Awesome RL with Human Feedback / 2025 / arXiv

Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback

作者：Yafu Li, Xuyang Hu, Xiaoye Qu, Linjie Li, Yu Cheng · 来源：arXiv · 发布日期：2025

偏好学习对齐目标设计策略优化在线人类反馈强化学习
新标签打开 AlphaXiv新标签打开 Code
Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback figure
AlphaXiv 中文概览（可滚动查看）