# Video Models Can Reason with Verifiable Rewards

arXiv: https://arxiv.org/abs/2605.15458 · HTML: https://mlsanity.com/paper/2605.15458/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 41 of its 47 references that are in the map.
- First posted on arXiv 14 May 2026.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 30 of 41)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild](https://mlsanity.com/paper/2503.18892/) (2025)
- [Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model](https://mlsanity.com/paper/2503.24290/) (2025)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [Diffusion Probabilistic Modeling for Video Generation](https://mlsanity.com/paper/2203.09481/) (2022)
- [Video models are zero-shot learners and reasoners](https://mlsanity.com/paper/2509.20328/) (2025)
- [How Far is Video Generation from World Model: A Physical Law Perspective](https://mlsanity.com/paper/2411.02385/) (2024)
- [Do generative video models understand physical principles?](https://mlsanity.com/paper/2501.09038/) (2025)
- [HunyuanVideo 1.5 Technical Report](https://mlsanity.com/paper/2511.18870/) (2025)
- [Flow Matching Policy Gradients](https://mlsanity.com/paper/2507.21053/) (2025)
- [BranchGRPO: Stable and Efficient GRPO with Structured Branching in Diffusion Models](https://mlsanity.com/paper/2509.06040/) (2025)
- [Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems](https://mlsanity.com/paper/2504.02918/) (2025)
- [Are Video Models Ready as Zero-Shot Reasoners? An Empirical Study with the MME-CoF Benchmark](https://mlsanity.com/paper/2510.26802/) (2025)
- [Thinking with Video: Video Generation as a Promising Multimodal Reasoning Paradigm](https://mlsanity.com/paper/2511.04570/) (2025)
- [ARM: Adaptive Reasoning Model](https://mlsanity.com/paper/2505.20258/) (2025)
- [A Very Big Video Reasoning Suite](https://mlsanity.com/paper/2602.20159/) (2026)
- [VChain: Chain-of-Visual-Thought for Reasoning in Video Generation](https://mlsanity.com/paper/2510.05094/) (2025)
- [Deductive Beam Search: Decoding Deducible Rationale for Chain-of-Thought Reasoning](https://mlsanity.com/paper/2401.17686/) (2024)
- [VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward](https://mlsanity.com/paper/2603.26599/) (2026)

## Built on by (most cited first, 9 of 9)

- [VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System](https://mlsanity.com/paper/2607.27380/) (2026)
- [VBVR-Pro: A Scalable and Verifiable Suite for Native Visual Reasoning](https://mlsanity.com/paper/2608.26105/) (2026)
- [VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization](https://mlsanity.com/paper/2606.02564/) (2026)
- [VGI-Bench: Probing Visual Intelligence in Video Generation Models](https://mlsanity.com/paper/2608.19583/) (2026)
- [Visual General Intelligence: A White Paper](https://mlsanity.com/paper/2608.25924/) (2026)
- [Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision](https://mlsanity.com/paper/2609.04203/) (2026)
- [The Low-Rank Structure of VLA Reinforcement Learning](https://mlsanity.com/paper/2609.34599/) (2026)
- [Learning via Self-Consistency for Diffusion-based Video Reasoning](https://mlsanity.com/paper/2609.36826/) (2026)
- [ProAR: Learning Prospective Reasoning with Autoregressive Video Models](https://mlsanity.com/paper/2610.03664/) (2026)

## Abstract (arXiv)

Video diffusion models have made rapid progress in perceptual realism and temporal coherence, but they remain primarily optimized for plausible generation rather than verifiable reasoning. This limitation is especially pronounced in tasks where generated videos must satisfy explicit spatial, temporal, or logical constraints. Inspired by the role of reinforcement learning with verifiable rewards (RLVR) in reasoning-oriented language models, we introduce VideoRLVR, a practical recipe for optimizing video diffusion models with rule-based feedback. VideoRLVR formulates video reasoning as the generation of verifiable visual trajectories and consists of an SDE-GRPO optimization backbone, dense decomposed rewards, and an Early-Step Focus strategy for efficient training. The Early-Step Focus strategy restricts policy optimization to the early denoising phase, reducing training latency by about 40% while preserving performance. We evaluate VideoRLVR on Maze, FlowFree, and Sokoban, three procedurally generated domains with objective success criteria. Across these tasks, VideoRLVR consistently improves over supervised fine-tuning baselines, with dense decomposed rewards proving especially important in low-success-rate settings. Our RL-optimized model also outperforms the evaluated proprietary and open-source video generation models on these verifiable reasoning benchmarks and out-of-domain benchmarks. These results suggest that verifiable RL can move video models beyond perceptual imitation toward more reliable rule-consistent visual reasoning.