Microsoft Research Introduces Orchard for Scalable Agentic AI

Microsoft Research has unveiled Orchard, an open-source framework designed for scalable agentic modeling. At its core is Orchard Env, a lightweight Kubernetes environment that offers reusable, isolated components for building and running AI agents at scale, encompassing data collection, reinforcement learning, and evaluation. Orchard-SWE, a specific application within the framework, achieves 73% on SWE-bench Verified with value-model reranking, approaching frontier systems ten times larger.