跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 22 天前AI 評分46

Switch-SWE:編碼智能體在未完成任務間切換時能否保持專注?

Switch-SWE: Do Coding Agents Hold Focus When Switching Between Unfinished Tasks?

AI 導讀

Switch-SWE 基準測試顯示,編碼智能體在同一程式碼庫交錯處理未完成任務時,焦點任務的完成率平均下降 11.5 個百分點。基準涵蓋 19 個 Python 程式碼庫中的 200 項焦點任務,並評估 7 個編碼智能體。OpenCode 上的情境管理模組令焦點任務完成率提升 5.5 至 15.5 個百分點。

正文

Published on Nov 1

Authors:

,

,

,

,

,

,

,

,

Abstract

A benchmark for resuming interrupted software tasks reveals performance drops from interleaved work, and a context-management module improves recovery.

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 \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 github.com/Miraclecsc/Switch-SWE.

View arXiv page View PDF Project page GitHub Add to collection

Get this paper in your agent:

hf papers read 2611.02017

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.02017 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.02017 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.02017 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co