Cursor's planner-worker agent swarm rebuilds SQLite in Rust, passing 80% of tests in 4 hours with widely varying costs

Cursor 测试新型 AI 智能体集群：规划者+执行者分工，4小时通过80% SQL测试

Cursor redesigned its agent swarm into a tree-shaped planner-worker split and retested it on rebuilding SQLite in Rust from docs. The new swarm beat the old one in every model config: with Grok 4.5 it hit 80% on a held-out SQL test suite in 4 hours, while the old swarm spiraled before hour two. Quality stayed similar across model mixes, but costs varied enormously—the post shows a comparison chart without exact dollar figures. The design isolates context so planners never see implementation details and workers only focus on narrow tasks, preventing drift on long runs.

Why it matters: First-party engineering experiment from Cursor, not a press release. The planner-executor tree architecture comes with concrete numbers (4 hours, 80% pass rate), hitting all three HKR axes. Not 85+ because this is a single experiment, not a product launch, and the post doesn't...