这个 Princeton 开源项目让 AI 自己修 Bug，19K Stars 但 90% 的人只用了 1% 功能 🔥
Princeton University has launched an open-source AI agent called SWE-agent, designed to autonomously fix GitHub issues. Despite gaining over 19,000 stars on GitHub, most users are only utilizing a small fraction of its capabilities. The project showcases advanced features that allow it to excel in various programming challenges and cybersecurity tasks.
- ▪SWE-agent was developed by researchers from Princeton and Stanford universities and has achieved a 12% fix rate on real GitHub issues.
- ▪The agent can be configured to operate in different modes, including a cybersecurity training mode that excels in CTF challenges.
- ▪SWE-agent supports various language models, allowing users to switch between local and cloud-based models easily.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3887968) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } 韩 Posted on May 26 这个 Princeton 开源项目让 AI 自己修 Bug，19K Stars 但 90% 的人只用了 1% 功能 🔥 Princeton 大学的研究团队发布了一个开源 AI Agent，能自主修复 GitHub Issues——但它真正厉害的地方，大部分人根本不知道。 SWE-agent 由 Princeton 大学和 Stanford 大学的研究人员联合开发，自 NeurIPS 2024 亮相以来已斩获 19,310 个 GitHub Stars。项目最初在真实 GitHub Issues 上的修复率仅为 12%，但 1.0 版本配合 Claude 3.7 在 SWE-bench 基准上达到了业界领先水平。以下是你可能错过的隐藏玩法。 2026 年，AI 编程助手已经全面普及。GitHub Copilot、Cursor、Cline 占据了大部分开发者的屏幕。但 SWE-agent 代表了另一种范式——它是首个在标准化软件工程基准上与闭源方案匹敌的开源系统，而且可以直接跑在你现有的硬件上。 隐藏用法 #1：把 CTF…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
