Meta 论文提出 RSD：智能体无需人工标注也能从自身历史轨迹学习
Meta 这篇论文教你把智能体的失败记录也变成训练数据，不用人工标注，Qwen3-8B 在 ALFWorld 上跑到 76.6%，比有奖励信号的方法还强。
Meta 发布论文，提出 RSD 方法，让模型在任务结束后回看自己的每一步轨迹并打分，从而在没有正确答案和奖励信号的情况下完成训练。在 ScienceWorld 基准上，Qwen3-14B 的成功率从 12.9% 提升到 20.6%。在 ALFWorld 上，Qwen3-8B 达到 76.6%，超过了所有被测试的方法，包括使用了奖励或标准答案的方法。论文还指出每轮都要重新生成复盘笔记：用固定旧笔记时 ALFWorld 成功率到第 3 轮只有 59.7%，用新鲜笔记则是 67.9%。
New Meta paper finds that AI agents can learn from their own past attempts at tasks, even ones nobody marked right or wrong, by looking back at each step once they know how it ended.
Most agent runs come with no correct answer and no reward, which standard training relies on. RSD has the same model reread each finished run, knowing how it ended and what worked on similar tasks. It scores every action, and the agent learns from those scores.
On ScienceWorld, Qwen3-14B's success rate rose from 12.9% to 20.6%. On ALFWorld, Qwen3-8B hit 76.6%, beating every other method tested, even ones given rewards or ground truth.
Keep your agent's unlabeled runs, failures included, and train it on a hindsight review of them. Rebuild the review each round, since frozen notes left ALFWorld success at 59.7% by round 3, versus 67.9% with fresh ones.
