Orchard：用于可扩展智能体AI的开源框架
原标题：Orchard: An open framework for scalable agentic AI
AI 摘要
微软研究博客发布了Orchard，一个用于可扩展和成本效益的智能体AI研究的开源框架，其核心是Orchard Env，一个可复用的环境服务，支持在多个任务领域训练和评估智能体。Orchard支持软件工程、网页导航和个人助理智能体，并能在Codex、OpenClaw和ZeroClaw等真实部署框架中直接训练。Orchard-SWE在SWE-bench Verified上达到69.7%的准确率，使用约30亿活跃参数，接近使用超过10倍参数的先进系统。项目还发布了训练数据和评估方法，以帮助研究社区构建和研究开放智能体系统。
正文节选
At a glance - Orchard is an open-source framework for scalable and cost-effective agentic AI research, built around Orchard Env, a reusable environment service for training and evaluating agents across task domains. - The same Orchard infrastructure supports software-engineering, web-navigation, and personal-assistant agents, and can train them directly inside real deployment harnesses such as Codex, OpenClaw, and ZeroClaw—letting researchers reuse environments, data pipelines, and evaluation wo