@inproceedings{wang-etal-2026-knowing,
    title = "From Knowing to Teaching: Scaffolding Pedagogical Decisions for {LLM} Agent",
    author = "Wang, Yucheng  and
      Yang, Shen  and
      Yu, Jifan  and
      Li, Haoxuan  and
      Lim, Joy Jia Yin  and
      Zhang-Li, Daniel  and
      Liu, Huiqin  and
      Hou, Lei  and
      Li, Juanzi  and
      Xu, Bin",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1328/",
    pages = "28778--28801",
    ISBN = "979-8-89176-390-6",
    abstract = "Knowing and teaching differ fundamentally: effective instruction requires transforming knowledge into forms learners can grasp. Large language models, when asked to generate lessons (a concrete form of teaching), produce content lacking pedagogical depth. We trace this failure to three decisions that expert teachers make: \textit{selecting} content by recognizing each source{'}s instructional role, \textit{sequencing} topics so foundations precede applications, and \textit{synthesizing} components into a unified whole. To scaffold these decisions, we introduce \textbf{TeachCraft}, a framework with three agents: Explorer classifies sources by pedagogical intent to guide selection; Planner orders objectives from foundational to advanced; Generator produces lesson materials through a schema that ensures consistency across components. To evaluate this approach, we construct LessonBench, 40 expert-designed lessons paired with two to five heterogeneous source documents, on which TeachCraft achieves 67.8{\%} win rate in human evaluation and 79.6{\%} in LLM-based evaluation against eight baselines, with ablations confirming that each decision contributes independently to overall lesson quality.[Source code is available at {\ensuremath{<}}https://anonymous.4open.science/r/TeachCraft-1672{\ensuremath{>}}]"
}