交接代价：LLM智能体中非原生轨迹的延续

摘要

编码智能体执行长时间运行的任务，涵盖数十次模型调用、工具使用和代码编辑。随着这些运行逐步推进，用户面临一个实际的质量-成本权衡：当较便宜的模型遇到困难时升级到更强的模型，或在复杂的推理完成后降级。每次切换都要求接收方继续执行由另一个模型产生的非原生轨迹。我们研究这种交接如何影响质量和成本，以及接收方继承的轨迹信息变化如何改变结果。使用来自Claude和GPT家族的成对低成本、低能力（LC）和高成本、高能力（HC）模型，我们改变交接方向、时机和接口，比较完整轨迹转移、压缩以及在保留仓库状态的同时移除轨迹。在两个模型家族中，完整轨迹升级仅恢复了LC到HC质量差距的不到一半，同时产生了可观的成本溢价。我们将这种成本-质量损失称为交接税。相比之下，降级提供了一个有利的成本-质量平衡点。有趣的是，偏好的接口也随方向反转：减少LC模型的轨迹信息提高了升级质量，而移除HC模型的轨迹则降低了降级质量。

English

Coding agents perform long-running tasks spanning dozens of model calls, tool uses, and code edits. As these runs unfold, users face a practical cost-quality trade-off: escalating to a stronger model when a cheaper one struggles, or downshifting once the hard reasoning is complete. Each switch requires the receiver to continue a non-native trajectory produced by another model. We study how this handoff affects quality and cost, and how varying the trajectory information inherited by the receiver changes the outcome. Using pairs of low-cost, low-capability (LC) and high-cost, high-capability (HC) models from the Claude and GPT families, we vary handoff direction, timing, and interface, comparing full-trajectory transfer, compaction, and trajectory removal while preserving the repository state. Across both model families, full-trajectory escalation recovers less than half of the LC-to-HC quality gap while incurring a substantial cost premium. We term this cost-quality penalty the handoff tax. By contrast, downshift offers a favorable cost-quality point. Interestingly, the preferred interface also reverses with direction: reducing LC-model trajectory information improves escalation quality, whereas removing the HC-model trajectory reduces downshift quality.