Related papers: Detecting Silent Failures in Multi-Agentic AI Traj…

This paper presents a temporal expression language for monitoring AI agent behavior, enabling systematic error-detection of LLM-based agentic systems that exhibit variable outputs due to stochastic generation processes. Drawing from…

As multi-agent systems powered by Large Language Models (LLMs) are increasingly adopted in real-world workflows, users with diverse technical backgrounds are now building and refining their own agentic processes. However, these systems can…

Multimodal Large Language Models (MLLMs) are evolving from passive observers into active agents, solving problems through Visual Expansion (invoking visual tools) and Knowledge Expansion (open-web search). However, existing evaluations fall…

Detecting cognitive biases in large language models (LLMs) is a fascinating task that aims to probe the existing cognitive biases within these models. Current methods for detecting cognitive biases in language models generally suffer from…

Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who…

Machine learning (ML) is crucial in network anomaly detection for proactive threat hunting, reducing detection and response times significantly. However, challenges in model training, maintenance, and frequent false positives impact its…

Developing autonomous agents for web-based tasks is a core challenge in AI. While Large Language Model (LLM) agents can interpret complex user requests, they often operate as black boxes, making it difficult to diagnose why they fail or how…

With the rapid development of multi-cloud environments, it is increasingly important to ensure the security and reliability of intelligent monitoring systems. In this paper, we propose an anomaly detection and early warning mechanism for…

Multimodal artificial intelligence (AI) systems have the potential to enhance clinical decision-making by interpreting various types of medical data. However, the effectiveness of these models across all medical fields is uncertain. Each…

We address the problem of runtime trajectory anomaly detection, a critical capability for enabling trustworthy LLM agents. Current safety measures predominantly focus on static input/output filtering. However, we argue that ensuring LLM…

Anomaly detection (AD) is essential in areas such as fraud detection, network monitoring, and scientific research. However, the diversity of data modalities and the increasing number of specialized AD libraries pose challenges for…

Emerging AI systems in behavioral health and psychiatry use multi-step or multi-agent LLM pipelines for tasks like assessing self-harm risk and screening for depression. However, common evaluation approaches, like LLM-as-a-judge, do not…

Benefiting from generalizability of vision-language models (VLMs) such as CLIP, many zero-/few-shot anomaly detection (AD) approaches have achieved impressive detection performance across various datasets. Nevertheless, they require…

Benchmarking anomaly detection approaches for multivariate time series is a challenging task due to a lack of high-quality datasets. Current publicly available datasets are too small, not diverse and feature trivial anomalies, which hinders…

Autonomous LLM agents generate multi-step action plans that can fail due to contextual misalignment or structural incoherence. Existing anomaly detection methods are ill-suited for this challenge: mean-pooling embeddings dilutes anomalous…

Anomaly detection on text-rich graphs is widely prevalent in real life, such as detecting incorrectly assigned academic papers to authors and detecting bots in social networks. The remarkable capabilities of large language models (LLMs)…

The reliable execution of high-level missions in multi-robot systems with heterogeneous agents, requires robust methods for detecting spurious behaviors. In this paper, we address the challenge of identifying spurious executions of plans…

Human drivers can recognise fast abnormal driving situations to avoid accidents. Similar to humans, automated vehicles are supposed to perform anomaly detection. In this work, we propose the spatio-temporal graph auto-encoder for learning…

Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks. As MAS become increasingly autonomous in various safety-critical tasks, detecting malicious agents has become a critical…

This project explores large language models (LLMs) for anomaly detection across heterogeneous log sources. Traditional intrusion detection systems suffer from high false positive rates, semantic blindness, and data scarcity, as logs are…