Microsoft Research has released Orchard, an open-source framework for building, training, and evaluating autonomous AI agents that the company says lets relatively small open-weight models approach the performance of frontier systems more than ten times their size. The project, detailed in a blog post on August 3, 2026, is the company's most ambitious bid yet to give the broader research community the kind of infrastructure that has, until now, largely remained locked inside proprietary labs.

The release arrives as the AI industry shifts from static question-answering toward agents that can plan, reason, and act across multistep environments. For more on how the field is moving toward autonomous systems, see our latest AI industry coverage.

What Orchard actually is

At the center of the project is Orchard Env, a lightweight, Kubernetes-based environment service that provides reusable, isolated components for running agents at scale. According to Microsoft, the same service can support software-engineering agents, web-browsing agents, and personal-assistant agents without modification. It handles everything from collecting training data to reinforcement-learning rollouts and evaluation.

The key architectural decision is that the runtime environment is treated as a standalone, reusable service rather than infrastructure embedded inside a specific training framework. Because Orchard Env sits on Kubernetes, it can create, manage, and remove thousands of isolated containers in parallel. Teams can introduce new benchmarks, agent systems, or training algorithms without rebuilding the underlying infrastructure from scratch.

Training inside real harnesses

One of Orchard's distinguishing features is its ability to train agents directly inside the deployment harnesses they will actually use in production. Today's most capable agents rarely run as a bare model. They operate through sophisticated harnesses such as Codex, OpenClaw, and ZeroClaw that manage multi-turn reasoning, tool use, and connections to external systems.

Open training tools usually cannot handle these stateful, multi-process harnesses, forcing researchers to train on a simplified stand-in and then deploy in the real setting, which creates a mismatch between training and deployment. Orchard closes this gap: a lightweight proxy records the harness's own model calls as training data while each rollout runs in its own container, allowing an agent to be trained end-to-end directly in the harness it will use in production.

Three domain-specific recipes

To demonstrate the approach, Microsoft released three training workflows.

Orchard-SWE: software engineering

Orchard-SWE targets one of the most demanding settings for autonomous agents: multi-step reasoning over real codebases. It was built using the Mini-SWE-Agent framework and evaluated on SWE-bench Verified, a benchmark that tests a model's ability to navigate, diagnose, and repair real-world codebases.

To train the system, Microsoft distilled 107,000 agent interactions from two advanced open-weight models, MiniMax-M2.5 and Qwen3.5-397B, covering a broad range of GitHub issues. Using a technique called credit-assignment supervised fine-tuning, the system learns from the productive portions of partial attempts rather than discarding them entirely.

The results move the model from a 61.4% baseline on SWE-bench Verified to 69.1% with reinforcement learning, and 69.7% with dense-reward techniques. With value-model reranking, the figure reaches 73.0% — a new state of the art among open-source models of comparable size, using only about 3 billion active parameters.

Orchard-GUI: web navigation

Orchard-GUI trains a 4-billion-parameter vision-language model as a browser agent. Despite using a relatively small amount of supervision — 400 distilled demonstrations combined with 2,200 open-ended training tasks — the model achieved 74.1% on WebVoyager, 67.0% on Online-Mind2Web, and 64.0% on DeepShop, for an average of 68.4%. Microsoft says these results place it among the strongest open-source web agents to date.

Orchard-Claw: personal assistant tasks

Orchard-Claw focuses on everyday productivity tasks like reading and drafting emails, managing calendars, and searching for information. Trained on just 200 synthetic tasks and evaluated on the Claw-Eval benchmark, it completed 59.6% of tasks given up to three attempts, rising to 73.9% when paired with the stronger ZeroClaw agent system.

Why the small-model results matter

The benchmark numbers are notable because they come from models with roughly 3 to 4 billion active parameters — far smaller than the frontier systems from OpenAI, Anthropic, and Google that dominate leaderboards. Microsoft's argument is that the right training infrastructure and environment can close much of the gap, making capable agentic systems accessible to researchers and organizations that cannot afford to train or run the largest proprietary models.

Alongside the models and workflows, Microsoft released the training data and evaluation methods used to build them, with the stated goal of helping the broader research community build and study open agentic systems. The work was led by Baolin Peng, Wenlin Yao, Qianhui Wu, Hao Cheng, and Jianfeng Gao of Microsoft Research.

Stay Ahead of AI

Microsoft's Orchard release signals that the infrastructure behind frontier agentic AI is beginning to democratize. Read more breaking AI news and Read more AI news →