1
Strategy-Induct: Task-Level Strategy Induction for Instruction Generation
新研究提出Strategy-Induct框架，无需标注答案即可从输入-输出对中自动归纳更优任务级提示，提升LLM指令生成效率。
arXiv:2605.20924v1 Announce Type: new Abstract: Designing effective task-level prompts is crucial for improving the performance of Large Language Mode…