Google 论文提出 OO-Harness：按任务类型演化专用智能体 harness
New Google paper shows that agents score higher when each task gets a specialized harness from a shared family, not 1 global harness.
Google 新论文提出 OO-Harness，把智能体 harness 按代码类演化，每个专用 harness 继承父类并只改动所属任务簇需要调整的部分，再由路由器根据基础运行结果选择专用 harness 或保留基础结果。在 AutomationBench 业务工作流上，该方法得分 77.41%，基础 harness 为 61.62%，全局方法 Meta-Harness 为 63.92%；在陌生应用上它保留基础 harness，通过率维持 59.18%，而 Meta-Harness 的全局 harness 降至 44.90%。作者建议混合负载时以基础 harness 作兜底，仅在运行暴露已知问题时路由到专用 harness。
推荐理由
AI 评分 57
原文给出 OO-Harness 与全局 harness 方法在 AutomationBench 上的分数对比，可看任务专用 harness 的收益与代价。
主题
正文
New Google paper shows that agents score higher when each task gets a specialized harness from a shared family, not 1 global harness.
An agent harness is the prompts, tools and control code around a model. Most tuning methods evolve 1 global harness, though a fix for 1 task type can hurt another.
OO-Harness evolves harnesses as code classes, and each specialist inherits from a parent and changes only what its cluster needs. A router reads a normal base run and picks a specialist or keeps the base result.
On AutomationBench business workflows, it scored 77.41% versus 61.62% for the base harness and 63.92% for Meta-Harness, a global method. On unfamiliar apps, it kept the base harness and held 59.18% pass rate, while Meta-Harness's global harness fell to 44.90%.
For mixed workloads, keep the base harness as a fallback and route to specialists only when a run shows a known problem.