1
Scaling Textual Gradients via Sampling-Based Momentum
把大模型反馈当“文本梯度”，用采样动量解决提示词优化的扩展与稳定性问题，方法新颖且直击痛点。
arXiv:2506.00400v4 Announce Type: replace Abstract: LLM-based prompt optimization, which uses LLM-provided ``textual gradients'' (feedback) to refine …