LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring 事件

LLMs Are Already Good Tutors: Training-Free Prompt Optimization for Pedagogical Math Tutoring arXiv:2605.27088v1 Announce Type: new Abstract: Aligning LLMs for math tutoring typically requires RL-based training with multi-GPU infrastructure. We investigate whether training-free prompt optimization-evolving only the system prompt via API calls-can serve as a practical alternative. We adapt 7 published methods and propose 5 education-specialized methods, evaluating these 12 methods under 5 condit