# Linguistic Relative Policy Optimization for Video Anomaly Reasoning

arXiv: https://arxiv.org/abs/2607.00654 · HTML: https://mlsanity.com/paper/2607.00654/

## Key facts

- Cited by 2 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 7 of its 56 references that are in the map.
- First posted on arXiv 1 Jul 2026.

## 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, 7 of 7)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [InternLM2 Technical Report](https://mlsanity.com/paper/2403.17297/) (2024)
- [Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM](https://mlsanity.com/paper/2406.12235/) (2024)
- [Training-Free Group Relative Policy Optimization](https://mlsanity.com/paper/2510.08191/) (2025)
- [Verbalized Machine Learning: Revisiting Machine Learning with Language Models](https://mlsanity.com/paper/2406.04344/) (2024)

## Built on by (most cited first, 2 of 2)

- [Representation--Behavior Alignment for Explainable Weakly-Supervised Video Anomaly Detection](https://mlsanity.com/paper/2610.05129/) (2026)
- [RoMod: Temporal Routing Modulation via Mixture-of-Experts for Video Anomaly Detection](https://mlsanity.com/paper/2610.05131/) (2026)

## Abstract (arXiv)

Video anomaly detection (VAD) with multimodal large language models has shown strong potential, yet most existing methods still depend on large-scale annotations or expert-designed priors, limiting their ability to acquire anomaly knowledge with as little human intervention as possible. To address this, we propose Linguistic Relative Policy Optimization (LRPO), which distills group-relative semantic advantages from multiple reasoning trajectories into a linguistically expressed anomaly experience prior, and adapts the model by injecting this prior into the context to steer its output distribution without any parameter updates. LRPO builds two complementary experience representations: general experience captures transferable anomaly preferences across scenarios, while scenario experience models context-dependent anomaly rules for targeted refinement. To further improve the learned experience, we introduce an anomaly alignment reward that guides trajectory optimization to match human risk preferences and reinforce temporally grounded reasoning. Extensive experiments on XD-Violence, UCF-Crime, and UBnormal demonstrate that LRPO significantly outperforms existing state-of-the-art methods under tuning-free settings.