基于智能体与大型语言模型的多模态异常检测：架构、挑战与前景
Agentic and LLM-Based Multimodal Anomaly Detection: Architectures, Challenges, and Prospects.
摘要(中文译文)
异常检测对于维护工业制造、网络安全和自主系统等不同领域中复杂系统的安全性、可靠性和最优性能至关重要。传统方法通常处理单一数据模态，但近年来，多模态检测在动态真实环境中的应用日益增多。本文对智能体人工智能与基于大语言模型的多模态异常检测交叉领域的近期研究进行了全面综述。我们基于智能体架构、推理能力、工具集成和模态范围，对现有研究进行了系统分析和分类。本工作的主要贡献是提出了一种新颖的分类体系，统一了智能体与多模态异常检测方法，并涵盖基准数据集、评估方法、关键挑战和缓解策略。此外，我们识别了主要开放问题，包括数据对齐、可扩展性、可靠性、可解释性和评估标准化。最后，我们展望了未来研究方向，特别强调可信自主智能体、高效多模态融合、人在回路系统以及在安全关键应用中的真实部署。
Abstract
Anomaly detection is crucial in maintaining the safety, reliability, and optimal performance of complex systems across diverse domains, such as industrial manufacturing, cybersecurity, and autonomous systems. While conventional methods typically handle single data modalities, recently, there has been an increase in the application of multimodal detection in dynamic real-world environments. This paper presents a comprehensive review of recent research at the intersection of agentic artificial intelligence and large language-based multimodal anomaly detection. We systematically analyze and categorize existing studies based on the agent architecture, reasoning capabilities, tool integration, and modality scope. The main contribution of this work is a novel taxonomy that unifies agentic and multimodal anomaly detection methods, alongside benchmark datasets, evaluation methods, key challenges, and mitigation strategies. Furthermore, we identify major open issues, including data alignment, scalability, reliability, explainability, and evaluation standardization. Finally, we outline future research directions, with a particular emphasis on trustworthy autonomous agents, efficient multimodal fusion, human-in-the-loop systems, and real-world deployment in safety-critical applications.
如何引用
AMA
Mohammed Ayalew Belay, Amirshayan Haghipour, Adil Rasheed, Pierluigi Salvo Rossi. Agentic and LLM-Based Multimodal Anomaly Detection: Architectures, Challenges, and Prospects.. Sensors (Basel, Switzerland). 2026; doi:10.3390/s26082330.
APA
Mohammed Ayalew Belay, Amirshayan Haghipour, Adil Rasheed, Pierluigi Salvo Rossi (2026). Agentic and LLM-Based Multimodal Anomaly Detection: Architectures, Challenges, and Prospects.. Sensors (Basel, Switzerland). https://doi.org/10.3390/s26082330
GB/T 7714
Mohammed Ayalew Belay, Amirshayan Haghipour, Adil Rasheed, Pierluigi Salvo Rossi. Agentic and LLM-Based Multimodal Anomaly Detection: Architectures, Challenges, and Prospects.[J]. Sensors (Basel, Switzerland), 2026 doi:10.3390/s26082330.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出