Microsoft Research Unveils Orchard for Scalable Agentic AI

Microsoft Research has introduced 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. Orchard also includes specific tools like Orchard-SWE, Orchard-GUI, and Orchard-Claw, along with training data and evaluation methods. The framework uses a value model trained on past reinforcement learning rollouts to rerank candidate solutions, achieving new state-of-the-art results on benchmarks like SWE-bench Verified.