Cognition 模型 / Devin 博客（网页）·· 12 小时前精选AI 评分65
Cognition 发布 SWE-grep 和 SWE-grep-mini，用 RL 训练快速并行上下文检索模型
Introducing SWE-grep and SWE-grep-mini: RL for Multi-Turn, Fast Context Retrieval10.16.25We trained SWE-grep and SWE-grep-mini, fast agentic models specialized in highly parallel context retrieval. They match the retrieval capabilities of frontier coding models, while taking an order of magnitude less time. Available now in Windsurf’s new Fast Context subagent, and our new SWE-grep demo playground!
AI 导读
Cognition 训练了 SWE-grep 和 SWE-grep-mini 两个快速智能体模型，专攻高度并行的上下文检索，检索能力匹敌前沿编码模型，耗时低一个数量级。
推荐理由
官方公布了模型设计、RL 训练细节和评测数字，读者可以借此了解并行上下文检索的实现路径。
来源：Cognition 模型 / Devin 博客（网页） · cognition.com