Introducing Phi-4-reasoning, adding reasoning models to the Phi family of SLMs. The model is trained with both supervised finetuning (using a carefully curated dataset of reasoning demonstration) and Reinforcement Learning. 📌Competitive results on reasoning benchmarks with

I am thrilled to share our newest Phi models. This time we went all in on post-training to produce Phi-4-reasoning (SFT only) and Phi-4-reasoning-plus (SFT + a touch of RL) — both 14B models that pack a punch in a small size across reasoning and general purpose benchmarks🧵

Excited to share our latest Phi model, Phi4-reasoning, a small but powerful model that match the performance of much larger reasoning models up to DeepSeek R1. Here is the report for new insights into training reasoning models and evaluating them: lnkd.in/g_Pz5JQA

Excited to release our first set of reasoning models Phi-4-reasoning and Phi-4-reasoning-plus, available today on HuggingFace and Azure AI foundry. Some interesting insights below and more deep dives in following days!

Continued thanks to: Suriya Gunasekar, Shital Shah, Vaish Shrivastava, Vibhav Vineet, Vidhisha Balachandran, Guoqing Zheng, Caio César Teodoro Mendes, Piero Kauffmann, Safoora Yousefi, and Yue Wu

Excited to release Magentic-UI, a new OSS release from the team that created Magentic-One and AutoGen. Magentic-UI is a computer use agent that puts the user at the center, with controls for safety. microsoft.com/en-us/research…

A few months back, our team released Magentic-one -- showing how we can build multi-agent systems with AutoGen for complex web task completion. But how should humans interact with such systems? Magentic-UI shows how to build an agentic user experience, prioritizing

📌 You can now find all the evaluation logs (and reasoning traces for common benchmarks!) from our inference-time scaling report and the Phi-4 reasoning report at  huggingface.co/datasets/micro…. The evaluation code can be found at Eureka ML Insights: github.com/microsoft/eure….

If you're running agents in production, consider taking this short survey from my research group! We're collaborating with IBM, Stanford, UIUC, Intesa Sanpaolo and others to better understand the challenges in building agents. It only takes 5 minutes: agents-survey.github.io/AI-Agent-Surve…