发表机构
AWS, Agentic AI（亚马逊云科技智能体人工智能部门）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究聚焦大语言模型智能体的交接代价，通过对比Claude和GPT系列模型的不同交接设置，发现完整轨迹升级质量提升有限且成本高，降级更具优势，且交接接口偏好随方向反转。
AI 中文摘要
编码智能体执行跨越数十次模型调用、工具使用和代码编辑的长时间运行任务。随着这些运行的推进，用户面临着实际的成本-质量权衡：当低成本模型遇到困难时，升级到更强的模型，或在困难推理完成后降级。每次切换都需要接收方延续由另一个模型生成的非原生轨迹。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的变化如何改变结果。使用来自Claude和GPT系列的低成本、低能力（LC）模型与高成本、高能力（HC）模型的配对，我们改变交接的方向、时间和接口，比较完整轨迹转移、压缩和轨迹移除，同时保留仓库状态。在两个模型系列中，完整轨迹升级恢复了不到LC到HC质量差距的一半，同时产生了显著的成本溢价。我们将这种成本-质量惩罚称为交接代价。相比之下，降级提供了有利的成本-质量点。有趣的是，首选接口也随方向反转：减少LC模型轨迹信息可提升升级质量，而移除HC模型轨迹会降低降级质量。
英文摘要
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.
