Cognition 的 Devin Fusion 用一个小模型当副手，让主力模型专心做决策，省资源还提高缓存效率，做多代理系统的人值得看。
Cognition 的 Devin Fusion 采用混合模型架构，引入“sidekick” 小模型与前沿模型并行运行。前沿模型负责任务规划、进度监控和最终审查，小模型处理具体工作。这种设计在保证智能的同时避免不必要的 frontier 模型开销，并确保所有子代理能利用累积上下文缓存。该方法能提升缓存命中率，降低推理成本。
This is a neat idea around doing model routing and sub-agent delegation while ensuring cache hits on...
This is a neat idea around doing model routing and sub-agent delegation while ensuring cache hits on accumulated context for all agents. It makes a lot of sense: you want to ensure that all subagents can also make use of accumulated context in their cache Cognition @cognition Devin Fusion uses a hybrid-model harness built around two ideas: First, a “sidekick” agent: a smaller agent runs in parallel with the frontier agent. The frontier agent delegates work, monitors progress, and keeps ownership of planning, ambiguity, and final review. This lets Fusion stay intelligent while avoiding unnecessary frontier-model spend. 🔗 View Quoted Tweet 💬 2 🔄 3 ❤️ 33 👀 4229 📊 8 ⚡