TrajAD: Trajectory Anomaly Detection for Trustworthy LLM Agents
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 agents reliability requires auditing the intermediate execution process. In this work, we formulate the task of Trajectory Anomaly Detection. The goal is not merely detection, but precise error localization. This capability is essential for enabling efficient rollback-and-retry. To achieve this, we construct TrajBench, a dataset synthesized via a perturb-and-complete strategy to cover diverse procedural anomalies. Using this benchmark, we investigate the capability of models in process supervision. We observe that general-purpose LLMs, even with zero-shot prompting, struggle to identify and localize these anomalies. This reveals that generalized capabilities do not automatically translate to process reliability. To address this, we propose TrajAD, a specialized verifier trained with fine-grained process supervision. Our approach outperforms baselines, demonstrating that specialized supervision is essential for building trustworthy agents.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly DetectionSimilar Papers 제목 키워드 기반
Trustworthy Anomaly Detection: A Survey
Anomaly detection has a wide range of real-world applications, such as bank fraud detection and cyber intrusion detection. In the past decade, a variety of anomaly detection models have been developed, which lead to big …
Anomaly DetectionFairnessFraud DetectionIntrusion Detection+1Intention-aware Hierarchical Diffusion Model for Long-term Trajectory Anomaly Detection
Long-term trajectory anomaly detection is a challenging problem due to the diversity and complex spatiotemporal dependencies in trajectory data. Existing trajectory anomaly detection methods fail to simultaneously consid…
Anomaly DetectionAnomaly Detection in Multi-Agent Trajectories for Automated Driving
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-en…
Anomaly DetectionA Multi-perspective Approach To Anomaly Detection For Self-aware Embodied Agents
This paper focuses on multi-sensor anomaly detection for moving cognitive agents using both external and private first-person visual observations. Both observation types are used to characterize agents' motion in a given…
Anomaly DetectionReeFRAME: Reeb Graph based Trajectory Analysis Framework to Capture Top-Down and Bottom-Up Patterns of Life
In this paper, we present ReeFRAME, a scalable Reeb graph-based framework designed to analyze vast volumes of GPS-enabled human trajectory data generated at 1Hz frequency. ReeFRAME models Patterns-of-life (PoL) at both t…
Anomaly Detection