---
title: "MAViS — paper by Wang et al. (2026) — summary and ideas"
description: "The authors also propose Script Writing Guidelines, which steer scripts toward content that current… 65 references, cited by 1 paper here."
authors: ["Qian Wang", "Ziqi Huang", "Ruoxi Jia", "Paul Debevec", "Ning Yu"]
year: 2026
venue: "Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.eacl-long.101/"
doi: "10.18653/v1/2026.eacl-long.101"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wang-2026-mavis-multi-agent-framework-long/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-mavis-multi-agent-framework-long/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/14/) / MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling

# MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling

**Authors:** [Qian Wang](https://md.research.elamur.ai/free/en/authors/qian-wang/), [Ziqi Huang](https://md.research.elamur.ai/free/en/authors/ziqi-huang/), [Ruoxi Jia](https://md.research.elamur.ai/free/en/authors/ruoxi-jia/), Paul Debevec and [Ning Yu](https://md.research.elamur.ai/free/en/authors/ning-yu/) · **Year:** 2026 · **Venue:** [Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/eacl/) ([EACL 2026](https://md.research.elamur.ai/free/en/venues/eacl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.eacl-long.101/) · [PDF](https://aclanthology.org/2026.eacl-long.101.pdf) · [DOI 10.18653/v1/2026.eacl-long.101](https://doi.org/10.18653/v1/2026.eacl-long.101) · [OpenAlex](https://openalex.org/W7140083991)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · 1 in our library, of the 149,439 papers whose bibliographies we read

## Summary
Current generative video models can produce convincing single shots, but they struggle to build minute-long stories. Existing storytelling pipelines often need users to write scripts and train LoRA models by hand, and they still tend to produce distorted frames, repetitive motion and weak shot structure. MAViS addresses this with a multi-agent system that turns a short user prompt into a complete narrated video with background music. Specialised agents handle six consecutive stages: script writing, shot designing, character modeling (LoRA-based identity consistency), keyframe generation with T2I models, animation with I2V models, and audio generation. Within each stage, agents follow the 3E Principle. One agent drafts an output (Explore), a reviewer checks it against guidelines (Examine), and a refiner revises the request (Enhance). This loop repeats before the result moves to the next stage. The authors also propose Script Writing Guidelines, which steer scripts toward content that current generators can actually render. Experiments and user preference votes favour MAViS over prior systems on assistive capability, visual quality and expressiveness. Its modular design lets the underlying models be swapped.

## Key points
- The pipeline works end to end from a brief prompt. Each output is a sequence of N shots, and every shot pairs a video clip with an audio track. The authors claim MAViS is the only framework that delivers voice-over and background music together with the video.
- The script stage uses three reviewers: Structure, Content and Style. Ablations suggest each one matters. Removing the Structure Reviewer hurts narrative expressiveness, removing the Content Reviewer lowers visual quality, and removing the Style Reviewer weakens alignment with user intent.
- The Shot Reviewer, Voice Reviewer and Subtitle Refiner were evaluated with a Compliance Rate metric, defined as the share of outputs that fully meet their guidelines. Removing these agents lowered compliance, with the largest drop in voice-over generation.
- In the T2I/I2V ablation, Dynamic Degree was higher without 3E (44.58 vs. 35.63). The authors attribute this to the agents preferring calmer, more physically stable clips.
- Stated limitations:
  - The method is restricted to a T2I+I2V paradigm.
  - Stories contain no character dialogue and the framework has no video editing.
  - The multimodal evaluators are unreliable. In practice the authors add VBench operators to support them, but they excluded these from the experiments for fairness.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Nanyang Technological University](https://md.research.elamur.ai/free/en/universities/nanyang-technological-university/) — University, Singapore, Singapore · 156 works · 25,644 citations
- [Virginia Tech](https://md.research.elamur.ai/free/en/universities/virginia-tech/) — University, Blacksburg, United States · 36 works · 43,036 citations

📚 Shelves (3): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 2,869 works · [🖥️ Computer Graphics and Computer-Aided Design](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-graphics-and-computer-aided-design/) · 7 works

## Cite

Cite as: Qian Wang, Ziqi Huang, Ruoxi Jia, Paul Debevec and Ning Yu. 2026. MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling. Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{wang2026mavis,
  title = {{MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling}},
  author = {Qian Wang, Ziqi Huang, Ruoxi Jia, Paul Debevec and Ning Yu},
  booktitle = {Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.eacl-long.101},
  url = {https://doi.org/10.18653/v1/2026.eacl-long.101}
}
```

- [← previous MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery](https://md.research.elamur.ai/free/en/papers/tandazo-2026-maubert-universal-phonetic-inductive-biases/)
- [next → MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding](https://md.research.elamur.ai/free/en/papers/zhang-2026-mavis-multi-agent-video-retrieval/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/14/)

## References

65 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
2. Wang Ang and Ai et al. Baole. 2025. Wan: Open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314. [find](https://scholar.google.com/scholar?q=Wang+Ang+and+Ai+et+al%2E+Baole%2E+2025%2E+Wan%3A+Open+and+advanced+large%2Dscale+video+generative+models%2E+arXiv+preprint+arXiv%3A2503%2E20314%2E)
3. Rohan Anil, Sebastian Borgeaud, Yonghui Wu, Jean-Baptiste Alayrac, Jiahui Yu, Radu Soricut, Johan Schalkwyk, Andrew M Dai, Anja Hauth, Katie Millican, and 1 others. 2023. [Gemini: A family of highly capable multimodal models](https://md.research.elamur.ai/free/en/papers/gemini-team-2023-gemini-family-highly-capable-multimodal/). arXiv preprint arXiv:2312.11805, 1.
4. BlackForestLabs. 2023. Flux. [https://github.com/](https://github.com/) black-forest-labs/flux. [↗](https://github.com/)
5. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
6. Siyu Cao, Hangting Chen, Peng Chen, Yiji Cheng, Yutao Cui, Xinchi Deng, Ying Dong, Kipper Gong, Tianpeng Gu, Xiusen Gu, and 1 others. 2025. [Hunyuanimage 3.0 technical report](https://md.research.elamur.ai/free/en/papers/team-2025-hunyuan-hunyuanimage-3-0-technical/). arXiv preprint arXiv:2509.23951.
7. Rinon Gal, Yuval Alaluf, Yuval Atzmon, Or Patashnik, Amit H Bermano, Gal Chechik, and Daniel Cohen-Or. 2022. An image is worth one word: Personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618. [find](https://scholar.google.com/scholar?q=Rinon+Gal%2C+Yuval+Alaluf%2C+Yuval+Atzmon%2C+Or+Patashnik%2C+Amit+H+Bermano%2C+Gal+Chechik%2C+and+Daniel+Cohen%2DOr%2E+2022%2E+An+image+is+worth+one+word%3A+Personalizing+text%2Dto%2Dimage+generation+using+textual+inversion%2E)
8. Songwei Ge, Thomas Hayes, Harry Yang, Xi Yin, Guan Pang, David Jacobs, Jia-Bin Huang, and Devi Parikh. 2022. Long video generation with time-agnostic vqgan and time-sensitive transformer. In European Conference on Computer Vision, pages 102–118. Springer. [find](https://scholar.google.com/scholar?q=Songwei+Ge%2C+Thomas+Hayes%2C+Harry+Yang%2C+Xi+Yin%2C+Guan+Pang%2C+David+Jacobs%2C+Jia%2DBin+Huang%2C+and+Devi+Parikh%2E+2022%2E+Long+video+generation+with+time%2Dagnostic+vqgan+and+time%2Dsensitive+transformer%2E+In+European+)
9. GenmoTeam. 2024. Mochi 1. [https://github.com/](https://github.com/) genmoai/models. [↗](https://github.com/)
10. Rohit Girdhar, Mannat Singh, Andrew Brown, Quentin Duval, Samaneh Azadi, Sai Saketh Rambhatla, Akbar Shah, Xi Yin, Devi Parikh, and Ishan Misra. 2023. Emu video: Factorizing text-to-video generation by explicit image conditioning. arXiv preprint arXiv:2311.10709. [find](https://scholar.google.com/scholar?q=Rohit+Girdhar%2C+Mannat+Singh%2C+Andrew+Brown%2C+Quentin+Duval%2C+Samaneh+Azadi%2C+Sai+Saketh+Rambhatla%2C+Akbar+Shah%2C+Xi+Yin%2C+Devi+Parikh%2C+and+Ishan+Misra%2E+2023%2E+Emu+video%3A+Factorizing+text%2Dto%2Dvideo+generation+b)
11. DeepMind Google. 2024. Veo-2. [find](https://scholar.google.com/scholar?q=DeepMind+Google%2E+2024%2E+Veo%2D2%2E)
12. DeepMind Google. 2025. Introducing gemini 2.5 flash image, our state-of-the-art image model. [find](https://scholar.google.com/scholar?q=DeepMind+Google%2E+2025%2E+Introducing+gemini+2%2E5+flash+image%2C+our+state%2Dof%2Dthe%2Dart+image+model%2E)
13. Yuwei Guo, Ceyuan Yang, Ziyan Yang, Zhibei Ma, Zhijie Lin, Zhenheng Yang, Dahua Lin, and Lu Jiang. 2025. Long context tuning for video generation. arXiv preprint arXiv:2503.10589. — [arXiv:2503.10589](https://arxiv.org/abs/2503.10589) [find](https://scholar.google.com/scholar?q=Yuwei+Guo%2C+Ceyuan+Yang%2C+Ziyan+Yang%2C+Zhibei+Ma%2C+Zhijie+Lin%2C+Zhenheng+Yang%2C+Dahua+Lin%2C+and+Lu+Jiang%2E+2025%2E+Long+context+tuning+for+video+generation%2E+arXiv+preprint+arXiv%3A2503%2E10589%2E+%E2%80%94+%5BarXiv%3A2503%2E10589%5D)
14. Tiankai Hang, Shuyang Gu, Dong Chen, Xin Geng, and Baining Guo. 2024. Cca: Collaborative competitive agents for image editing. arXiv preprint arXiv:2401.13011. — [arXiv:2401.13011](https://arxiv.org/abs/2401.13011) [find](https://scholar.google.com/scholar?q=Tiankai+Hang%2C+Shuyang+Gu%2C+Dong+Chen%2C+Xin+Geng%2C+and+Baining+Guo%2E+2024%2E+Cca%3A+Collaborative+competitive+agents+for+image+editing%2E+arXiv+preprint+arXiv%3A2401%2E13011%2E+%E2%80%94+%5BarXiv%3A2401%2E13011%5D%28https%3A%2F%2Farxiv%2Eorg%2Fa)
15. Yingqing He, Tianyu Yang, Yong Zhang, Ying Shan, and Qifeng Chen. 2022. Latent video diffusion models for high-fidelity long video generation. arXiv preprint arXiv:2211.13221. — [arXiv:2211.13221](https://arxiv.org/abs/2211.13221) [find](https://scholar.google.com/scholar?q=Yingqing+He%2C+Tianyu+Yang%2C+Yong+Zhang%2C+Ying+Shan%2C+and+Qifeng+Chen%2E+2022%2E+Latent+video+diffusion+models+for+high%2Dfidelity+long+video+generation%2E+arXiv+preprint+arXiv%3A2211%2E13221%2E+%E2%80%94+%5BarXiv%3A2211%2E13221%5D%28htt)
16. Roberto Henschel, Levon Khachatryan, Daniil Hayrapetyan, Hayk Poghosyan, Vahram Tade-vosyan, Zhangyang Wang, Shant Navasardyan, and Humphrey Shi. 2024. Streamingt2v: Consistent, dynamic, and extendable long video generation from text. arXiv preprint arXiv:2403.14773. — [arXiv:2403.14773](https://arxiv.org/abs/2403.14773) [find](https://scholar.google.com/scholar?q=Roberto+Henschel%2C+Levon+Khachatryan%2C+Daniil+Hayrapetyan%2C+Hayk+Poghosyan%2C+Vahram+Tade%2Dvosyan%2C+Zhangyang+Wang%2C+Shant+Navasardyan%2C+and+Humphrey+Shi%2E+2024%2E+Streamingt2v%3A+Consistent%2C+dynamic%2C+and+extendabl)
17. Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, and 1 others. 2023. [Metagpt: Meta programming for multi-agent collaborative framework](https://md.research.elamur.ai/free/en/papers/hong-2023-metagpt-meta-programming-multi/). arXiv preprint arXiv:2308.00352.
18. Ziqi Huang, Yinan He, Jiashuo Yu, Fan Zhang, Chenyang Si, Yuming Jiang, Yuanhan Zhang, Tianxing Wu, Qingyang Jin, Nattapol Chanpaisit, Yaohui Wang, Xinyuan Chen, Limin Wang, Dahua Lin, Yu Qiao, and Ziwei Liu. 2024. VBench: Comprehensive benchmark suite for video generative models. In Proceedings of… [find](https://scholar.google.com/scholar?q=Ziqi+Huang%2C+Yinan+He%2C+Jiashuo+Yu%2C+Fan+Zhang%2C+Chenyang+Si%2C+Yuming+Jiang%2C+Yuanhan+Zhang%2C+Tianxing+Wu%2C+Qingyang+Jin%2C+Nattapol+Chanpaisit%2C+Yaohui+Wang%2C+Xinyuan+Chen%2C+Limin+Wang%2C+Dahua+Lin%2C+Yu+Qiao%2C+and+Zi)
19. Sangwon Jang, Jaehyeong Jo, Kimin Lee, and Sung Ju Hwang. 2024. Identity decoupling for multi-subject personalization of text-to-image models. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Sangwon+Jang%2C+Jaehyeong+Jo%2C+Kimin+Lee%2C+and+Sung+Ju+Hwang%2E+2024%2E+Identity+decoupling+for+multi%2Dsubject+personalization+of+text%2Dto%2Dimage+models%2E+In+The+Thirty%2Deighth+Annual+Conference+on+Neural+Informat)
20. Weijie Kong, Qi Tian, Zijian Zhang, Rox Min, Zuozhuo Dai, Jin Zhou, Jiangfeng Xiong, Xin Li, Bo Wu, Jianwei Zhang, and 1 others. 2024. [Hunyuanvideo: A systematic framework for large video generative models](https://md.research.elamur.ai/free/en/papers/kong-2024-hunyuanvideo-systematic-framework-large/). arXiv preprint arXiv:2412.03603.
21. Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. [Camel: Communicative agents for" mind" exploration of large language model society](https://md.research.elamur.ai/free/en/papers/li-2023-camel-communicative-agents-mind/). Advances in Neural Information Processing Systems, 36:51991–52008.
22. Yitong Li, Zhe Gan, Yelong Shen, Jingjing Liu, Yu Cheng, Yuexin Wu, Lawrence Carin, David Carlson, and Jianfeng Gao. 2019. Storygan: A sequential conditional gan for story visualization. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 6329–6338. [find](https://scholar.google.com/scholar?q=Yitong+Li%2C+Zhe+Gan%2C+Yelong+Shen%2C+Jingjing+Liu%2C+Yu+Cheng%2C+Yuexin+Wu%2C+Lawrence+Carin%2C+David+Carlson%2C+and+Jianfeng+Gao%2E+2019%2E+Storygan%3A+A+sequential+conditional+gan+for+story+visualization%2E+In+Proceeding)
23. Xinyao Liao, Xianfang Zeng, Liao Wang, Gang Yu, Guosheng Lin, and Chi Zhang. 2025. Motionagent: Fine-grained controllable video generation via motion field agent. arXiv preprint arXiv:2502.03207. — [arXiv:2502.03207](https://arxiv.org/abs/2502.03207) [find](https://scholar.google.com/scholar?q=Xinyao+Liao%2C+Xianfang+Zeng%2C+Liao+Wang%2C+Gang+Yu%2C+Guosheng+Lin%2C+and+Chi+Zhang%2E+2025%2E+Motionagent%3A+Fine%2Dgrained+controllable+video+generation+via+motion+field+agent%2E+arXiv+preprint+arXiv%3A2502%2E03207%2E+%E2%80%94+%5Ba)
24. Chang Liu, Haoning Wu, Yujie Zhong, Xiaoyun Zhang, Yanfeng Wang, and Weidi Xie. 2024. Intelligent grimm-open-ended visual storytelling via latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6190–6200. [find](https://scholar.google.com/scholar?q=Chang+Liu%2C+Haoning+Wu%2C+Yujie+Zhong%2C+Xiaoyun+Zhang%2C+Yanfeng+Wang%2C+and+Weidi+Xie%2E+2024%2E+Intelligent+grimm%2Dopen%2Dended+visual+storytelling+via+latent+diffusion+models%2E+In+Proceedings+of+the+IEEE%2FCVF+Confe)
25. Shilong Liu, Hao Cheng, Haotian Liu, Hao Zhang, Feng Li, Tianhe Ren, Xueyan Zou, Jianwei Yang, Hang Su, Jun Zhu, and 1 others. 2025. Llava-plus: Learning to use tools for creating multimodal agents. In European Conference on Computer Vision, pages 126–142. Springer. [find](https://scholar.google.com/scholar?q=Shilong+Liu%2C+Hao+Cheng%2C+Haotian+Liu%2C+Hao+Zhang%2C+Feng+Li%2C+Tianhe+Ren%2C+Xueyan+Zou%2C+Jianwei+Yang%2C+Hang+Su%2C+Jun+Zhu%2C+and+1+others%2E+2025%2E+Llava%2Dplus%3A+Learning+to+use+tools+for+creating+multimodal+agents%2E+I)
26. Luma. 2024. Dream machine. [find](https://scholar.google.com/scholar?q=Luma%2E+2024%2E+Dream+machine%2E)
27. MiniMax. 2024. Hailuoai. [find](https://scholar.google.com/scholar?q=MiniMax%2E+2024%2E+Hailuoai%2E)
28. The ModelScopeTeam. 2023. Modelscope: bring the notion of model-as-a-service to life. [find](https://scholar.google.com/scholar?q=The+ModelScopeTeam%2E+2023%2E+Modelscope%3A+bring+the+notion+of+model%2Das%2Da%2Dservice+to+life%2E)
29. OpenAI. 2024. Creating video from text. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2024%2E+Creating+video+from+text%2E)
30. OpenAI. 2025. Gpt image - openai platform. Accessed: 2025-04-30. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025%2E+Gpt+image+%2D+openai+platform%2E+Accessed%3A+2025%2D04%2D30%2E)
31. Joon Sung Park, Joseph C O’Brien, Carrie J Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. arxiv. arXiv preprint ArXiv:2304.03442. [find](https://scholar.google.com/scholar?q=Joon+Sung+Park%2C+Joseph+C+O%E2%80%99Brien%2C+Carrie+J+Cai%2C+Meredith+Ringel+Morris%2C+Percy+Liang%2C+and+Michael+S+Bernstein%2E+2023%2E+Generative+agents%3A+Interactive+simulacra+of+human+behavior%2E+arxiv%2E+arXiv+preprint+Ar)
32. Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, and 1 others. 2024b. Lavie: High-quality video generation with cascaded latent diffusion models. IJCV. [find](https://scholar.google.com/scholar?q=Yaohui+Wang%2C+Xinyuan+Chen%2C+Xin+Ma%2C+Shangchen+Zhou%2C+Ziqi+Huang%2C+Yi+Wang%2C+Ceyuan+Yang%2C+Yinan+He%2C+Jiashuo+Yu%2C+Peiqing+Yang%2C+and+1+others%2E+2024b%2E+Lavie%3A+High%2Dquality+video+generation+with+cascaded+latent+)
33. Tanzila Rahman, Hsin-Ying Lee, Jian Ren, Sergey Tulyakov, Shweta Mahajan, and Leonid Sigal. 2023. Make-a-story: Visual memory conditioned consistent story generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2493–2502. [find](https://scholar.google.com/scholar?q=Tanzila+Rahman%2C+Hsin%2DYing+Lee%2C+Jian+Ren%2C+Sergey+Tulyakov%2C+Shweta+Mahajan%2C+and+Leonid+Sigal%2E+2023%2E+Make%2Da%2Dstory%3A+Visual+memory+conditioned+consistent+story+generation%2E+In+Proceedings+of+the+IEEE%2FCVF+Co)
34. Yaohui Wang, Xin Ma, Xinyuan Chen, Cunjian Chen, Antitza Dantcheva, Bo Dai, and Yu Qiao. 2024c. Leo: Generative latent image animator for human video synthesis. International Journal of Computer Vision, pages 1–13. [find](https://scholar.google.com/scholar?q=Yaohui+Wang%2C+Xin+Ma%2C+Xinyuan+Chen%2C+Cunjian+Chen%2C+Antitza+Dantcheva%2C+Bo+Dai%2C+and+Yu+Qiao%2E+2024c%2E+Leo%3A+Generative+latent+image+animator+for+human+video+synthesis%2E+International+Journal+of+Computer+Visio)
35. Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. [Zero-shot text-to-image generation](https://md.research.elamur.ai/free/en/papers/ramesh-2021-zero-shot-text-image-generation/). In International conference on machine learning, pages 8821–8831. Pmlr.
36. Zhenyu Wang, Aoxue Li, Zhenguo Li, and Xihui Liu. 2024d. Genartist: Multimodal llm as an agent for unified image generation and editing. arXiv preprint arXiv:2407.05600. — [arXiv:2407.05600](https://arxiv.org/abs/2407.05600) [find](https://scholar.google.com/scholar?q=Zhenyu+Wang%2C+Aoxue+Li%2C+Zhenguo+Li%2C+and+Xihui+Liu%2E+2024d%2E+Genartist%3A+Multimodal+llm+as+an+agent+for+unified+image+generation+and+editing%2E+arXiv+preprint+arXiv%3A2407%2E05600%2E+%E2%80%94+%5BarXiv%3A2407%2E05600%5D%28https%3A%2F%2Fa)
37. Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10684–10695. [find](https://scholar.google.com/scholar?q=Robin+Rombach%2C+Andreas+Blattmann%2C+Dominik+Lorenz%2C+Patrick+Esser%2C+and+Bj%C3%B6rn+Ommer%2E+2022%2E+High%2Dresolution+image+synthesis+with+latent+diffusion+models%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+compu)
38. Nataniel Ruiz, Yuanzhen Li, Varun Jampani, Yael Pritch, Michael Rubinstein, and Kfir Aberman. 2023. Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 22500–22510. [find](https://scholar.google.com/scholar?q=Nataniel+Ruiz%2C+Yuanzhen+Li%2C+Varun+Jampani%2C+Yael+Pritch%2C+Michael+Rubinstein%2C+and+Kfir+Aberman%2E+2023%2E+Dreambooth%3A+Fine+tuning+text%2Dto%2Dimage+diffusion+models+for+subject%2Ddriven+generation%2E+In+Proceedings)
39. Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, and 1 others. 2022. [Laion-5b: An open large-scale dataset for training next generation image-text models](https://md.research.elamur.ai/free/en/papers/schuhmann-2022-laion-5b-open-large-scale/). Advances in neural information proce…
40. StabilityAI. 2024. Stable diffusion 3.5. [find](https://scholar.google.com/scholar?q=StabilityAI%2E+2024%2E+Stable+diffusion+3%2E5%2E)
41. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, and 1 others. 2023a. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/). arXiv preprint arXiv:2302.13971.
42. Zihao Wang, Shaofei Cai, Anji Liu, Yonggang Jin, Jinbing Hou, Bowei Zhang, Haowei Lin, Zhaofeng He, Zilong Zheng, Yaodong Yang, and 1 others. 2024e. Jarvis-1: Open-world multi-task agents with memory-augmented multimodal language models. IEEE Transactions on Pattern Analysis and Machine Intelligence… [find](https://scholar.google.com/scholar?q=Zihao+Wang%2C+Shaofei+Cai%2C+Anji+Liu%2C+Yonggang+Jin%2C+Jinbing+Hou%2C+Bowei+Zhang%2C+Haowei+Lin%2C+Zhaofeng+He%2C+Zilong+Zheng%2C+Yaodong+Yang%2C+and+1+others%2E+2024e%2E+Jarvis%2D1%3A+Open%2Dworld+multi%2Dtask+agents+with+memory%2D)
43. Wenming Weng, Ruoyu Feng, Yanhui Wang, Qi Dai, Chunyu Wang, Dacheng Yin, Zhiyuan Zhao, Kai Qiu, Jianmin Bao, Yuhui Yuan, and 1 others. 2024. Art-v: Auto-regressive text-to-video generation with diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pa… [find](https://scholar.google.com/scholar?q=Wenming+Weng%2C+Ruoyu+Feng%2C+Yanhui+Wang%2C+Qi+Dai%2C+Chunyu+Wang%2C+Dacheng+Yin%2C+Zhiyuan+Zhao%2C+Kai+Qiu%2C+Jianmin+Bao%2C+Yuhui+Yuan%2C+and+1+others%2E+2024%2E+Art%2Dv%3A+Auto%2Dregressive+text%2Dto%2Dvideo+generation+with+diffus)
44. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, and 1 others. 2024. Autogen: Enabling next-gen llm applications via multi-agent conversations. In First Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Qingyun+Wu%2C+Gagan+Bansal%2C+Jieyu+Zhang%2C+Yiran+Wu%2C+Beibin+Li%2C+Erkang+Zhu%2C+Li+Jiang%2C+Xiaoyun+Zhang%2C+Shaokun+Zhang%2C+Jiale+Liu%2C+and+1+others%2E+2024%2E+Autogen%3A+Enabling+next%2Dgen+llm+applications+via+multi%2Dage)
45. Weijia Wu, Mingyu Liu, Zeyu Zhu, Xi Xia, Haoen Feng, Wen Wang, Kevin Qinghong Lin, Chunhua Shen, and Mike Zheng Shou. 2025a. Moviebench: A hierarchical movie level dataset for long video generation. In Proceedings of the Computer Vision and Pattern Recognition Conference, pages 28984– 28994. [find](https://scholar.google.com/scholar?q=Weijia+Wu%2C+Mingyu+Liu%2C+Zeyu+Zhu%2C+Xi+Xia%2C+Haoen+Feng%2C+Wen+Wang%2C+Kevin+Qinghong+Lin%2C+Chunhua+Shen%2C+and+Mike+Zheng+Shou%2E+2025a%2E+Moviebench%3A+A+hierarchical+movie+level+dataset+for+long+video+generation%2E+I)
46. Weijia Wu, Zeyu Zhu, and Mike Zheng Shou. 2025b. Automated movie generation via multi-agent cot planning. arXiv preprint arXiv:2503.07314. — [arXiv:2503.07314](https://arxiv.org/abs/2503.07314) [find](https://scholar.google.com/scholar?q=Weijia+Wu%2C+Zeyu+Zhu%2C+and+Mike+Zheng+Shou%2E+2025b%2E+Automated+movie+generation+via+multi%2Dagent+cot+planning%2E+arXiv+preprint+arXiv%3A2503%2E07314%2E+%E2%80%94+%5BarXiv%3A2503%2E07314%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2503%2E07314%29)
47. Hugo Touvron, Louis Martin, Kevin Stone, Peter Albert, Amjad Almahairi, Yasmine Babaei, Nikolay Bashlykov, Soumya Batra, Prajjwal Bhargava, Shruti Bhosale, and 1 others. 2023b. [Llama 2: Open foundation and fine-tuned chat models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-2-open-foundation-fine/). arXiv preprint arXiv:2307.09288.
48. Zhifei Xie, Daniel Tang, Dingwei Tan, Jacques Klein, Tegawend F Bissyand, and Saad Ezzini. 2024. Dreamfactory: Pioneering multi-scene long video generation with a multi-agent framework. arXiv preprint arXiv:2408.11788. — [arXiv:2408.11788](https://arxiv.org/abs/2408.11788) [find](https://scholar.google.com/scholar?q=Zhifei+Xie%2C+Daniel+Tang%2C+Dingwei+Tan%2C+Jacques+Klein%2C+Tegawend+F+Bissyand%2C+and+Saad+Ezzini%2E+2024%2E+Dreamfactory%3A+Pioneering+multi%2Dscene+long+video+generation+with+a+multi%2Dagent+framework%2E+arXiv+preprint)
49. Jiuniu Wang, Zehua Du, Yuyuan Zhao, Bo Yuan, Kexiang Wang, Jian Liang, Yaxi Zhao, Yihen Lu, Gengliang Li, Junlong Gao, and 1 others. 2024a. Aesopagent: Agent-driven evolutionary system on story-to-video production. arXiv preprint arXiv:2403.07952. — [arXiv:2403.07952](https://arxiv.org/abs/2403.07952) [find](https://scholar.google.com/scholar?q=Jiuniu+Wang%2C+Zehua+Du%2C+Yuyuan+Zhao%2C+Bo+Yuan%2C+Kexiang+Wang%2C+Jian+Liang%2C+Yaxi+Zhao%2C+Yihen+Lu%2C+Gengliang+Li%2C+Junlong+Gao%2C+and+1+others%2E+2024a%2E+Aesopagent%3A+Agent%2Ddriven+evolutionary+system+on+story%2Dto%2Dvid)
50. Jinbo Xing, Menghan Xia, Yong Zhang, Haoxin Chen, Wangbo Yu, Hanyuan Liu, Gongye Liu, Xintao Wang, Ying Shan, and Tien-Tsin Wong. 2025. Dynami-crafter: Animating open-domain images with video diffusion priors. In European Conference on Computer Vision, pages 399–417. Springer. [find](https://scholar.google.com/scholar?q=Jinbo+Xing%2C+Menghan+Xia%2C+Yong+Zhang%2C+Haoxin+Chen%2C+Wangbo+Yu%2C+Hanyuan+Liu%2C+Gongye+Liu%2C+Xintao+Wang%2C+Ying+Shan%2C+and+Tien%2DTsin+Wong%2E+2025%2E+Dynami%2Dcrafter%3A+Animating+open%2Ddomain+images+with+video+diffusio)
51. Tao Xu, Pengchuan Zhang, Qiuyuan Huang, Han Zhang, Zhe Gan, Xiaolei Huang, and Xiaodong He. 2018. Attngan: Fine-grained text to image generation with attentional generative adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1316–1324. [find](https://scholar.google.com/scholar?q=Tao+Xu%2C+Pengchuan+Zhang%2C+Qiuyuan+Huang%2C+Han+Zhang%2C+Zhe+Gan%2C+Xiaolei+Huang%2C+and+Xiaodong+He%2E+2018%2E+Attngan%3A+Fine%2Dgrained+text+to+image+generation+with+attentional+generative+adversarial+networks%2E+In+Pr)
52. Deshun Yang, Luhui Hu, Yu Tian, Zihao Li, Chris Kelly, Bang Yang, Cindy Yang, and Yuexian Zou. 2024a. Worldgpt: a sora-inspired video ai agent as rich world models from text and image inputs. arXiv preprint arXiv:2403.07944. — [arXiv:2403.07944](https://arxiv.org/abs/2403.07944) [find](https://scholar.google.com/scholar?q=Deshun+Yang%2C+Luhui+Hu%2C+Yu+Tian%2C+Zihao+Li%2C+Chris+Kelly%2C+Bang+Yang%2C+Cindy+Yang%2C+and+Yuexian+Zou%2E+2024a%2E+Worldgpt%3A+a+sora%2Dinspired+video+ai+agent+as+rich+world+models+from+text+and+image+inputs%2E+arXiv+pr)
53. Canyu Zhao, Mingyu Liu, Wen Wang, Weihua Chen, Fan Wang, Hao Chen, Bo Zhang, and Chunhua Shen. 2024. Moviedreamer: Hierarchical generation for coherent long visual sequence. arXiv preprint arXiv:2407.16655. — [arXiv:2407.16655](https://arxiv.org/abs/2407.16655) [find](https://scholar.google.com/scholar?q=Canyu+Zhao%2C+Mingyu+Liu%2C+Wen+Wang%2C+Weihua+Chen%2C+Fan+Wang%2C+Hao+Chen%2C+Bo+Zhang%2C+and+Chunhua+Shen%2E+2024%2E+Moviedreamer%3A+Hierarchical+generation+for+coherent+long+visual+sequence%2E+arXiv+preprint+arXiv%3A2407%2E)
54. Boyuan Zheng, Boyu Gou, Jihyung Kil, Huan Sun, and Yu Su. 2024. [Gpt-4v (ision) is a generalist web agent, if grounded](https://md.research.elamur.ai/free/en/papers/zheng-2024-gpt-4v-ision-generalist-web/). arXiv preprint arXiv:2401.01614.
55. Hui Yang, Sifu Yue, and Yunzhong He. 2023a. Auto-gpt for online decision making: Benchmarks and additional opinions. arXiv preprint arXiv:2306.02224. [find](https://scholar.google.com/scholar?q=Hui+Yang%2C+Sifu+Yue%2C+and+Yunzhong+He%2E+2023a%2E+Auto%2Dgpt+for+online+decision+making%3A+Benchmarks+and+additional+opinions%2E+arXiv+preprint+arXiv%3A2306%2E02224%2E)
56. Mingzhe Zheng, Yongqi Xu, Haojian Huang, Xuran Ma, Yexin Liu, Wenjie Shu, Yatian Pang, Feilong Tang, Qifeng Chen, Harry Yang, and 1 others. 2025. Videogen-of-thought: Step-by-step generating multi-shot video with minimal manual intervention. arXiv preprint arXiv:2503.15138. — [arXiv:2503.15138](https://arxiv.org/abs/2503.15138) [find](https://scholar.google.com/scholar?q=Mingzhe+Zheng%2C+Yongqi+Xu%2C+Haojian+Huang%2C+Xuran+Ma%2C+Yexin+Liu%2C+Wenjie+Shu%2C+Yatian+Pang%2C+Feilong+Tang%2C+Qifeng+Chen%2C+Harry+Yang%2C+and+1+others%2E+2025%2E+Videogen%2Dof%2Dthought%3A+Step%2Dby%2Dstep+generating+multi%2Dsho)
57. Shuai Yang, Yuying Ge, Yang Li, Yukang Chen, Yixiao Ge, Ying Shan, and Yingcong Chen. 2024b. Seed-story: Multimodal long story generation with large language model. arXiv preprint arXiv:2407.08683. — [arXiv:2407.08683](https://arxiv.org/abs/2407.08683) [find](https://scholar.google.com/scholar?q=Shuai+Yang%2C+Yuying+Ge%2C+Yang+Li%2C+Yukang+Chen%2C+Yixiao+Ge%2C+Ying+Shan%2C+and+Yingcong+Chen%2E+2024b%2E+Seed%2Dstory%3A+Multimodal+long+story+generation+with+large+language+model%2E+arXiv+preprint+arXiv%3A2407%2E08683%2E+%E2%80%94+)
58. Cailin Zhuang, Ailin Huang, Wei Cheng, Jingwei Wu, Yaoqi Hu, Jiaqi Liao, Hongyuan Wang, Xinyao Liao, Weiwei Cai, Hengyuan Xu, and 1 others. 2025. Vistorybench: Comprehensive benchmark suite for story visualization. arXiv preprint arXiv:2505.24862. — [arXiv:2505.24862](https://arxiv.org/abs/2505.24862) [find](https://scholar.google.com/scholar?q=Cailin+Zhuang%2C+Ailin+Huang%2C+Wei+Cheng%2C+Jingwei+Wu%2C+Yaoqi+Hu%2C+Jiaqi+Liao%2C+Hongyuan+Wang%2C+Xinyao+Liao%2C+Weiwei+Cai%2C+Hengyuan+Xu%2C+and+1+others%2E+2025%2E+Vistorybench%3A+Comprehensive+benchmark+suite+for+story+)
59. Zhengyuan Yang, Linjie Li, Jianfeng Wang, Kevin Lin, Ehsan Azarnasab, Faisal Ahmed, Zicheng Liu, Ce Liu, Michael Zeng, and Lijuan Wang. 2023b. Mm-react: Prompting chatgpt for multimodal reasoning and action. Preprint, arXiv:2303.11381. [find](https://scholar.google.com/scholar?q=Zhengyuan+Yang%2C+Linjie+Li%2C+Jianfeng+Wang%2C+Kevin+Lin%2C+Ehsan+Azarnasab%2C+Faisal+Ahmed%2C+Zicheng+Liu%2C+Ce+Liu%2C+Michael+Zeng%2C+and+Lijuan+Wang%2E+2023b%2E+Mm%2Dreact%3A+Prompting+chatgpt+for+multimodal+reasoning+and+)
60. Da Yin, Faeze Brahman, Abhilasha Ravichander, Khyathi Chandu, Kai-Wei Chang, Yejin Choi, and Bill Yuchen Lin. 2023a. Lumos: Learning agents with unified data, modular design, and open-source llms. In ICLR 2024 Workshop on Large Language Model (LLM) Agents. [find](https://scholar.google.com/scholar?q=Da+Yin%2C+Faeze+Brahman%2C+Abhilasha+Ravichander%2C+Khyathi+Chandu%2C+Kai%2DWei+Chang%2C+Yejin+Choi%2C+and+Bill+Yuchen+Lin%2E+2023a%2E+Lumos%3A+Learning+agents+with+unified+data%2C+modular+design%2C+and+open%2Dsource+llms%2E+In+)
61. Shengming Yin, Chenfei Wu, Huan Yang, Jianfeng Wang, Xiaodong Wang, Minheng Ni, Zhengyuan Yang, Linjie Li, Shuguang Liu, Fan Yang, and 1 others. 2023b. Nuwa-xl: Diffusion over diffusion for extremely long video generation. arXiv preprint arXiv:2303.12346. [find](https://scholar.google.com/scholar?q=Shengming+Yin%2C+Chenfei+Wu%2C+Huan+Yang%2C+Jianfeng+Wang%2C+Xiaodong+Wang%2C+Minheng+Ni%2C+Zhengyuan+Yang%2C+Linjie+Li%2C+Shuguang+Liu%2C+Fan+Yang%2C+and+1+others%2E+2023b%2E+Nuwa%2Dxl%3A+Diffusion+over+diffusion+for+extremely+)
62. Zhengqing Yuan, Yixin Liu, Yihan Cao, Weixiang Sun, Haolong Jia, Ruoxi Chen, Zhaoxu Li, Bin Lin, Li Yuan, Lifang He, and 1 others. 2024. Mora: Enabling generalist video generation via a multi-agent framework. arXiv preprint arXiv:2403.13248. — [arXiv:2403.13248](https://arxiv.org/abs/2403.13248) [find](https://scholar.google.com/scholar?q=Zhengqing+Yuan%2C+Yixin+Liu%2C+Yihan+Cao%2C+Weixiang+Sun%2C+Haolong+Jia%2C+Ruoxi+Chen%2C+Zhaoxu+Li%2C+Bin+Lin%2C+Li+Yuan%2C+Lifang+He%2C+and+1+others%2E+2024%2E+Mora%3A+Enabling+generalist+video+generation+via+a+multi%2Dagent+fr)
63. Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, and Dimitris N Metaxas. 2017. Stackgan: Text to photo-realistic image synthesis with stacked generative adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 5907–5915. [find](https://scholar.google.com/scholar?q=Han+Zhang%2C+Tao+Xu%2C+Hongsheng+Li%2C+Shaoting+Zhang%2C+Xiaogang+Wang%2C+Xiaolei+Huang%2C+and+Dimitris+N+Metaxas%2E+2017%2E+Stackgan%3A+Text+to+photo%2Drealistic+image+synthesis+with+stacked+generative+adversarial+netwo)
64. Shiwei Zhang, Jiayu Wang, Yingya Zhang, Kang Zhao, Hangjie Yuan, Zhiwu Qin, Xiang Wang, Deli Zhao, and Jingren Zhou. 2023. I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models. arXiv preprint arXiv:2311.04145. — [arXiv:2311.04145](https://arxiv.org/abs/2311.04145) [find](https://scholar.google.com/scholar?q=Shiwei+Zhang%2C+Jiayu+Wang%2C+Yingya+Zhang%2C+Kang+Zhao%2C+Hangjie+Yuan%2C+Zhiwu+Qin%2C+Xiang+Wang%2C+Deli+Zhao%2C+and+Jingren+Zhou%2E+2023%2E+I2vgen%2Dxl%3A+High%2Dquality+image%2Dto%2Dvideo+synthesis+via+cascaded+diffusion+model)
65. Zhuosheng Zhang and Aston Zhang. 2024. [You only look at screens: Multimodal chain-of-action agents](https://md.research.elamur.ai/free/en/papers/zhang-2024-you-only-look-screens-multimodal/). Preprint, arXiv:2309.11436.

*Updated 1 November 2026*