迈向无风险的AI智能体部署
Towards Risk-free AI Agent Deployment
- Singapore Management University（新加坡管理大学）
- IBM T.J. Watson Research Center（IBM T.J. 沃森研究中心）
- National University of Singapore（新加坡国立大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对LLM智能体部署的安全、合规等风险，本文提出以智能体轨迹为基础，将测试与调试作为系统性研究方向，提炼部署就绪检查表并指出需解决的开放性问题，推动可信智能体部署。
AI中文摘要：
基于大语言模型（LLM）的智能体正迅速从研究原型转向组织的核心业务流程，但这些智能体在安全性、合规性和功能方面带来了部署风险。本文提出，无风险部署必须以智能体的轨迹为基础，轨迹是记录的推理步骤、工具调用和环境观测序列，任何智能体都具备轨迹，且许多故障仅能在轨迹中显现。为使智能体可部署且可持续，本文倡导将智能体测试与调试作为系统性研究方向，以检测和缓解这些风险。本文首先探讨智能体测试的挑战，包括预言机问题、非确定性、轨迹验证以及缺乏充足性指标；随后转向智能体调试，涵盖自动故障归因、修复与自进化。本文将这些方向提炼为覆盖完整部署生命周期的实用部署就绪检查表；最后，本文指出社区需解决的开放性问题，即形式化充足性指标、长程轨迹的根本原因归因以及自进化智能体的可靠性，以实现可信的智能体部署。
英文摘要：
LLM-based agents are rapidly moving from research prototypes into the core business processes of organizations, but these agents pose deployment risks to security, compliance, and functionality. In this article, we argue that risk-free deployment must be grounded in the agent's trajectory: the recorded sequence of reasoning steps, tool invocations, and environmental observations. Trajectories are available for any agent, and many failures are visible only in the trajectory. To make agents deployable and sustainable, we advocate agent testing and debugging as a systematic research direction for detecting and mitigating these risks. This article begins with the challenges of testing agents, including the oracle problem, non-determinism, trajectory validation, and the absence of adequacy metrics. We then turn to debugging agents, from automated failure attribution to repair and self-evolution. We distill these directions into a practical deployment-readiness checklist covering the full deployment lifecycle. Finally, we identify open problems, i.e., formal adequacy metrics, root-cause attribution over long-horizon trajectories, and the reliability of self-evolving agents, that the community must address to enable trustworthy agent deployment.
