CoLearn：一种在人机共学循环中学习其学习者的智能体导师
CoLearn: An Agentic Tutor that Learns its Learner in a Human--AI Co-Learning Loop
浏览论文内容
中文总结 AI 辅助
CoLearn是一种智能体导师，通过软证据贝叶斯知识追踪和自适应提问，在人机共学循环中构建学习者记忆，盲A/B评估中68-69%偏好个性化问题。
中文摘要 AI 辅助
优秀的辅导需要适应个体：它追踪学习者已知的内容，注意到他们出错的原因，并提出下一个最有帮助的问题。然而，大多数已部署的辅导工具仅提供固定的题库，并将错误答案视为单一信号。我们提出了CoLearn，一种交互式智能体导师，支持迭代辅导循环：学习者进行练习，系统构建基于证据的学习者掌握程度和误解的记忆。该记忆随着证据的积累而更新，并用于生成下一个个性化问题。CoLearn包含三个组件：（i）持久的学习者状态记忆，使用贝叶斯知识追踪的软证据变体按主题更新掌握程度，其中大语言模型充当连续观察函数；（ii）自适应问题生成，针对学习者最薄弱的主题和反复出现的误解；（iii）证据视图，通过实时进度可视化和盲A/B比较使个性化可见且可测试。在盲A/B评估中，基于该记忆条件化的问题在68-69%的情况下优于非个性化问题，而在具有隐藏真实掌握程度的人物模拟中，智能体的信念收敛于学习者的真实掌握程度。
英文摘要
Good tutoring adapts to the individual: it tracks what a learner knows, notices why they go wrong, and asks the next question that will help most. Most deployed tutoring tools instead serve fixed item banks and treat a wrong answer as a single bit of signal. We present CoLearn, an interactive, agentic tutor that supports an iterative tutoring loop: the learner practises, and the system builds an evidence-grounded memory of the learner's mastery and misconceptions. This memory is updated as evidence accumulates and is used to generate the next personalised question. CoLearn has three components: (i) a persistent learner-state memory that updates per-topic mastery with a soft-evidence variant of Bayesian Knowledge Tracing, where a large language model acts as a continuous observation function; (ii) adaptive question generation that targets the learner's weakest topic and recurring misconceptions; and (iii) an evidence view that makes personalisation visible and testable through live progress visualisation and blind A/B comparison. In blind A/B evaluation, questions conditioned on this memory are preferred over non-personalised ones 68-69% of the time, and in persona simulations with hidden ground-truth mastery the agent's belief converges toward the learner's true mastery.
