代理利用(系统提示,工具集,执行挂钩,和围绕模型的上下文管理支架)是代理任务成功的关键决定因素。自动化线束演化可以使较小的模型以前沿模型成本的一小部分来在特定领域的任务上表现良好。由于线束和模型权重都会影响行为,，我们询问如何将线束进化和轻量级微调结合起来。在七个企业代理任务, 中，我们首先使用较弱的模型, 开发一个工具，然后发现更强的专家通常更有效地使用它,，这表明专家监督可以缩小剩余的差距。然而，, 在专家的 完整轨迹上训练较弱的模型，在进化的安全带下会适得其反。: 在 Qwen3-Coder 和 Gemma 4, 上，所有七项任务的性能都会下降 4 到 30 个点，尽管相同的程序在未进化的安全带下有所帮助。我们的分析表明，模仿转移了知识并增加了支架的使用,，但破坏了模型线束拟合:，较弱的模型采用了专家的的规划策略，但没有能力执行它，并且不再匹配围绕其本地规划风格发展的线束。因此，我们开发了一个由元级 MLE 代理, 自动执行的策略专家校正管道,，该管道将较弱模型 自己的推出中的失败回合进行本地化，并要求专家仅重写该回合。这保留了 model的 的规划风格，并结合了线束进化和模型适应的收益。我们的结果确定并解决了线束和权重更新之间的争论根源,，从而为特定领域的企业任务的经济共同进化提供了一个保持兼容性的方法。

Agent harnesses (the system prompt, tool set, execution hooks, and context-management scaffolding around a model) are a critical determinant of agentic task success. Automated harness evolution can enable smaller models to perform well on domain-specific tasks at a fraction of frontier-model cost. Since both the harness and model weights shape behavior, we ask how harness evolution and lightweight fine-tuning should be combined. Across seven enterprise agent tasks, we first evolve a harness with the weaker model, then find that a stronger expert often uses it more effectively, suggesting expert supervision could close the remaining gap. However, training the weaker model on the expert的 complete trajectories under the evolved harness backfires: performance regresses on all seven tasks by 4 to 30 points across Qwen3-Coder and Gemma 4, even though the same procedure helps under the unevolved harness. Our analysis shows that imitation transfers knowledge and increases scaffold usage, but disrupts model-harness fit: the weaker model adopts the expert的 planning strategy without the competence to execute it and no longer matches the harness evolved around its native planning style. We therefore develop an on-policy expert-correction pipeline, automated by a meta-level MLE agent, that localizes the failing turn in the weaker model的 own rollout and asks the expert to rewrite only that turn. This preserves the model的 planning style and combines the gains of harness evolution and model adaptation. Our results identify and resolve a source of contention between harness and weight updates, yielding a compatibility-preserving recipe for economical co-evolution on domain-specific enterprise tasks.

科目:人工智能(cs.AI)

Subjects: Artificial Intelligence (cs.AI)