快讯
laxman发布Step-Jev，为无标准答案的agent RL提供逐步奖励
laxman称，DeepSeek R1之后常见做法是只奖励最终答案以避免逐步奖励被钻空子，但团队发现相反结果。Step-Jev提供step-by-step rewards；冻结正文在“our agent learned”处截断，未给出具体实验结果。
事件来源
查看原文
Help Step-Jev, my reward is stuck (plateauing) 🥵 laxman: 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