# VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation

arXiv: https://arxiv.org/abs/2606.08091 · HTML: https://mlsanity.com/paper/2606.08091/

## Key facts

- Cited by 7 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 43 of its 57 references that are in the map.
- First posted on arXiv 6 Jun 2026.

## 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 43)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Let's Verify Step by Step](https://mlsanity.com/paper/2305.20050/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks](https://mlsanity.com/paper/2602.12670/) (2026)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [VideoPhy: Evaluating Physical Commonsense for Video Generation](https://mlsanity.com/paper/2406.03520/) (2024)
- [Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills](https://mlsanity.com/paper/2603.25158/) (2026)
- [VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation](https://mlsanity.com/paper/2412.21059/) (2024)
- [SkillOpt: Executive Strategy for Self-Evolving Agent Skills](https://mlsanity.com/paper/2605.23904/) (2026)
- [MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents](https://mlsanity.com/paper/2602.02474/) (2026)
- [VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning](https://mlsanity.com/paper/2309.15091/) (2023)
- [MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory](https://mlsanity.com/paper/2601.03192/) (2026)
- [CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verification](https://mlsanity.com/paper/2604.01687/) (2026)
- [AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution](https://mlsanity.com/paper/2603.01145/) (2026)
- [EvoSkill: Automated Skill Discovery for Multi-Agent Systems](https://mlsanity.com/paper/2603.02766/) (2026)
- [TRAIL: Trace Reasoning and Agentic Issue Localization](https://mlsanity.com/paper/2505.08638/) (2025)
- [SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization](https://mlsanity.com/paper/2604.02268/) (2026)
- [XSkill: Continual Learning from Experience and Skills in Multimodal Agents](https://mlsanity.com/paper/2603.12056/) (2026)
- [Stable Video Infinity: Infinite-Length Video Generation with Error Recycling](https://mlsanity.com/paper/2510.09212/) (2025)
- [Helios: Real Real-Time Long Video Generation Model](https://mlsanity.com/paper/2603.04379/) (2026)
- [Memento-Skills: Let Agents Design Agents](https://mlsanity.com/paper/2603.18743/) (2026)
- [Video-Bench: Human-Aligned Video Generation Benchmark](https://mlsanity.com/paper/2504.04907/) (2025)
- [SkillOS: Learning Skill Curation for Self-Evolving Agents](https://mlsanity.com/paper/2605.06614/) (2026)
- [SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support](https://mlsanity.com/paper/2604.08618/) (2026)
- [Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models](https://mlsanity.com/paper/2412.09645/) (2024)
- [StoryMem: Multi-shot Long Video Storytelling with Memory](https://mlsanity.com/paper/2512.19539/) (2025)
- [MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild](https://mlsanity.com/paper/2603.17187/) (2026)

## Built on by (most cited first, 7 of 7)

- [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)
- [DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation](https://mlsanity.com/paper/2609.00646/) (2026)
- [AgenticGen: Reward-Guided Agentic Video Generation for Advertising](https://mlsanity.com/paper/2609.09187/) (2026)
- [Don't Read the Log: Execution Traces Contaminate Verifiers in Video-Generation Agents](https://mlsanity.com/paper/2609.28564/) (2026)
- [Reels-RSI: Program-Level Self-Improvement for Code-Rendered Explainer Videos](https://mlsanity.com/paper/2610.14495/) (2026)
- [REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation](https://mlsanity.com/paper/2610.16632/) (2026)

## Abstract (arXiv)

Agentic long video generation requires planning, tool orchestration, and cross-clip coordination over a long horizon. Most existing video agents either rely on static, human-crafted workflows, which require substantial manual effort and poorly adapt across tasks, or iteratively refine the output of the current task without persistently distilling execution experience into reusable skills for future tasks. We introduce VideoWeaver, an agent harness and benchmark that evaluates and evolves skills for long video generation. Given a single high-level instruction, an agent dynamically composes foundation skills into its own workflow rather than following a predefined pipeline. We construct a benchmark of 16 task categories and 285 cases, with references spanning text, image, audio, video, and their combinations. We further propose an evidence-grounded agent-as-judge that inspects both the execution trace and the final video to diagnose process and output failures. Based on this feedback, our evolution algorithm progressively refines category-level composition and creator skills, allowing recurring experience to guide dynamically constructed workflows for unseen cases. Experiments show that explicit composition skills improve the generation process over foundation skills alone, while skill evolution further improves output quality and generalizes to unseen cases. Incorporating judge feedback yields additional gains, especially on output metrics, and the agent-as-judge aligns well with human, particularly on process metrics. Code is available at https://github.com/JianhuiWei7/VideoWeaver.