# Microsoft trains Qwen3.8-27B on 187 tasks to improve agent repeatability > Source: > Published: 2026-10-23 02:32:11+00:00 # Microsoft trains Qwen3.8-27B on 187 tasks to improve agent repeatability **The Microsoft and Hugging Face experiment raised average success by 9.08 percentage points across 507 benchmark tasks, while the model solved at least one attempt on seven fewer tasks.** By [Ryan Merket](https://runtimewire.com/author/ryan-merket) · Published · Updated Primary source: [Hugging Face Newsroom](https://huggingface.co/blog/microsoft/thinkingbox-training) ## Why it matters Executable checks connect agent training to the actual records business systems retain. Microsoft's results show stronger repeatability on its benchmark. On October 22nd, Microsoft and [Hugging Face](https://huggingface.co/microsoft?ref=runtimewire) published an open-source training system that rewards an AI agent for the database state it leaves behind. In the [release results](https://huggingface.co/blog/microsoft/thinkingbox-training?ref=runtimewire), Microsoft applied scientist [Tuhin Kundu](https://www.linkedin.com/in/tuhinkundu?ref=runtimewire) and collaborators report that fine-tuning [Qwen3.8-27B](https://runtimewire.com/models/qwen/qwen3.8-27b) with executable checks raised average success by 9.08 percentage points across a 507-task evaluation.… When you purchase through links in our articles, [we may earn a small commission](https://runtimewire.com/affiliate-monetization-standards). This doesn’t affect our editorial independence.