Microsoft Research open-sources Orchard for scalable agentic AI
Microsoft Research released Orchard, an open framework to standardize training and evaluation of AI agents across task types. The project aims to cut infrastructure friction so researchers can get strong agent performance with smaller, cheaper models.
LLMgram editorial selection and synthesis · @llmgram. LLMgram is not the original publisher of this information.
Continue on LLMgram: Open in AI Signal →
Original reporting: Orchard: An open framework for scalable agentic AI