研究代码代理交接时的重发现成本，提升协作效率
Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks
- 设计交接协议，在指定点中断代理并冻结仓库状态
- 结构化交接信息使后续代理效率提升42%-63%
- 强调评估应关注接手成本而非仅看任务完成率
现有代码代理评测多基于连续执行任务，但真实开发中任务常被中断、转交、审查并由他人从部分状态继续。本文通过‘交接债务’——即前任工作不透明或不完整带来的重发现成本——研究此缺失维度。我们设计接管协议，在75个源任务中生成181个交接点，每个后续模型完成724次接管实验。对比四种交接视图（仅仓库状态、原始日志、摘要笔记、结构化笔记），含上下文的交接方式使代理事件中位数减少20%-59%，提示词总长度减少42%-63%。解题率提升较小且依赖模型，但效率增益稳定。结果表明，代码代理评估应不仅报告是否解决任务，还应衡量他人接手的成本。
原文摘要 · Abstract (English)
Coding-agent benchmarks evaluate whether a single uninterrupted agent can resolve a repository issue. Real software work is messier: tasks are interrupted, reassigned, reviewed, and resumed from partial states left by another agent or engineer. We study this missing dimension through handoff debt: the rediscovery cost imposed when a predecessor's work is opaque or incomplete. Our takeover protocol interrupts a coding agent at deterministic handoff points, freezes the repository, and evaluates successor agents under four handoff views: repository state only, raw trace, summary notes, and structured notes. Across 75 source tasks, the protocol generates 181 handoff-point tasks and 724 takeover runs per successor model. Across three successor models, context-bearing handoffs reduce median agent events by 20-59% and cumulative prompt tokens by 42-63% relative to repository-only takeover. Solved-rate effects are smaller and model-dependent, but efficiency gains are consistent. These findings suggest that coding-agent evaluation should report not only whether a task is solved, but also how costly that work is for another agent to resume.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。