做AI教育或智能辅导系统的开发者会发现，LLM在关键教学诊断上存在系统性盲区——它擅长确认正确，却搞不定“部分正确”和“错误”的微妙区分，这直接影响辅导质量。建议点开看看混合架构方案，或许能帮你避开部署中的坑。
一项新研究评估了七个大型语言模型（LLM）在命题逻辑辅导中的诊断精度，使用知识图谱生成的10,836个解决方案-反馈对作为基准。结果显示，LLM在识别最优步骤上接近完美，但系统性地过度拒绝有效但次优的推理，并过度验证错误的解决方案——这正是自适应辅导最需要精准反馈的地方。这些失败在所有模型中一致出现，表明是架构限制而非信息不足。此外，准确诊断并不总能转化为可操作的反馈，揭示了诊断判断与教学效果之间的差距。研究建议，LLM更适合混合架构，由知识图谱模型负责诊断，LLM负责开放式引导和对话。
Confirming Correct, Missing the Rest: LLM Tutoring Agents Struggle Where Feedback Matters Most
Effective tutoring requires distinguishing optimal, valid but suboptimal, and incorrect student solutions, a distinction central to intelligent tutoring systems (ITS) but untested for LLM-based tutors. As LLMs are increasingly explored as conversational complements to ITS, evaluating their diagnostic precision is essential. We present a benchmark of seven LLM feedback agents in propositional logic using knowledge-graph-derived ground truth across 10,836 solution--feedback pairs and three feedback conditions. Models achieved near-ceiling performance on optimal steps but systematically over-rejected valid but suboptimal reasoning and over-validated incorrect solutions, precisely where adaptive tutoring matters most. These failures persisted across models regardless of solution context, suggesting architectural rather than informational limits. Moreover, accurate diagnosis did not reliably produce pedagogically actionable feedback, revealing a gap between diagnostic judgment and instructional effectiveness. Our findings suggest that LLMs are better suited for hybrid architectures where KG-grounded models handle diagnosis while LLMs support open-ended scaffolding and dialogue.