微软发布开源智能体框架 Orchard，支持多任务训练与评估
微软开源 Orchard 框架，用统一环境服务支撑多种智能体任务，小模型也能逼近大模型效果。
Orchard 是微软开源的智能体研究框架，核心是轻量级 Kubernetes 环境，可复用不同任务域的隔离组件。它发布了三个训练配方：Orchard-SWE（代码修复，SWE-Bench 67.5%）、Orchard-GUI（网页导航，WebVoyager 74.1%）和 Orchard-Claw（个人助手，pass@3 59.6），用约 30 亿参数接近百亿级模型的性能。
正文摘录
 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 pipe…