TrajMind is a framework for diagnosing collective anomalies in urban trajectory data. It separates continuous screening from on-demand diagnosis, using a fast text-only path for alerts and a slow vision‑language path that chains role‑specialized LoRA adapters for detailed, evidence‑backed what‑who‑where‑when records. Experiments show the slow path outperforms baselines by over 15 percentage points in typing and 13 in localization, while the fast path cuts latency by 41% and retains high accuracy.
arXiv:2606. 07054v1 Announce Type: cross Abstract: Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level monitoring.
The paper introduces TITAnD, a Trajectory Image Transformer that converts dense and sparse GPS trajectories into a Hyperspectral Trajectory Image (HTI) and applies vision-based classification and segmentation for anomaly detection. It employs a Cyclic Factorized Transformer (CFT) that splits attention along within-day and across-day axes, drastically reducing computational cost and enabling multi-month analysis. Empirical results show TITAnD outperforms existing sparse and dense benchmarks, achieving higher AUC-PR and faster inference than comparable Transformers.
The paper introduces VisAnomBench, a new benchmark that augments public time‑series datasets with high‑quality natural‑language anomaly explanations generated by large vision‑language models. Using this benchmark, the authors fine‑tune a parameter‑efficient VLM called VisAnomReasoner, which achieves significantly higher precision and F1 scores than existing baselines on VisAnomBench and also generalizes well to the TSB‑AD‑U benchmark.
MAADBench is a refreshable benchmark for anomaly detection in multi‑agent systems powered by large language models. It addresses the challenge of keeping benchmarks current by sampling and coupling generative tasks, generating trace data under configurable LLM backbones, and automatically providing deterministic step‑level labels. The authors evaluated 25 anomaly‑detection methods on 5,200 labeled traces, finding that existing approaches depend heavily on supervision, struggle with subtle MAS‑specific anomalies, and lack robustness across different LLM backbones.
arXiv:2605. 22779v2 Announce Type: replace-cross Abstract: Production systems generate millions of log lines daily, yet most anomaly detectors operate at the session or window-level, flagging groups of lines rather than identifying the specific message responsible.
arXiv:2609.07941v2 Announce Type: replace Abstract: In this paper, we propose ReactVAU, a Slow-Fast Decoupled Framework for real-time streaming Video Anomaly Understanding (VAU). Existing VAU methods...
DriftNet is a dual‑head trajectory Transformer designed to detect and localize prompt injection attacks in large language model agents. It processes logged tool‑call trajectories, classifying each as compromised or not while labeling every step as benign, injection point, hijacked, or failed injection. On the AgentDrift benchmark, DriftNet achieves high accuracy, with an F1 score of 0.983, 98.7% exact injection‑point recovery, and low false‑alarm rates.
arXiv:2602. 13807v2 Announce Type: replace Abstract: Time series anomaly detection is critical in many real-world applications, where effective solutions must localize anomalous regions and support reliable decision-making under complex settings.
arXiv:2608. 12441v1 Announce Type: cross Abstract: Deep learning detectors for anomalies in dynamic graphs have reached strong accuracy, yet they remain opaque: when an edge is flagged, the analyst receives a score but no reason.
MoG-VLM is a motion‑guided vision‑language model designed for efficient video anomaly detection. It uses a lightweight motion signal, Temporal Gradient Magnitude, to perform content‑aware sampling and activates dense multi‑frame VLM reasoning only around frames with high anomaly likelihood via a hierarchical dual‑stream design. The method achieves state‑of‑the‑art AUC‑ROC scores on four benchmarks and delivers a 1.31× inference speedup on XD‑Violence.
arXiv:2608. 03391v1 Announce Type: new Abstract: Precise anomaly localization over long-context time series is a crucial task in monitoring applications across clinical care, industrial operations, financial services, and logistics, where brief evidence may hide inside long spans of high-frequency data.
arXiv:2606. 14724v1 Announce Type: cross Abstract: Video anomaly detection in surveillance settings must balance detection accuracy against real-time throughput, a tension that existing methods address either through stronger feature extractors or more efficient architectures, but rarely both.