AI 学会从自己的失败中迭代，无需人工标注
AI 智能体（比如帮你写代码、做研究的工具）通常需要一套“工具箱”（技能、工具、流程）来解决问题。以前，优化这套工具箱需要人工标注正确答案，这在真实场景中很难做到。这篇论文提出了一种新方法 RHO，让 AI 自己从过去的任务轨迹中学习：它先挑出之前做错或做得不好的任务，然后重新尝试解决，并通过自我验证和一致性检查来评估不同方案，最后选出最优的改进。在软件工程测试中，一次优化就让通过率从 59% 提升到 78%，且无需任何外部评分。这不是你明天就能用的功能，但它展示了一种让 AI 持续自我进化的新方向——未来你的 AI 助手可能会越用越聪明，因为它会从自己的错误中学习。
📄 原文摘要(英文)
AI agents rely on a harness of skills, tools, and workflows to solve complex problems. Continually improving this harness is essential for adapting to new tasks. However, existing optimization methods typically require ground-truth validation sets, yet such labeled data is difficult to acquire in practical deployment settings. To address this problem, we introduce Retrospective Harness Optimization (RHO), a self-supervised method that optimizes the agent harness using only past trajectories. Specifically, RHO selects a diverse coreset of challenging tasks from past trajectories and re-solves them in parallel. The agent analyzes these rollouts using self-validation and self-consistency, then generates candidate harness updates and selects the most effective one by its own pairwise self-preference. We evaluate RHO across three diverse domains, spanning software engineering, technical work, and knowledge work. Notably, a single optimization round improves the pass rate on SWE-Bench Pro from 59% to 78% without any external grading. Furthermore, our analysis demonstrates that RHO effectively targets prior failure modes. As a result, the optimized harness alters the agent's behavior patterns and sustains higher accuracy during long-horizon sessions.