为大模型智能体构建可观测性体系，保障其安全可控
AgentOps: Enabling Observability of LLM Agents
- 提出智能体全生命周期可观测性分类框架
- 系统梳理现有工具，归纳需追踪的关键数据产物
- 帮助开发者实现监控与异常检测，适合安全研发团队参考
大语言模型智能体在多个领域展现出强大能力，受到学术界和产业界的广泛关注。然而，由于其自主性、非确定性及持续演化特性，带来显著的AI安全风险。从DevOps视角看，实现智能体可观测性是保障AI安全的关键，使利益相关方能够洞察智能体内部运作，主动理解行为、检测异常并预防潜在故障。本文通过系统映射现有AgentOps工具，构建了覆盖智能体全生命周期的可观测性分类体系，识别出应追踪的各类数据产物。该分类框架可作为开发者的参考模板，用于设计和实现支持监控、日志记录与分析的AgentOps基础设施，从而确保AI安全。
原文摘要 · Abstract (English)
Large language model (LLM) agents have demonstrated remarkable capabilities across various domains, gaining extensive attention from academia and industry. However, these agents raise significant concerns on AI safety due to their autonomous and non-deterministic behavior, as well as continuous evolving nature . From a DevOps perspective, enabling observability in agents is necessary to ensuring AI safety, as stakeholders can gain insights into the agents' inner workings, allowing them to proactively understand the agents, detect anomalies, and prevent potential failures. Therefore, in this paper, we present a comprehensive taxonomy of AgentOps, identifying the artifacts and associated data that should be traced throughout the entire lifecycle of agents to achieve effective observability. The taxonomy is developed based on a systematic mapping study of existing AgentOps tools. Our taxonomy serves as a reference template for developers to design and implement AgentOps infrastructure that supports monitoring, logging, and analytics. thereby ensuring AI safety.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。