paperJune 2025Unreviewed

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

Shaina Raza, Ranjan Sapkota, Manoj Karkee, Christos Emmanouilidis

AI Open

Abstract

Agentic AI systems, built upon large language models (LLMs) and deployed in multi-agent configurations, are redefining intelligence, 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 and highlight its architectural distinctions from traditional AI

Cite

@techreport{raza2025trism,
  title = {{TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems}},
  author = {Shaina Raza and Ranjan Sapkota and Manoj Karkee and Christos Emmanouilidis},
  year = {2025},
  month = jun,
  institution = {AI Open},
  eprint = {2506.04133},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2506.04133},
  url = {https://www.semanticscholar.org/paper/753736d18fa9bf3ed730836b30b89bf5653cd8dd}
}