arXiv cs.AI· Victor Shea-Jay Huang, Rongqing Li, Zhangyue Yin, Kelong Mao, Yaqi Zhao, Xinyuan Wang, Yao Yin, Lirui Luo, Renrui Zhang, Hongsheng Li·· 12 小时前AI 评分45
SWE-Shift：评估编码智能体在执行中变化的工作空间中的表现
SWE-Shift: Evaluating Coding Agents in Evolving Workspaces
AI 导读
SWE-Shift 是一个评估编码智能体在执行中途遭遇任务相关变更时表现的基准，包含 12 类变更、120 个场景，每场景在 9 个预定干预位置评测。17 个编码智能体系统的 Shifted 成功率均低于 Clean，GPT-6 Astra 从 67.35% 降至 24.79%，配对成功率仅 20.34%。
正文 · 原文
Abstract:Repository-level coding benchmarks largely assume that tasks and environments remain unchanged throughout execution. In software development, code, dependencies, runtime state, and requirements can change while an agent is still working. We introduce SWE-Shift, a benchmark for evaluating coding agents under such mid-execution changes. From the same saved history and workspace, a Clean continuation proceeds without intervention, while a matched Shifted continuation receives a task-relevant update. Success requires completing the current task, preserving still-valid work, and satisfying the applicable state and evidence checks. The benchmark contains 120 scenarios across 12 change families, each evaluated at nine scheduled intervention positions. We evaluate 17 coding-agent systems, all of which have lower Shifted than Clean success. GPT-6 Astra drops from 67.35% to 24.79%, with 20.34% paired success. Tool/session changes and stale evidence yield zero paired success across all systems. Late-position paired success is lower for some systems and higher for others. These results show that success on the unchanged task can coexist with failures to preserve work, recover state, or refresh evidence after an update.
| Comments: | 47 pages. Code: this https URL |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.32196 [cs.AI] |
| (or arXiv:2610.32196v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32196 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Victor Shea-Jay Huang [view email]
[v1]
Fri, 23 Oct 2026 05:47:59 UTC (1,841 KB)
来源：arXiv cs.AI · arxiv.org