VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation

• URL: http://arxiv.org/abs/2606.08091v1
• Date: Sat, 06 Jun 2026 10:35:28 GMT
• Title: VideoWeaver: Evaluating and Evolving Skills for Agentic Long Video Generation
• Abstract summary: We introduce VideoWeaver, an agent harness and benchmark that evaluates and evolves skills for long video generation.<n>An agent-as-judge inspects both the execution trace and the final video, grounding its scores in evidence such as metadata and intermediate files.<n>We find that an explicit composition skill improves the generation process over using foundation skills alone.
• Score: 31.298725533176253
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent agent frameworks such as Claude Code, Codex, and OpenClaw are strong at tool use and orchestration, but whether they can handle long video generation, a long-horizon multimodal task, remains underexplored. Unlike earlier video agents whose pipeline is handcrafted, these frameworks can build and refine their own workflows. We introduce VideoWeaver, an agent harness and benchmark that evaluates and evolves skills for long video generation, where an agent turns a single instruction into a long video by composing foundation skills into its own workflow rather than following a predefined pipeline. The benchmark has 16 task categories and 285 cases, with references spanning text, image, audio, video, and their combinations. Because errors can arise at any stage and not just in the final video, we propose an agent-as-judge that inspects both the execution trace and the final video, grounding its scores in evidence such as metadata and intermediate files. Using this feedback, we further design a skill evolution algorithm that refines and merges the agent's skills. Across multiple frameworks and models, we find that an explicit composition skill improves the generation process over using foundation skills alone, that skill evolution further improves output quality, and that performance varies notably across harness and model choices. The proposed agent-as-judge also aligns well with human judgments, especially on process metrics. Code and dataset is available at https://github.com/JianhuiWei7/VideoWeaver

Related papers

• 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)
• Sandboxed Coding Agents are Competitive Omni-modal Task Solvers [22.269016330825128]
  We show that coding agents with only text+image access and a sandboxed tool-use interface can match SOTA native omnimodal models.<n>Our trajectory analysis suggests that their strength comes from writing code and orchestrating tools to extract relevant evidence.<n>We introduce Code-X, a training recipe with the OmniCoding trajectory dataset and verifiable reward, and provide baselines on Qwen-3.5-9B and Qwen-3.6-27B.
  arXiv  Detail & Related papers  (2026-05-30T07:04:27Z)
• 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)
• Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance [55.32799307123252]
  We introduce a scalable data generation pipeline that transforms existing video editing pairs into high-fidelity training quadruplets.<n>We propose a unified editing architecture, Kiwi-Edit, that synergizes learnable queries and latent visual features for reference semantic guidance.
  arXiv  Detail & Related papers  (2026-03-02T18:46:28Z)
• UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist [107.04196084992907]
  We introduce UniVA, an omni-capable multi-agent framework for next-generation video generalists.<n>UniVA employs a Plan-and-Act dual-agent architecture that drives a highly automated and proactive workflow.<n>We also introduce UniVA-Bench, a benchmark suite of multi-step video tasks spanning understanding, editing, segmentation, and generation.
  arXiv  Detail & Related papers  (2025-11-11T17:58:13Z)
• CAViAR: Critic-Augmented Video Agentic Reasoning [90.48729440775223]
  We ask: can perception capabilities be leveraged to perform more complex video reasoning?<n>We develop a large language model agent given access to video modules as subagents or tools.<n>We show that the combination of our agent and critic achieve strong performance on datasets.
  arXiv  Detail & Related papers  (2025-09-09T17:59:39Z)
• Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding [60.88843818016968]
  Long-form video understanding presents significant challenges due to temporal-spatial complexity and difficulty of question answering.<n>We propose the Deep Video Discovery (DVD) agent to leverage an agentic search strategy over segmented video clips.<n>Our DVD agent achieves state-of-the-art performance on the challenging LVBench dataset, reaching an accuracy of 74.2%.
  arXiv  Detail & Related papers  (2025-05-23T16:37:36Z)
• StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration [88.94832383850533]
  We propose a multi-agent framework designed for Customized Storytelling Video Generation (CSVG) StoryAgent decomposes CSVG into distinct subtasks assigned to specialized agents, mirroring the professional production process. Specifically, we introduce a customized Image-to-Video (I2V) method, LoRA-BE, to enhance intra-shot temporal consistency. Our contributions include the introduction of StoryAgent, a versatile framework for video generation tasks, and novel techniques for preserving protagonist consistency.
  arXiv  Detail & Related papers  (2024-11-07T18:00:33Z)
• Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs [20.168429351519055]
  Video understanding is a crucial next step for multimodal large language models (LMLMs)<n>We propose VideoNIAH (Video Needle In A Haystack), a benchmark construction framework through synthetic video generation.<n>We conduct a comprehensive evaluation of both proprietary and open-source models, uncovering significant differences in their video understanding capabilities.
  arXiv  Detail & Related papers  (2024-06-13T17:50:05Z)

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.