Turbo Harness：实例自适应 Harness 优化

中文摘要 AI 辅助

自动化搜索有效的 harness 是使智能体能够递归自我改进的重要一步。现有的 harness 优化通常产生一个单一的全局 harness，并统一应用于所有任务实例。然而，一个在平均情况下表现良好的 harness 可能并非对每个实例都是最优的。我们引入了 Turbo Harness，一个能够通过重用原始优化过程中生成的信息，将全局优化的 harness 适应到每个实例的框架。具体来说，Turbo Harness 回收在完成的全局 harness 优化运行期间产生的产物，并将它们总结成一个结构化的 playbook。我们训练一个 harness 编辑器，以利用这种先前的优化经验来生成针对全局 harness 的实例特定补丁。在推理时，编辑器使用实例和 playbook 来构建一个定制的 harness，执行模型在其中运行。通过数值实验，我们表明 Turbo Harness 在跨越交互式智能体任务、软件工程和长视野终端任务的七个基准上，持续优于现有的 harness 优化基线。

英文摘要

Automating the search for effective harnesses is an important step toward enabling agents to recursively self-improve. Existing harness optimizations typically produce a single global harness that is applied uniformly across task instances. However, a harness that works well on average may not be optimal for every instance. We introduce Turbo Harness, a framework that can adapt a globally optimized harness to each instance by reusing information generated during the original optimization process. Specifically, Turbo Harness recycles artifacts produced during a completed global harness optimization run, and summarizes them into a structured playbook. We train a harness editor to leverage this prior optimization experience to generate instance-specific patches to the global harness. At inference time, the editor uses the instance and the playbook to construct a tailored harness in which the execution model operates. Through numerical experiments, we show that Turbo Harness consistently outperforms existing harness optimization baselines across seven benchmarks spanning interactive agent tasks, software engineering, and long-horizon terminal tasks.

发表机构

• Rutgers University（罗格斯大学）
• Red Hat AI Innovation（红帽AI创新）
• MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）

机构由 AI 辅助整理，请以论文原文为准。