Tag
该论文提出 MISCONCEPTDIALOGUE 框架，发现基准式精确匹配评分与人工校准的 LLM-as-judge 在相同对话上相差 39.2 个百分点，并指出 LLM 数学导师几乎不会依据所提供的诊断信息调整教学。
Physics Tutor is an AI agent designed to teach physics through first principles reasoning, using Socratic guidance and adaptive techniques to improve understanding and address misconceptions.