Offloop搞了个D1路由层，3B参数就能自动调度多个AI agent，基准上干掉了Claude Code和Codex，挺有意思。
Offloop团队推出D1层，一个仅3B参数的多智能体路由层。它在GDPval基准上达到SOTA，领先Claude Code和Codex，覆盖美国年收入2.4万亿美元的岗位需求。D1自动决定每个步骤由哪个智能体执行，替代手动比较多个agent输出。
This might be big Instead of just sending one prompt to multiple agents and comparing the results m...
This might be big Instead of just sending one prompt to multiple agents and comparing the results manually... this D1 layer is: - Deciding which agent acts at each step - Only 3B active parameters - SOTA on router benchmarks So it just acts between you and the different agents Pretty cool! Your browser does not support the video tag. 🔗 View on Twitter Offloop @Offloop Introducing Offloop! We're a team of four. Today our multi-agent harness hit state of the art on GDPval, ahead of Claude code and Codex across jobs that pay $2.4 trillion a year in the US. Offloop gives every knowledge worker what the Fortune 500 spends billions on: a high-performing agent army that runs itself and grows the business. Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 2 🔄 0 ❤️ 6 👀 2912 📊 3 ⚡