AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding

• URL: http://arxiv.org/abs/2608.03779v1
• Date: Tue, 04 Aug 2026 15:01:59 GMT
• Title: AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding
• Abstract summary: We present AgenticVAU, a training-free multi-agent framework for video anomaly understanding.<n>Four specialized agents are introduced to handle visual-rule construction, search planning, video observation, and final decision.<n>AgenticVAU interleaves broad temporal exploration, dense local verification, and cross-interval comparison until sufficient evidence is collected.
• Score: 14.12320671130862
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Video anomaly understanding (VAU) focuses on comprehensively interpreting abnormal events in videos, requiring models to identify anomalous occurrences, discover their supporting evidence, and explain the underlying causes beyond simple anomaly detection. Existing VAU methods often rely on specialized training or limited observations, restricting generalization or evidence coverage. Although single-agent alternatives support adaptive video observation, they still integrate exploration, observation, and decision-making within a unified reasoning process, offering limited role specialization and structured evidence coordination. To address these limitations, we present AgenticVAU, a training-free multi-agent framework that casts VAU as an explore--verify process, where the system first discovers potential anomalies and then verifies them through targeted observations. To achieve this, four specialized agents are introduced to handle visual-rule construction, search planning, video observation, and final decision, respectively. These agents communicate through an anchor registry, a shared evidence memory that binds each observation. Guided by this agent framework, AgenticVAU interleaves broad temporal exploration, dense local verification, and cross-interval comparison until sufficient evidence is collected. We conduct extensive experiments on the ECVA, UCF-Crime, and MSAD subsets of VAU-Bench, the results show that AgenticVAU outperforms zero-shot inference and reinforcement learning-based baselines, demonstrating the value of multi-agent collaboration for video anomaly understanding.

Related papers

• Beyond Hazard Resemblance: Contrastive Event Adjudication for Training-Free Video Anomaly Detection [42.523544959534746]
  We propose Contrastive Event Adjudication for training-free Video Anomaly Detection (CEAVAD)<n>CEAVAD shifts the unit of inference from isolated anomaly concepts to falsifiable event hypotheses.<n> Experiments on three widely used VAD benchmarks demonstrate that CEAVAD achieves state-of-the-art performance under the training-free paradigm.
  arXiv  Detail & Related papers  (2026-08-10T17:52:51Z)
• Glance, Scrutinize, and Think: Advancing Video Anomaly Detection from Training-Free to Agentic Reasoning [27.676141768874732]
  Video Anomaly Detection (VAD) aims to identify anomalous events and localize their temporal intervals.<n>Existing approaches exhibit a "when-what" dissociation: traditional methods localize when anomalies occur but lack semantic understanding.<n>We propose Glance then Scrutinize (GtS), a training-free framework using static and dynamic textual guidance.<n>Experiments show that GtS substantially surpasses training-free baselines, while the agentic model delivers both higher accuracy and faster inference.
  arXiv  Detail & Related papers  (2026-08-07T17:07:49Z)
• Unleashing Multimodal Large Language Models for Training-free HOI Detection in the Wild [49.77540427384148]
  We present AgentHOI, a training-free, agentic framework that transfers the generalist multimodal reasoning capabilities of foundation models to HOI detection in the wild.<n>To address the challenges of incomplete interaction discovery and ambiguous localization in complex scenes, we introduce two key mechanisms.<n>AgentHOI achieves superior performance over state-of-the-art supervised and weakly supervised methods in real-world settings.
  arXiv  Detail & Related papers  (2026-07-15T14:30:20Z)
• Structured Evidence Selection for Weakly Supervised Video Anomaly Detection [24.113971346791942]
  Weakly supervised video anomaly detection relies solely on video-level labels for training.<n>We propose a Structured Evidence Selection framework (SESAD) that reformulates anomaly detection as a structured reasoning process.<n>SESAD reorganizes clip representations into semantically structured candidate evidence and performs context-conditioned selection under scene and action constraints.
  arXiv  Detail & Related papers  (2026-07-11T13:01:01Z)
• RT-SDGOD: Real-Time Single-Domain Generalized Object Detection [29.73970506841414]
  Under real-time constraints, weather and imaging variations induce significant distribution shifts, severely degrading detectors.<n>We introduce Real-Time Single-Domain Generalized Object Detection (RT-SDGOD)<n>Our method achieves better generalization performance than existing approaches across multiple unseen target domains.
  arXiv  Detail & Related papers  (2026-06-08T11:39:18Z)
• Causal Bootstrapped Alignment for Unsupervised Video-Based Visible-Infrared Person Re-Identification [52.784239635604735]
  VVI-ReID is a critical technique for all-day surveillance, where temporal information provides additional cues beyond static images.<n>Existing approaches rely heavily on fully supervised learning with expensive cross-modality annotations, limiting scalability.<n>We propose a Causal Bootstrapped Alignment framework that explicitly exploits inherent video priors.
  arXiv  Detail & Related papers  (2026-04-17T02:15:59Z)
• Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection [52.5174167737992]
  Video anomaly detection (VAD) aims to identify abnormal events in videos.<n>We propose SteerVAD, which advances MLLM-based VAD by shifting from passively reading to actively steering and rectifying internal representations.<n>Our method achieves state-of-the-art performance among tuning-free approaches requiring only 1% of training data.
  arXiv  Detail & Related papers  (2026-02-27T13:48:50Z)
• Advancing Adaptive Multi-Stage Video Anomaly Reasoning: A Benchmark Dataset and Method [96.63801368613177]
  We present a new task that elevates video anomaly analysis from descriptive understanding to structured, multi-stage reasoning.<n>We present a new dataset with 8,641 videos, totaling more than 50,000 samples, making it one of the largest datasets for video anomaly understanding.<n>Building upon the proposed task and dataset, we develop an end-to-end MLLM-based VAR model termed Vad-R1-Plus, which supports adaptive hierarchical reasoning and risk-aware decision making.
  arXiv  Detail & Related papers  (2026-01-15T08:09:04Z)
• Unlocking Vision-Language Models for Video Anomaly Detection via Fine-Grained Prompting [17.850029260662648]
  We propose ASK-Hint, a structured prompting framework for video anomaly detection.<n>Our approach organizes prompts into semantically coherent groups and formulates fine-grained guiding questions.<n>Experiments on UCF-Crime and XD-Violence show that ASK-Hint consistently improves AUC over prior baselines.
  arXiv  Detail & Related papers  (2025-10-02T16:06:31Z)
• Open-Vocabulary Video Anomaly Detection [57.552523669351636]
  Video anomaly detection (VAD) with weak supervision has achieved remarkable performance in utilizing video-level labels to discriminate whether a video frame is normal or abnormal. Recent studies attempt to tackle a more realistic setting, open-set VAD, which aims to detect unseen anomalies given seen anomalies and normal videos. This paper takes a step further and explores open-vocabulary video anomaly detection (OVVAD), in which we aim to leverage pre-trained large models to detect and categorize seen and unseen anomalies.
  arXiv  Detail & Related papers  (2023-11-13T02:54:17Z)
• Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models [33.43062232461652]
  Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems. This survey extends the conventional scope of VAD beyond unsupervised methods, encompassing a broader spectrum termed Generalized Video Anomaly Event Detection (GVAED)
  arXiv  Detail & Related papers  (2023-02-10T07:11:37Z)
• Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video [128.41392860714635]
  We introduce Weakly-Supervised Snoma-Temporally Detection (WSSTAD) in surveillance video. WSSTAD aims to localize a-temporal tube (i.e. sequence of bounding boxes at consecutive times) that encloses abnormal event. We propose a dual-branch network which takes as input proposals with multi-granularities in both spatial-temporal domains.
  arXiv  Detail & Related papers  (2021-08-09T06:11:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.