论文提出终止滞后再量化编码智能体早解出晚停止现象
Termination Lag: Coding Agents Solve Early but Stop Late
AI 导读
arXiv 论文 2611.14960 提出「终止滞后」概念，指编码智能体首次生成正确补丁到运行结束之间的步数，覆盖五个模型、两个智能体框架和三个 SWE-bench 数据集。
正文 · 原文
Abstract:Coding agents can solve a task well before they stop working on it. We characterize \emph{termination lag}--the number of steps between an agent's first correct patch and the end of its run--across five models, two agent frameworks, and three SWE-bench datasets by recording and testing every distinct repository patch generated during execution. Our analysis reveals that 38--82% of successful runs achieve a correct solution on their initial source-code edit. However, agents continue to expend substantial effort after correct patches, with post-solution steps accounting for a median of 35--37% for Qwen3-Coder and 54--60% for Laguna-XS.2 in successful runs on SWE-bench Verified and Multilingual. Agents spend most of these additional steps verifying their work and exploring the repository. In a small fraction of cases (1--8%), this continued activity leads agents to undo their earlier correct patch, leaving the final solution incorrect.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.14960 [cs.AI] |
| (or arXiv:2611.14960v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.14960 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Burak Topcu [view email]
[v1]
Wed, 11 Nov 2026 03:11:00 UTC (702 KB)
来源：arXiv cs.AI · arxiv.org