面向代理式AI的TRiSM框架：基于大语言模型的代理多智能体系统中信任、风险与安全管理综述

TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems

June 4, 2025

作者: Shaina Raza, Ranjan Sapkota, Manoj Karkee, Christos Emmanouilidis

cs.AI

摘要

基于大型语言模型（LLMs）构建并部署于多智能体配置中的自主AI系统，正在重新定义企业和社会领域中的智能自主性、协作与决策。本综述对基于LLM的自主多智能体系统（AMAS）中的信任、风险与安全管理（TRiSM）进行了结构化分析。首先，我们探讨了自主AI的概念基础，其与传统AI智能体在架构上的差异，以及支持可扩展、工具使用自主性的新兴系统设计。随后，通过治理、可解释性、模型运维（ModelOps）及隐私/安全四大支柱，详细阐述了自主AI框架中的TRiSM，每一支柱均针对自主LLMs进行了情境化分析。我们识别了独特的威胁向量，并引入了一套全面的风险分类体系，辅以展示现实世界漏洞的案例研究。此外，本文还调查了分布式LLM智能体系统中的信任构建机制、透明度与监督技术，以及最先进的可解释性策略。同时，回顾了评估信任、可解释性及以人为中心性能的指标，并指出了开放基准测试的挑战。通过加密、对抗防御及遵守不断演进的AI法规，解决了安全与隐私问题。文章最后提出了负责任自主AI的发展路线图，建议研究新兴多智能体系统如何与稳健的TRiSM原则对齐，以实现安全、可问责且透明的部署。

English

Agentic AI systems, built on large language models (LLMs) and deployed in multi-agent configurations, are redefining intelligent autonomy, collaboration and decision-making across enterprise and societal domains. This review presents a structured analysis of Trust, Risk, and Security Management (TRiSM) in the context of LLM-based agentic multi-agent systems (AMAS). We begin by examining the conceptual foundations of agentic AI, its architectural differences from traditional AI agents, and the emerging system designs that enable scalable, tool-using autonomy. The TRiSM in the agentic AI framework is then detailed through four pillars governance, explainability, ModelOps, and privacy/security each contextualized for agentic LLMs. We identify unique threat vectors and introduce a comprehensive risk taxonomy for the agentic AI applications, supported by case studies illustrating real-world vulnerabilities. Furthermore, the paper also surveys trust-building mechanisms, transparency and oversight techniques, and state-of-the-art explainability strategies in distributed LLM agent systems. Additionally, metrics for evaluating trust, interpretability, and human-centered performance are reviewed alongside open benchmarking challenges. Security and privacy are addressed through encryption, adversarial defense, and compliance with evolving AI regulations. The paper concludes with a roadmap for responsible agentic AI, proposing research directions to align emerging multi-agent systems with robust TRiSM principles for safe, accountable, and transparent deployment.