🚨 AI News | TestingCatalog@testingcatalogOffloop 推出基于频道的多智能体工作空间，让多个 AI 智能体协同处理重复任务。其自研调度模型 D1 决定每一步由哪个智能体执行，在 GDPval 上达 84.9%，JobBench 上达 67.2%，成本仅为对比多智能体系统前沿水平的约 1/5。
Offloop has launched a Channel-based workspace where multiple AI agents can work together on recurring tasks.
A custom dispatcher model called D1 decides which agent acts at each step.
84.9% on GDPval. 67.2% on JobBench. At around 1/5 of the cost frontier of multi-agent systems it tested against.
Agents with a workplace 👀
🚨 AI News | TestingCatalog@testingcatalog · XOffloop 推出基于频道的多智能体工作空间，让多个 AI 智能体协同处理重复任务。其自研调度模型 D1 决定每一步由哪个智能体执行，在 GDPval 上达 84.9%，JobBench 上达 67.2%，成本仅为对比多智能体系统前沿水平的约 1/5。
Offloop has launched a Channel-based workspace where multiple AI agents can work together on recurring tasks.
A custom dispatcher model called D1 decides which agent acts at each step.
84.9% on GDPval. 67.2% on JobBench. At around 1/5 of the cost frontier of multi-agent systems it tested against.
Agents with a workplace 👀