# Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought

arXiv: https://arxiv.org/abs/2505.19877 · HTML: https://mlsanity.com/paper/2505.19877/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning.
- Builds on 38 of its 92 references that are in the map.
- First posted on arXiv 26 May 2025.

## Placed in

- LLM reasoning / [Chain-of-thought reasoning for driving](https://mlsanity.com/lr/chain-of-thought-reasoning-for-driving/)
- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

## Builds on (most cited first, 30 of 38)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Video-LLaVA: Learning United Visual Representation by Alignment Before Projection](https://mlsanity.com/paper/2311.10122/) (2023)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models](https://mlsanity.com/paper/2306.05424/) (2023)
- [VideoChat: Chat-Centric Video Understanding](https://mlsanity.com/paper/2305.06355/) (2023)
- [LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention](https://mlsanity.com/paper/2303.16199/) (2023)
- [Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models](https://mlsanity.com/paper/2503.06749/) (2025)
- [LLaVA-Video: Video Instruction Tuning With Synthetic Data](https://mlsanity.com/paper/2410.02713/) (2024)
- [VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding](https://mlsanity.com/paper/2501.13106/) (2025)
- [Long Context Transfer from Language to Vision](https://mlsanity.com/paper/2406.16852/) (2024)
- [Video-R1: Reinforcing Video Reasoning in MLLMs](https://mlsanity.com/paper/2503.21776/) (2025)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning](https://mlsanity.com/paper/2404.16994/) (2024)
- [VideoChat-R1: Enhancing Spatio-Temporal Perception via Reinforcement Fine-Tuning](https://mlsanity.com/paper/2504.06958/) (2025)
- [VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling](https://mlsanity.com/paper/2501.00574/) (2024)
- [InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling](https://mlsanity.com/paper/2501.12386/) (2025)
- [LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs](https://mlsanity.com/paper/2501.06186/) (2025)
- [Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding](https://mlsanity.com/paper/2503.13377/) (2025)
- [Streaming Video Question-Answering with In-context Video KV-Cache Retrieval](https://mlsanity.com/paper/2503.00540/) (2025)
- [Streaming Video Understanding and Multi-round Interaction with Memory-enhanced Knowledge](https://mlsanity.com/paper/2501.13468/) (2025)
- [Holmes-VAU: Towards Long-term Video Anomaly Understanding at Any Granularity](https://mlsanity.com/paper/2412.06171/) (2024)
- [Vision-R1: Evolving Human-Free Alignment in Large Vision-Language Models via Vision-Guided Reinforcement Learning](https://mlsanity.com/paper/2503.18013/) (2025)
- [Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM](https://mlsanity.com/paper/2406.12235/) (2024)

## Built on by (most cited first, 24 of 24)

- [Video-R2: Reinforcing Consistent and Grounded Reasoning in Multimodal Language Models](https://mlsanity.com/paper/2511.23478/) (2025)
- [Video-LMM Post-Training: A Deep Dive into Video Reasoning with Large Multimodal Models](https://mlsanity.com/paper/2510.05034/) (2025)
- [A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding](https://mlsanity.com/paper/2505.21962/) (2025)
- [CueBench: Advancing Unified Understanding of Context-Aware Video Anomalies in Real-World](https://mlsanity.com/paper/2511.00613/) (2025)
- [Learning to Watch: Active Video Anomaly Understanding via Interleaved Policy Optimization](https://mlsanity.com/paper/2607.00622/) (2026)
- [TAU-R1: Visual Language Model for Traffic Anomaly Understanding](https://mlsanity.com/paper/2603.19098/) (2026)
- [Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models](https://mlsanity.com/paper/2605.02912/) (2026)
- [MAVEN: A Multi-stage Agentic Annotation Pipeline for Video Reasoning Tasks](https://mlsanity.com/paper/2605.21917/) (2026)
- [ESOM: Efficiently Understanding Streaming Video Anomalies with Open-world Dynamic Definitions](https://mlsanity.com/paper/2604.07772/) (2026)
- [Is Video Anomaly Detection Misframed? Evidence from LLM-Based and Multi-Scene Models](https://mlsanity.com/paper/2605.12725/) (2026)
- [TAU-Bench: From Anomaly Instance Tracking to Fine-Grained Video Anomaly Understanding](https://mlsanity.com/paper/2608.05699/) (2026)
- [From Detection to Understanding: TAR and TAR-Bench for Multi-Task Traffic Anomaly Reasoning](https://mlsanity.com/paper/2608.10317/) (2026)
- [UniTraffic-Agent: Unified Traffic Video Reasoning for AI City Challenge 2026 Track 3 with Two Out-of-Domain Evaluations](https://mlsanity.com/paper/2608.13031/) (2026)
- [DAMS:Dual-Branch Adaptive Multiscale Spatiotemporal Framework for Video Anomaly Detection](https://mlsanity.com/paper/2507.20629/) (2025)
- [SRVAU-R1: Enhancing Video Anomaly Understanding via Reflection-Aware Learning](https://mlsanity.com/paper/2602.01004/) (2026)
- [LATERN: Test-Time Context-Aware Explainable Video Anomaly Detection](https://mlsanity.com/paper/2605.15054/) (2026)
- [O-VAD: Industrial Video Anomaly Detection through Object-Centric Tracking and Reasoning](https://mlsanity.com/paper/2607.18142/) (2026)
- [TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly Understanding](https://mlsanity.com/paper/2608.25935/) (2026)
- [Parser-Free VLM Verification for Federated Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2609.07455/) (2026)
- [ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding](https://mlsanity.com/paper/2609.07941/) (2026)
- [Test-time Reinforcement Learning for Anomalous Video Understanding](https://mlsanity.com/paper/2609.26099/) (2026)
- [Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding](https://mlsanity.com/paper/2610.01754/) (2026)
- [Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization](https://mlsanity.com/paper/2610.02019/) (2026)
- [trACT: temporal revelation Airborne Camera Trap](https://mlsanity.com/paper/2610.09417/) (2026)

## Abstract (arXiv)

Recent advancements in reasoning capability of Multimodal Large Language Models (MLLMs) demonstrate its effectiveness in tackling complex visual tasks. However, existing MLLM-based Video Anomaly Detection (VAD) methods remain limited to shallow anomaly descriptions without deep reasoning. In this paper, we propose a new task named Video Anomaly Reasoning (VAR), which aims to enable deep analysis and understanding of anomalies in the video by requiring MLLMs to think explicitly before answering. To this end, we propose Vad-R1, an end-to-end MLLM-based framework for VAR. Specifically, we design a Perception-to-Cognition Chain-of-Thought (P2C-CoT) that simulates the human process of recognizing anomalies, guiding the MLLM to reason anomaly step-by-step. Based on the structured P2C-CoT, we construct Vad-Reasoning, a dedicated dataset for VAR. Furthermore, we propose an improved reinforcement learning algorithm AVA-GRPO, which explicitly incentivizes the anomaly reasoning capability of MLLMs through a self-verification mechanism with limited annotations. Experimental results demonstrate that Vad-R1 achieves superior performance, outperforming both open-source and proprietary models on VAD and VAR tasks. Codes and datasets will be released at https://github.com/wbfwonderful/Vad-R1.