{"type":"ScholarlyArticle","title":"PoemDirector: A Multi-Agent Context-Adaptive Instructional Mode Selection Framework for Chinese Classical Poetry Video Generation","authors":[{"name":"Tengteng Cheng","slug":"tengteng-cheng","given":"Tengteng","family":"Cheng","affiliation":""},{"name":"Xiaoli Zeng","slug":"xiaoli-zeng","given":"Xiaoli","family":"Zeng","affiliation":""},{"name":"Jialu Huang","slug":"jialu-huang","given":"Jialu","family":"Huang","affiliation":""},{"name":"Mingliang Hou","slug":"mingliang-hou","given":"Mingliang","family":"Hou","affiliation":""},{"name":"Zitao Liu","slug":"zitao-liu","given":"Zitao","family":"Liu","affiliation":""},{"name":"Xiangyu Zhao","slug":"xiangyu-zhao","given":"Xiangyu","family":"Zhao","affiliation":""},{"name":"Weiqi Luo","slug":"weiqi-luo","given":"Weiqi","family":"Luo","affiliation":""}],"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.","doi":"10.24963/ijcai.2026/790","url":"https://ijcai.org/proceedings/2026/790","pdf":"https://ijcai.org/proceedings/2026/0790.pdf","markdown":"https://ijcai.org/proceedings/2026/790.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/790","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI and Social Good","track":"AI and Social Good","number":790,"pages":{"first":7102,"last":7110},"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"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}