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

• URL: http://arxiv.org/abs/2510.15831v1
• Date: Fri, 17 Oct 2025 17:12:08 GMT
• Title: VISTA: A Test-Time Self-Improving Video Generation Agent
• Abstract summary: VISTA (Video Iterative Self-improvemenT Agent) is a novel system that autonomously improves video generation through refining prompts in an iterative loop.<n>It consistently improves video quality and alignment with user intent, achieving up to 60% pairwise win rate against state-of-the-art baselines.<n>Human evaluators concur, preferring VISTA outputs in 66.4% of comparisons.
• Score: 45.53495043750626
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding [61.00809248898572]
  Long video understanding is a problem in which an agent reads the video turn by turn along the temporal axis, deciding at each turn how fast to watch, what evidence to retain, when to revisit uncertain segments, and when to stop and answer.<n>We propose textbfVideoScout, a multi-turn reasoning agent that instantiates the SEA paradigm through adaptive reasoning pacing.<n>Experiments on long video understanding and reasoning benchmarks demonstrate that our 7B model achieves strong performance compared with existing trained 7B agentic models.
  arXiv  Detail & Related papers  (2026-09-14T14:04:03Z)
• VideoAgent: All-in-One Framework for Video Understanding and Editing [26.019384130449733]
  VideoAgent is an all-in-one agentic framework for video editing.<n>We develop automated video shot creation with shot planning agents for coherent narratives.<n>Intent parsing filters relevant tools while textual-gradient graph optimizations assemble editing pipelines.
  arXiv  Detail & Related papers  (2026-06-22T13:37:08Z)
• Bridging Creative Intent and Visual Quality: Creator-Driven Recurrent Video Generation with Agentic Feedback Loops [36.169206628733484]
  We introduce CHIEF, a human-AI co-creation video generation framework that places the creator at the center of human-in-the-loop iterative video refinement.<n>The creator incorporates their creative direction by driving each iteration, while their revisions are incorporated by a specialized refiner agent.<n>To test the effectiveness of our proposed framework, we work with high school and college students with no prior filmmaking experience to create videos.
  arXiv  Detail & Related papers  (2026-06-17T01:39:30Z)
• CutClaw: Agentic Hours-Long Video Editing via Music Synchronization [96.62825277039117]
  CutClaw is an autonomous multi-agent framework designed to edit hours-long raw footage into meaningful short videos.<n>It produces videos with synchronized music, followed by instructions, and a visually appealing appearance.<n>We conduct detailed experiments to demonstrate that CutClaw significantly outperforms state-of-the-art baselines in generating high-quality, rhythm-aligned videos.
  arXiv  Detail & Related papers  (2026-03-31T12:25:53Z)
• Plenoptic Video Generation [80.3116444692858]
  We introduce PlenopticDreamer, a framework that synchronizes generative hallucinations to maintain synchronization-temporal memory.<n>The core idea is to train a multi-in-out video-conditioned model in an autoregressive manner.<n>Our training incorporates context-scaling to improve convergence, self-conditioning to hallucinations caused by error accumulation, and a long-video conditioning mechanism to support extended video generation.
  arXiv  Detail & Related papers  (2026-01-08T18:58:32Z)
• Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning [66.51617619673587]
  We present Skyra, a specialized large language model (MLLM) that identifies human-perceivable visual artifacts in AI-generated videos.<n>To support this objective, we construct ViF-CoT-4K for Supervised Fine-Tuning (SFT), which represents the first large-scale AI-generated video dataset with fine-grained human annotations.<n>We then develop a two-stage training strategy that systematically enhances our model's artifact's-temporal perception, explanation capability, and detection accuracy.
  arXiv  Detail & Related papers  (2025-12-17T18:48:26Z)
• VideoScore2: Think before You Score in Generative Video Evaluation [69.43069741467603]
  VideoScore2 is a multi-dimensional, interpretable, and human-aligned framework that explicitly evaluates visual quality, text-to-video alignment, and physical/common-sense consistency.<n>Our model is trained on a large-scale dataset VideoFeedback2 containing 27,168 human-annotated videos.
  arXiv  Detail & Related papers  (2025-09-26T18:09:03Z)
• We'll Fix it in Post: Improving Text-to-Video Generation with Neuro-Symbolic Feedback [5.743225523680124]
  Current text-to-video (T2V) generation models struggle to generate semantically and temporally consistent videos when dealing with longer, more complex prompts.<n>We introduce NeuS-E, a novel zero-training video refinement pipeline that leverages neuro-symbolic feedback to automatically enhance video generation.<n>Our approach first derives the neuro-symbolic feedback by analyzing a formal video representation and pinpoints semantically inconsistent events, objects, and their corresponding frames.
  arXiv  Detail & Related papers  (2025-04-24T01:34:12Z)
• Long-Video Audio Synthesis with Multi-Agent Collaboration [20.332328741375363]
  LVAS-Agent is a novel framework that emulates professional dubbing through collaborative role.<n>Our approach decomposes long-video synthesis into four steps including scene segmentation, script generation, sound design and audio synthesis.<n>Central innovations include a discussion-correction mechanism for scene/script refinement and a generation-retrieval loop for temporal-semantic alignment.
  arXiv  Detail & Related papers  (2025-03-13T07:58:23Z)
• VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention [76.3175166538482]
  VideoGen-of-Thought (VGoT) is a step-by-step framework that automates multi-shot video synthesis from a single sentence.<n>VGoT addresses three core challenges: Narrative fragmentation, visual inconsistency, and transition artifacts.<n>Combined in a training-free pipeline, VGoT surpasses strong baselines by 20.4% in within-shot face consistency and 17.4% in style consistency.
  arXiv  Detail & Related papers  (2024-12-03T08:33:50Z)
• VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment [19.313541287648473]
  We introduce VELOCITI, a benchmark to study Video-LLMs by disentangling and assessing the comprehension of agents.<n>We adopt the Video-Language Entailment setup and propose StrictVLE that requires correct classification (rather than ranking) of the positive and negative caption.<n>Results show that action understanding lags behind agents, and negative captions created using entities appearing in the video perform worse than those obtained from pure text manipulation.
  arXiv  Detail & Related papers  (2024-06-16T10:42:21Z)
• SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction [93.26613503521664]
  This paper presents a short-to-long video diffusion model, SEINE, that focuses on generative transition and prediction. We propose a random-mask video diffusion model to automatically generate transitions based on textual descriptions. Our model generates transition videos that ensure coherence and visual quality.
  arXiv  Detail & Related papers  (2023-10-31T17:58:17Z)
• Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer [66.56167074658697]
  We present a method that builds on 3D-VQGAN and transformers to generate videos with thousands of frames. Our evaluation shows that our model trained on 16-frame video clips can generate diverse, coherent, and high-quality long videos. We also showcase conditional extensions of our approach for generating meaningful long videos by incorporating temporal information with text and audio.
  arXiv  Detail & Related papers  (2022-04-07T17:59:02Z)
• Blind Video Temporal Consistency via Deep Video Prior [61.062900556483164]
  We present a novel and general approach for blind video temporal consistency. Our method is only trained on a pair of original and processed videos directly. We show that temporal consistency can be achieved by training a convolutional network on a video with the Deep Video Prior.
  arXiv  Detail & Related papers  (2020-10-22T16:19:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.