发表机构
AI Ready School（AI预备学校）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对认知诊断中Q矩阵人工构建的瓶颈，提出课程大脑系统，通过双仓库和十一代理管道自动生成课程知识图谱，在241次运行中实现67.6%无升级解决率，每章成本1.19美元。
AI 中文摘要
认知诊断模型（CDMs）能够识别学生已掌握和未掌握的特定技能，这是个性化学习路径所需的信号，而单一的总体分数无法提供这一信息。然而，这些模型很少被实际部署。其障碍在于其前置条件：Q矩阵，即从每个评估项目到其所要求技能的映射，历来由人工编写。我们将该任务分为两个阶段：首先构建课程自身的知识图谱，即其所包含的概念和技能的完整空间，独立于任何项目；然后按需将项目映射到该图谱上。本文仅处理第一阶段。项目映射阶段已设计但未在此实现，因此，将判断成本从每个项目一次转移到每个课程一次的主张是设计理由而非研究发现。我们提出了课程大脑（Curriculum Brain），一个双仓库系统，将版本控制的知识库与一个由十一个单一职责代理组成的代理管道配对，并置于一个轻量级确定性编排器之下。它从官方课程文档中生成候选概念-技能映射，根据累积规则对其进行检查，并与从教科书中独立提取的概念-技能图进行比较，修复自身的失败，仅在无法自行解决案例时才升级给人类。在241次章节运行（168个不同章节）中，41.5%的生成器输出在无需补丁的情况下通过了两次检查，67.6%的案例无需升级即得到解决。两者均根据系统自身产生的标准进行衡量，因此描述的是内部一致性而非与外部标准的一致性，并且两者汇总了在第77次运行中因单一变更而分离的两种管道配置；在此之后，数字分别为57.0%和91.5%。观察到的支出为每章节1.19美元，仅为API支出，不包括人工审查。我们发布了框架和由此产生的课程数据集。
英文摘要
Cognitive Diagnostic Models (CDMs) identify which specific skills a student has and has not mastered, the signal a personalized learning path needs and a single aggregate score cannot give. Yet they are rarely deployed. The obstacle is their precondition: the Q-matrix, a mapping from every assessment item to the skills it requires, historically authored by hand. We separate the task into two stages: first construct the curriculum's own knowledge graph, the full space of concepts and skills it contains, independent of any item; then map items against that graph on demand. This paper addresses the first stage only. The item-mapping stage is designed but not implemented here, so the claim that this shifts judgment cost from once per item to once per curriculum is a design rationale rather than a finding. We present Curriculum Brain, a two-repository system pairing a version-controlled knowledge base with an agentic pipeline of eleven single-responsibility agents under a thin deterministic orchestrator. It generates candidate concept-skill mappings from official curriculum documents, checks them against accumulated rules, and compares them with a concept-skill map extracted independently from the textbook, repairing its own failures and escalating to a human only when it cannot resolve a case itself. Across 241 chapter runs (168 distinct chapters), 41.5% produced a Generator output passing both checks without a patch, and 67.6% resolved without escalation. Both are measured against criteria the system itself produced, so both describe internal consistency rather than agreement with an external standard, and both pool two pipeline configurations separated by a single change at run 77; after it the figures are 57.0% and 91.5%. Observed spend was $1.19 per chapter, API spend only, excluding human review. We release both the framework and the resulting curriculum dataset.
Comments28 pages, 3 figures, 7 tables. Code: https://github.com/MaximusTitan/q-matrix-agents and https://github.com/MaximusTitan/q-matrix-kb-template. Dataset: https://github.com/MaximusTitan/q-matrix-dataset
