相比原版 43 万行代码，这个 99% 的“瘦身”极其震撼。它向开发者证明了一件事：构建一个全功能的、能干活的 AI Agent，其实不需要几十万行代码的堆砌，核心逻辑其实非常纯粹。
AI Center of Excellence for its Bangalore office. This role focuses on designing, developing, and deploying cloud-based ...
On SWE-Bench Verified, the model achieved a score of 70.6%. This performance is notably competitive when placed alongside significantly larger models; it outpaces DeepSeek-V3.2, which scores 70.2%, ...
一些您可能无法访问的结果已被隐去。
显示无法访问的结果