# VideoGen-Eval: Agent-based System for Video Generation Evaluation

arXiv: https://arxiv.org/abs/2503.23452 · HTML: https://mlsanity.com/paper/2503.23452/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 60 of its 73 references that are in the map.
- First posted on arXiv 30 Mar 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 30 of 60)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [HunyuanVideo: A Systematic Framework For Large Video Generative Models](https://mlsanity.com/paper/2412.03603/) (2024)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2310.19512/) (2023)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives](https://mlsanity.com/paper/2211.04894/) (2022)

## Built on by (most cited first, 23 of 23)

- [OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation](https://mlsanity.com/paper/2505.20292/) (2025)
- [VideoScore2: Think before You Score in Generative Video Evaluation](https://mlsanity.com/paper/2509.22799/) (2025)
- [LPM 1.0: Video-based Character Performance Model](https://mlsanity.com/paper/2604.07823/) (2026)
- [Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning](https://mlsanity.com/paper/2601.04153/) (2026)
- [Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow](https://mlsanity.com/paper/2510.05836/) (2025)
- [LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation](https://mlsanity.com/paper/2510.26412/) (2025)
- [Evolution of Video Generative Foundations](https://mlsanity.com/paper/2604.06339/) (2026)
- [ViBES: A Conversational Agent with Behaviorally-Intelligent 3D Virtual Body](https://mlsanity.com/paper/2512.14234/) (2025)
- [VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing](https://mlsanity.com/paper/2608.05485/) (2026)
- [HarnessEval-W: Agentifying the Evaluation of Visual Worlds](https://mlsanity.com/paper/2608.16859/) (2026)
- [Gloria: Consistent Character Video Generation via Content Anchors](https://mlsanity.com/paper/2603.29931/) (2026)
- [How Far Are Video Models from True Multimodal Reasoning?](https://mlsanity.com/paper/2604.19193/) (2026)
- [Open Evaluation Agent: Efficient and Promptable Evaluation of Visual Generative Models](https://mlsanity.com/paper/2608.09666/) (2026)
- [IE-Critic-R1: Advancing the Explanatory Measurement of Text-Driven Image Editing for Human Perception Alignment](https://mlsanity.com/paper/2511.18055/) (2025)
- [End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstruction](https://mlsanity.com/paper/2603.14435/) (2026)
- [RoboGaze: Evaluating Robot World Models via Structured Vision-Language Analysis](https://mlsanity.com/paper/2606.28385/) (2026)
- [Test-Time Scaling in Multimodal Foundation Models: A Comprehensive Survey of Generation and Reasoning](https://mlsanity.com/paper/2606.08231/) (2026)
- [A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talks](https://mlsanity.com/paper/2606.28531/) (2026)
- [DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation](https://mlsanity.com/paper/2609.00646/) (2026)
- [VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinement](https://mlsanity.com/paper/2609.03153/) (2026)
- [PDMD: Projected Distribution Matching Distillation for Video Diffusion Models](https://mlsanity.com/paper/2609.35768/) (2026)
- [Token-Level Video Reinforcement Learning](https://mlsanity.com/paper/2610.01973/) (2026)
- [DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation](https://mlsanity.com/paper/2610.02188/) (2026)

## Abstract (arXiv)

The rapid advancement of video generation has rendered existing evaluation systems inadequate for assessing state-of-the-art models, primarily due to simple prompts that cannot showcase the model's capabilities, fixed evaluation operators struggling with Out-of-Distribution (OOD) cases, and misalignment between computed metrics and human preferences. To bridge the gap, we propose VideoGen-Eval, an agent evaluation system that integrates LLM-based content structuring, MLLM-based content judgment, and patch tools designed for temporal-dense dimensions, to achieve a dynamic, flexible, and expandable video generation evaluation. Additionally, we introduce a video generation benchmark to evaluate existing cutting-edge models and verify the effectiveness of our evaluation system. It comprises 700 structured, content-rich prompts (both T2V and I2V) and over 12,000 videos generated by 20+ models, among them, 8 cutting-edge models are selected as quantitative evaluation for the agent and human. Extensive experiments validate that our proposed agent-based evaluation system demonstrates strong alignment with human preferences and reliably completes the evaluation, as well as the diversity and richness of the benchmark.