Cursor新出的智能体集群让强模型负责规划，弱模型干活，用SQLite重写Rust测试全满分，比旧版靠谱多了。
Cursor用升级后的agent swarm和旧版本分别尝试仅凭文档将SQLite用Rust重写，新系统将规划者与执行者分离。所有配置的agent swarm均在测试套件中取得100%得分，而旧版swarm因自身合并冲突失败。这一实验表明，使用像Claude或GPT-4等前沿模型进行任务规划，可以用更便宜的模型完成大部分编码工作。
Cursor's agent swarm suggests cheaper models can handle most coding when frontier models plan the work
Cursor asked its upgraded agent swarm and its predecessor to rebuild SQLite in Rust using only the documentation, with no source code or internet access. Every configuration of the new system, which separates planners from workers, eventually scored 100 percent on the test suite. The old swarm choked on merge conflicts of its own making. The article Cursor's agent swarm suggests cheaper models can handle most coding when frontier models plan the work appeared first on The Decoder .