arXiv cs.CL· Shuochen Chang, Qianli Ma, Yibo Miao, Qingyang Liu, Bingjie Gao, Haonan Zhao, Siyu Sun, Yulin Sun, Han Zhao, Jiangtong Li·· 11 小时前AI 评分40
Switch-SWE：编码智能体在未完成任务间切换时还能保持专注吗？
Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?
AI 导读
研究团队提出 Switch-SWE 基准，用于衡量编码智能体在同一仓库多个未完成任务交错进行时能否恢复先前任务。该基准包含来自 19 个 Python 仓库的 200 个焦点任务、400 组匹配会话规格；7 个编码智能体在任务交错后焦点任务解决率平均下降 11.5 个百分点，区间为 6.0 至 15.0 个百分点。
正文 · 原文
Abstract:Software development sessions often involve several unfinished tasks rather than one issue carried through to completion. As coding agents take on repository-level development, they need to recover an earlier task's requirements and partial progress after intervening work. Existing repository-level benchmarks typically score one issue-to-patch episode and do not directly measure whether an agent can resume a task after advancing other unfinished work in the same repository. We introduce \textbf{\ourmethod}, a benchmark for focus-task resumption in sessions that interleave unfinished tasks drawn from the same source repository, with a persistent checkout for each task. Each focus task is evaluated in matched uninterrupted and switched sessions with identical focus requirements and executable verifiers. The switched session interleaves ordered stages from other unfinished tasks in the same repository, while only the final focus patch is scored. \ourmethod~contains 200 focus tasks from 19 Python repositories, reconstructed from issue, pull-request, and review histories and rendered as 400 matched session specifications. Across 7 coding agents, interleaved unfinished work produces an average focus-task resolution gap of 11.5 percentage points, ranging from 6.0 to 15.0 percentage points. Trajectory analysis identifies cross-task requirement confusion and loss of task state as recurrent resumption behaviors. We introduce a plug-in context-management module that selects task-relevant history and maintains concise task-state summaries. On OpenCode, the module improves focus-task completion under same-repository task switching by 5.5 to 15.5 percentage points across the evaluated models. Code is available at this http URL.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.02017 [cs.CL] |
| (or arXiv:2611.02017v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.02017 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shuochen Chang [view email]
[v1]
Sun, 1 Nov 2026 16:04:16 UTC (784 KB)
来源：arXiv cs.CL · arxiv.org