Toward Autonomous LLM-Based AI Agents for Predictive Maintenance: State of the Art, Challenges, and Future Perspectives

Abstract

Recent advances in Large Language Models (LLMs) enable agentic systems that combine perception, reasoning, and action across the enitre Predictive Maintenance (PdM) lifecycle, including machine fault diagnosis. However, the literature on LLM-driven agents for PdM remains fragmented and lacks a unified view on contemporary frameworks such as Model Context Procotol. This paper reviews discriminative, generative, and LLM-based approaches for PdM and consolidates fragmented evidence on LLM-driven AI agents. Namely, it introduces agentic AI concepts for PdM and develops an analysis of potential applications, challenges, and risks in light of agency theory, while mapping drivers and barriers to adoption based on recent evidence from industry analysis. Findings indicate near-term value for information and decision-support agents, while higher autonomy needs stronger governance, benchmarks, and safety evidence.