EUVIMEDEUVIMED entdecken
Crossref

GENMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration

Kaiyi Huang, Yukun Huang, Xuefei Ning, Zinan Lin, Yu Wang, Xihui Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (7) · 5049-5057

DOI: 10.1609/aaai.v40i7.37418 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Kaiyi Huang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text-to-video generation models have shown significant progress in recent years. However, they still struggle with compositional text prompts, such as attribute binding for multiple objects, temporal dynamics associated with differ- ent objects, and interactions between objects. Inspired by ef- fective human creative workflow, we propose GENMAC, a multi-agent collaboration framework that enables composi- tional text-to-video generation. The framework incorporates a three-stage collaborative workflow: DESIGN, GENERATION, and REDESIGN, with an iterative loop between the latter two stages to progressively verify and refine the generated videos. In the DESIGN stage, a large language model (Design Agent) plans objects with layouts, and then a video gener- ation model synthesizes videos in the GENERATION stage. The REDESIGN stage is the most challenging stage that aims to verify the generated videos, suggest corrections, and re- design the text prompts, frame-wise layouts, and guidance scales for the next iteration of generation. To avoid halluci- nation of single-agent and naive multi-agent frameworks, we apply a division-of-labor strategy in this stage by introducing a sequence of specialized agents, executed by MLLMs (mul- timodal large language models): Verification Agent, Sugges- tion Agent, Correction Agent, and Output Structuring Agent. Furthermore, to tackle diverse scenarios of compositional text-to-video generation, we design a self-routing mechanism to adaptively select the proper correction agent from a suite of correction agents, each specialized for one scenario. Ex- tensive experiments demonstrate the effectiveness of GEN- MAC by generating videos based on long compositional text prompts and achieving state-of-the-art in the compositional text-to-video generation benchmark.

Zitieren

APA

Huang, K., Huang, Y., Ning, X., Lin, Z., Wang, Y., & Liu, X. (2026). GENMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration. Proceedings of the AAAI Conference on Artificial Intelligence, 40(7), 5049-5057. https://doi.org/10.1609/aaai.v40i7.37418

Vancouver

Huang K, Huang Y, Ning X, Lin Z, Wang Y, Liu X. GENMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(7):5049-5057. doi:10.1609/aaai.v40i7.37418

BibTeX
@article{Huang2026,
  author = {Huang, Kaiyi and Huang, Yukun and Ning, Xuefei and Lin, Zinan and Wang, Yu and Liu, Xihui},
  title = {GENMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {7},
  pages = {5049--5057},
  doi = {10.1609/aaai.v40i7.37418}
}
Kostenlos starten →