiness remains an under-explored area. As agents can directly interact with the physical environment, their reliability and safety is critical. This paper presents an Agent-Constitution-based agent framework, TrustAgent, an initial investigation into improving the safety dimension of trustworthiness in LLM-based agents. This framework consists of threefold strategies: pre-planning strategy which injects safety knowledge to the model prior to plan generation, in-planning strategy which bolsters safety during plan generation, and post-planning strategy which ensures safety by post-planning inspection. Through experimental analysis, we demonstrate how these approaches can effectively elevate an LLM agent's safety by identifying and preventing potential dangers. Furthermore, we explore the intricate relationships between safety and helpfulness, and between the model's reasoning ability and its efficacy as a safe agent. This paper underscores the imperative of integrating safety awareness and trustworthiness into the design and deployment of LLM-based agents, not only to enhance their performance but also to ensure their responsible integration into human-centric environments. Data and code are available at https://github.com/agiresearch/TrustAgent.

翻译：基于大语言模型（LLM）的智能体引起了广泛关注，但其可信度仍是研究不足的领域。由于智能体可直接与物理环境交互，其可靠性与安全性至关重要。本文提出了一种基于Agent宪法的智能体框架TrustAgent，这是提升LLM智能体可信安全性维度的初步探索。该框架包含三重策略：规划前策略（在计划生成前向模型注入安全知识）、规划中策略（在计划生成期间强化安全性）以及规划后策略（通过规划后检查确保安全性）。通过实验分析，我们展示了这些方法如何通过识别和预防潜在危险有效提升LLM智能体的安全性。此外，我们还探讨了安全性与有用性之间的复杂关系，以及模型推理能力与其作为安全智能体效能之间的关联。本文强调，将安全意识和可信度融入LLM智能体的设计与部署至关重要，这不仅能增强其性能，更能确保其负责任地融入人类中心环境。数据和代码可通过https://github.com/agiresearch/TrustAgent获取。