PoemDirector: A Multi-Agent Context-Adaptive Instructional Mode Selection Framework for Chinese Classical Poetry Video Generation

Cheng, Tengteng; Zeng, Xiaoli; Huang, Jialu; Hou, Mingliang; Liu, Zitao; Zhao, Xiangyu; Luo, Weiqi

doi:10.24963/ijcai.2026/790

PoemDirector: A Multi-Agent Context-Adaptive Instructional Mode Selection Framework for Chinese Classical Poetry Video Generation

Tengteng Cheng, Xiaoli Zeng, Jialu Huang, Mingliang Hou, Zitao Liu, Xiangyu Zhao, Weiqi Luo

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. AI and Social Good. Pages 7102-7110.

https://doi.org/10.24963/ijcai.2026/790

Keywords

Natural Language Processing: Natural Language Processing
Humans and AI: Humans and AI
Agent-based and Multi-agent Systems: Agent-based and Multi-agent Systems

Abstract

Classical poetry is central to aesthetic education and cultural inheritance in China's K-12 education, and web-based instructional videos have become a primary learning resource. However, existing production pipelines either require costly teacher-guided editing or generate videos automatically without systematic instructional design, leading to unclear logic, shallow explanations, and limited contextual adaptation. We propose PoemDirector, a multi-agent framework developed with a national K-12 educational platform partner that unifies context-adaptive instructional mode selection, hierarchical explanation, and end-to-end video generation. A Director Agent analyzes each poem, selects a pedagogically grounded instructional mode from a teacher-co-designed library, and coordinates specialized agents to produce a complete instructional video from a poem title alone. We further establish a multidimensional evaluation framework, refined by literary and education experts, to assess instructional quality and poetic presentation. Experiments show that PoemDirector substantially outperforms commercial baselines and approaches human-crafted video quality across multiple dimensions. The resources are publicly available at https://github.com/ai4ed/PoemDirector.

Tengteng Cheng, Xiaoli Zeng, Jialu Huang, Mingliang Hou, Zitao Liu, Xiangyu Zhao, and Weiqi Luo. 2026. PoemDirector: A Multi-Agent Context-Adaptive Instructional Mode Selection Framework for Chinese Classical Poetry Video Generation. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 7102–7110. https://doi.org/10.24963/ijcai.2026/790

@inproceedings{ijcai2026p790,
  title     = {PoemDirector: A Multi-Agent Context-Adaptive Instructional Mode Selection Framework for Chinese Classical Poetry Video Generation},
  author    = {Cheng, Tengteng and Zeng, Xiaoli and Huang, Jialu and Hou, Mingliang and Liu, Zitao and Zhao, Xiangyu and Luo, Weiqi},
  booktitle = {Proceedings of the Thirty-Fifth International Joint Conference on
               Artificial Intelligence, {IJCAI-26}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Diego Calvanese},
  pages     = {7102--7110},
  year      = {2026},
  month     = {8},
  note      = {AI and Social Good},
  doi       = {10.24963/ijcai.2026/790},
  url       = {https://doi.org/10.24963/ijcai.2026/790},
}

TY  - CPAPER
TI  - PoemDirector: A Multi-Agent Context-Adaptive Instructional Mode Selection Framework for Chinese Classical Poetry Video Generation
AU  - Cheng, Tengteng
AU  - Zeng, Xiaoli
AU  - Huang, Jialu
AU  - Hou, Mingliang
AU  - Liu, Zitao
AU  - Zhao, Xiangyu
AU  - Luo, Weiqi
T2  - Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2026
SP  - 7102
EP  - 7110
DO  - 10.24963/ijcai.2026/790
UR  - https://doi.org/10.24963/ijcai.2026/790
ER  -