Metraipolis › archive › dc_2bfe862043d2
Video-Coder: Reinforcing Agentic Coding for Video Generation — arXiv:2611.09894
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09894
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:45:31.054Z
- SHA-256 of the archived text
d171b800e2219ace0a570f76b2bad7dc3c5d3cc0a4a358396941d2492c1908a2- Stable URL of this page
https://metraipolis.com/documento/dc_2bfe862043d2
How to cite
Video-Coder: Reinforcing Agentic Coding for Video Generation — arXiv:2611.09894 — arXiv (en), https://arxiv.org/abs/2611.09894 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2bfe862043d2 (Metraipolis archive dc_2bfe862043d2, sha256 d171b800e2219ace0a570f76b2bad7dc3c5d3cc0a4a358396941d2492c1908a2)
BibTeX
@misc{dc2bfe862043d2,
title = {Video-Coder: Reinforcing Agentic Coding for Video Generation — arXiv:2611.09894},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09894},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2bfe862043d2; sha256 d171b800e2219ace0a570f76b2bad7dc3c5d3cc0a4a358396941d2492c1908a2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09894. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Recent years have witnessed remarkable progress in video generation in terms of visual quality and temporal consistency. However, generating videos with precise spatial structure, coherent motion dynamics, and controllable scene composition remains challenging. In this paper, we introduce Video-Coder, the first attempt to train a code-driven video generation agent, which autonomously writes and executes code to construct a dynamic 3D scene (Draft Video) that provides structure and motion signals to downstream video generators. To support this paradigm, we design a dedicated data pipeline and curate two high-quality datasets, Video-Coder-SFT-6k and Video-Coder-RL-2k, which contain diverse prompts and ground-truth reference videos. We further develop the Video- Coder Harness, a unified interactive environment integrating code execution, 3D scene rendering, and execution feedback for agent training and inference. We then train Video-Coder with SFT fol- lowed by harness-native agentic reinforcement learning with dual reward feedback, which combines execution-based and video-based rewards. Additionally, we design an annealing training strategy that gradually reduces the execution reward over time, allowing the model to rely more on the video reward in the later training stages. Experiments show that Video-Coder achieves significant gains, improving Minimax-H3 by approximately 7 points on PhyGenBench and 24 points on VBench-2.0. We hope this work can serve as an open foundation for coding agents in video generation, and we fully open-source our data, models, and code Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.09894 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-09T22:37:47.236Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).