# PARSEE-VAD: Efficient Training-Free Online Video Anomaly Detection via Proposition-Aware Reasoning and Streaming Evidence Escalation

arXiv: https://arxiv.org/abs/2609.33236 · HTML: https://mlsanity.com/paper/2609.33236/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 4 of its 29 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Video understanding with MLLMs](https://mlsanity.com/mllm/video-understanding-with-mllms/)

## Builds on (most cited first, 4 of 4)

- [Flashback: Memory-Driven Zero-shot, Real-time Video Anomaly Detection](https://mlsanity.com/paper/2505.15205/) (2025)
- [MoniTor: Exploiting Large Language Models with Instruction for Online Video Anomaly Detection](https://mlsanity.com/paper/2510.21449/) (2025)
- [SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere](https://mlsanity.com/paper/2605.08003/) (2026)
- [TD-VAD: Breaking Visual Dependence in Video Anomaly Detection with Text-Driven Learning](https://mlsanity.com/paper/2608.11820/) (2026)

## Abstract (arXiv)

Training-free online video anomaly detection (VAD) with frozen multimodal language models faces two coupled challenges: extracting reliable current-window semantics under causal and computational constraints, and maintaining temporal continuity without repeatedly transmitting high-dimensional history. Encoding history through text can compress visual evidence and introduce semantic bias, whereas retaining visual history expands multimodal context. We introduce PARSEE-VAD, a two-module framework that separates semantic evidence acquisition from score-state evolution. Proposition-Aware Reasoning (PAR) extracts structured propositional evidence from the current causal window and conditionally activates more specific queries when coarse evidence warrants further refinement. By sharing a reusable causal visual prefix across queries, PAR reduces redundant computation through selective execution. Streaming Evidence Escalation (SEE) maps the acquired proposition evidence into a compact score-domain event state through current evidence escalation, then propagates only the resulting bounded state across decisions to support temporal continuity. Experiments on four benchmarks demonstrate strong training-free online performance while selective routing reduces specialist computation and score-state propagation remains sparse. These results support a current-first principle for streaming multimodal inference: resolve present semantics first, then use compact historical state only to repair residual continuity gaps.