编码代理越来越多地在可执行环境中运行，其中失败的尝试会产生可操作的反馈，而不仅仅是错误的答案。现有的成本感知系统通常将此类故障视为级联决策: 首先尝试廉价模型,，然后将困难案例升级为更强大且更昂贵的模型。在编码中, 然而, 执行反馈也可以使进一步的廉价模型恢复变得值得, 提出预算部署问题: 代理何时应该花费更多廉价计算, 以及何时应该升级? 我们将此故障后决策制定为异构操作上的恢复路由，并通过执行部署训练受监督的路由器。为了使同一路由器在不断变化的预算,下可用，我们添加了一个保形风险控制(CRC)层，该层选择部署时间成本损失而无需重新训练，并在可交换性下提供边际预期成本控制。在五个编码基准, 的失败中，廉价的恢复和升级展现了互补的成功模式。校准边界比固定操作, 仅提示路由器, 和主 GPT-5.4-nano/GPT-5.4 设置, 中的二进制级联基线; 有所改进，一个 CRC 校准边界点超过了始终升级的解决率，同时使用了其平均恢复成本的 35%。代码可从此 https URL 获取。
Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rather than merely an incorrect answer. Existing cost-aware systems typically treat such failures as cascade decisions: try a cheap model first, then escalate hard cases to a stronger and more expensive model. In coding, however, execution feedback can also make further cheap-model recovery worthwhile, raising a budgeted deployment question: when should an agent spend more cheap compute, and when should it escalate? We formulate this post-failure decision as recovery routing over heterogeneous actions and train a supervised router from execution rollouts. To make the same router usable under changing budgets, we add a Conformal Risk Control (CRC) layer that selects a deployment-time cost penalty without retraining and provides marginal expected-cost control under exchangeability. Across held-out failures from five coding benchmarks, cheap recovery and escalation exhibit complementary success patterns. The calibrated frontier improves over fixed actions, prompt-only routers, and a binary cascade baseline; in the main GPT-5.4-nano/GPT-5.4 setting, one CRC-calibrated frontier point exceeds always-escalate solve rate while using 35% of its mean recovery cost. Code is available at this https URL.
科目:人工智能(cs.AI)
Subjects: Artificial Intelligence (cs.AI)