# VISTA: A Test-Time Self-Improving Video Generation Agent

arXiv: https://arxiv.org/abs/2510.15831 · HTML: https://mlsanity.com/paper/2510.15831/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 85 references that are in the map.
- First posted on arXiv 17 Oct 2025.

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

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (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)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Automatic Prompt Optimization with "Gradient Descent" and Beam Search](https://mlsanity.com/paper/2305.03495/) (2023)
- [Movie Gen: A Cast of Media Foundation Models](https://mlsanity.com/paper/2410.13720/) (2024)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [Optimizing Prompts for Text-to-Image Generation](https://mlsanity.com/paper/2212.09611/) (2022)
- [VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation](https://mlsanity.com/paper/2406.15252/) (2024)
- [NISQA: A Deep CNN-Self-Attention Model for Multidimensional Speech Quality Prediction with Crowdsourced Datasets](https://mlsanity.com/paper/2104.09494/) (2021)
- [A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems](https://mlsanity.com/paper/2508.07407/) (2025)
- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)
- [Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators](https://mlsanity.com/paper/2403.16950/) (2024)
- [MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis](https://mlsanity.com/paper/2412.15322/) (2024)
- [The Prompt Report: A Systematic Survey of Prompt Engineering Techniques](https://mlsanity.com/paper/2406.06608/) (2024)
- [One-Minute Video Generation with Test-Time Training](https://mlsanity.com/paper/2504.05298/) (2025)
- [Improving Text-to-Image Consistency via Automatic Prompt Optimization](https://mlsanity.com/paper/2403.17804/) (2024)
- [Mora: Enabling Generalist Video Generation via A Multi-Agent Framework](https://mlsanity.com/paper/2403.13248/) (2024)
- [High-Fidelity and Freely Controllable Talking Head Video Generation](https://mlsanity.com/paper/2304.10168/) (2023)

## Built on by (most cited first, 30 of 31)

- [VQQA: An Agentic Approach for Video Evaluation and Quality Improvement](https://mlsanity.com/paper/2603.12310/) (2026)
- [RAPO++: Cross-Stage Prompt Optimization for Text-to-Video Generation via Data Alignment and Test-Time Scaling](https://mlsanity.com/paper/2510.20206/) (2025)
- [Planning with Sketch-Guided Verification for Physics-Aware Video Generation](https://mlsanity.com/paper/2511.17450/) (2025)
- [SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents](https://mlsanity.com/paper/2603.08403/) (2026)
- [GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling](https://mlsanity.com/paper/2606.20799/) (2026)
- [Active Intelligence in Video Avatars via Closed-loop World Modeling](https://mlsanity.com/paper/2512.20615/) (2025)
- [BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation](https://mlsanity.com/paper/2603.02816/) (2026)
- [COMIC: Agentic Sketch Comedy Generation](https://mlsanity.com/paper/2603.11048/) (2026)
- [FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling](https://mlsanity.com/paper/2607.19038/) (2026)
- [TransVLM: A Vision-Language Framework and Benchmark for Detecting Any Shot Transitions](https://mlsanity.com/paper/2604.27975/) (2026)
- [SPEAR: Code-Augmented Agentic Prompt Optimization](https://mlsanity.com/paper/2605.26275/) (2026)
- [Bridging Creative Intent and Visual Quality: Creator-Driven Recurrent Video Generation with Agentic Feedback Loops](https://mlsanity.com/paper/2606.18591/) (2026)
- [AgentHOI: Multi-Agent Reasoning for Human-Object-Interaction Video Generation via Implicit Representation Alignment](https://mlsanity.com/paper/2607.22241/) (2026)
- [CineForge: Self-Improving Agents for Long-Horizon Video Generation](https://mlsanity.com/paper/2608.29621/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [WanPE: Towards Cinematic Prompt Enhancement for Modern Text-to-Video Generation](https://mlsanity.com/paper/2609.30221/) (2026)
- [Retrieval, Refinement, and Ranking for Text-to-Video Generation via Prompt Optimization and Test-Time Scaling](https://mlsanity.com/paper/2603.01509/) (2026)
- [Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short](https://mlsanity.com/paper/2606.09380/) (2026)
- [PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory](https://mlsanity.com/paper/2606.16449/) (2026)
- [Test-Time Scaling for Video Diffusion Models via Diagnosis-Guided Candidate Recycling](https://mlsanity.com/paper/2608.29322/) (2026)
- [Motion-Omni: End-to-End Joint Speech and Full-Body Motion for Spoken Dialogue](https://mlsanity.com/paper/2609.04250/) (2026)
- [AgenticGen: Reward-Guided Agentic Video Generation for Advertising](https://mlsanity.com/paper/2609.09187/) (2026)
- [VideoGen-Agent: Reinforcing Video Generation Agents](https://mlsanity.com/paper/2609.24997/) (2026)
- [Don't Read the Log: Execution Traces Contaminate Verifiers in Video-Generation Agents](https://mlsanity.com/paper/2609.28564/) (2026)
- [MVAgent: Multi-Agent Video Generation via Consistent Condition Construction and Shot-Level Policy Optimization](https://mlsanity.com/paper/2609.30609/) (2026)
- [SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Engineering](https://mlsanity.com/paper/2609.34335/) (2026)
- [Towards Unified Evaluation of Prompt Enhancers for Video Generation](https://mlsanity.com/paper/2610.11736/) (2026)
- [PreCoG: Preview-Edit for Efficient Video Correction in Generation-Time](https://mlsanity.com/paper/2610.13174/) (2026)
- [PhysForge: Material-Controllable 3D Reconstruction with Separable Components](https://mlsanity.com/paper/2610.13681/) (2026)
- [TIDE: Trajectory-Informed Skill Distillation for Efficient Text-to-Video Prompt Optimization](https://mlsanity.com/paper/2610.15098/) (2026)

## Abstract (arXiv)

Despite rapid advances in text-to-video synthesis, generated video quality remains critically dependent on precise user prompts. Existing test-time optimization methods, successful in other domains, struggle with the multi-faceted nature of video. In this work, we introduce VISTA (Video Iterative Self-improvemenT Agent), a novel multi-agent system that autonomously improves video generation through refining prompts in an iterative loop. VISTA first decomposes a user idea into a structured temporal plan. After generation, the best video is identified through a robust pairwise tournament. This winning video is then critiqued by a trio of specialized agents focusing on visual, audio, and contextual fidelity. Finally, a reasoning agent synthesizes this feedback to introspectively rewrite and enhance the prompt for the next generation cycle. Experiments on single- and multi-scene video generation scenarios show that while prior methods yield inconsistent gains, VISTA consistently improves video quality and alignment with user intent, achieving up to 60% pairwise win rate against state-of-the-art baselines. Human evaluators concur, preferring VISTA outputs in 66.4% of comparisons.