VideoGen-Agent: Reinforcing Video Generation Agents

arXiv:2609.24997 · cs.CV · Submitted 2026-09-21 · Read on arXiv

cs.CV

Submitted: 2026-09-21

Updated: 2026-10-05

Code: https://github.com/genmoai/models

Terminology

• Verification — 26× in this paper · explained in 2 episodes
• Grounding — 21× in this paper · explained in 3 episodes
• Procedural Knowledge — 21× in this paper · explained in 2 episodes
• Multi-Entity Identity — 18× in this paper
• Physics Simulation — 16× in this paper
• Compositional Scene — 14× in this paper
• Reinforcement Learning — 14× in this paper · explained in 4 episodes
• Single-Entity Identity — 14× in this paper
• Benchmark — 9× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• GRPO — 7× in this paper · explained in 6 episodes
• Commentary — 6× in this paper · explained in 2 episodes
• Consistency — 5× in this paper · explained in 3 episodes
• Fine-Tuning — 5× in this paper · explained in 5 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Optical Flow — 4× in this paper · explained in 2 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Diffusion Model — 3× in this paper · explained in 8 episodes
• Diffusion Models — 3× in this paper · explained in 6 episodes
• Evaluation Dimensions — 3× in this paper · explained in 3 episodes
• Generative Model — 3× in this paper · explained in 2 episodes
• Generative Models — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Core — 2× in this paper · explained in 2 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Agentic Framework — 1× in this paper · explained in 6 episodes
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Agentic Search — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• GRPO Objective — 1× in this paper · explained in 2 episodes
• Group Relative Policy Optimization — 1× in this paper
• Group Relative Policy Optimization (GRPO) — 1× in this paper · explained in 5 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Momentum transfer — 1× in this paper · explained in 2 episodes
• Multi-Agent System — 1× in this paper · explained in 6 episodes
• Reasoning Traces — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Qwen3-VL Technical Report
• Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
• Gen-Searcher: Reinforcing Agentic Search for Image Generation
• NEWTON: Agentic Planning for Physically Grounded Video Generation
• Seedance 1.0: Exploring the Boundaries of Video Generation Models
• T2VPhysBench: A First-Principles Benchmark for Physical Consistency in Text-to-Video Generation
• Ctrl-World: A Controllable Generative World Model for Robot Manipulation
• ViMax: Agentic Video Generation
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
• ToRL: Scaling Tool-Integrated RL
• The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• Movie Gen: A Cast of Media Foundation Models
• Seedance 2.0: Advancing Video Generation for World Complexity
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
• Wan: Open and Advanced Large-Scale Video Generative Models
• Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
• Loong: Generating Minute-level Long Videos with Autoregressive Language Models

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models