Diogo Almeida· @CompleteSkeptic · X·· 2 小时前AI 评分37
AI 导读
太牛了!用通用验证器(jev)做过程奖励——希望它对抗鲁棒性足够强
正文
super sick! process rewards using a universal verifier (jev) - hopefully it's adversarially robust enough
Excited to release Step-Jev 🔥 step-by-step rewards for agent RL, even when there’s no answer key After DeepSeek R1, everyone said step rewards get hacked, so just reward the final answer. We found the opposite. With an AI judge grading only the final answer, our agent learned to fool it and accuracy dropped every single update until it was worse than no training at all. Step rewards fixed it. Everything is open!在 X 查看被引用的帖子
来源:Diogo Almeida · x.com