SWEeper-Bench：智能体能否发现交互式软件中的 bug？
原标题：SWEeper-Bench: Can Agents Discover Bugs in Interactive Software?
AI 摘要
该论文提出 SWEeper-Bench 基准，包含 200 个来自真实开源 Web 应用 bug 修复的任务，要求编码智能体仅凭代码库和开放式请求自行发现并修复依赖多步交互才能触发的 bug。评估显示 15 个前沿智能体中最佳仅通过 59.0% 任务，主要瓶颈在于识别 buggy 行为而非修复本身；若给出详细 bug 描述，通过率升至约 96%。该基准将编码智能体评估从修复推进到发现阶段。
正文节选
in Interactive Software? ††footnotetext: ∗ Equal Contribution Abstract - Coding agents increasingly interact with users by generating interactive software on the fly rather than replying in text, yet many bugs in such software reveal themselves only after multi-step interactions. Today, users must discover these bugs and wait for fixes, making the development loop slow and expensive. Existing benchmarks typically assume the bugs have already been identified, leaving agents’ ability to find inter