At a glance MagenticLite is an agentic application that works across both the browser and local file system in a single workflow. Built as the next generation of Magentic-UI, it combines a redesigned app with a harness optimized for small models. MagenticBrain and Fara1.5 are small models designed for orchestration and computer-use tasks, respectively. Fara1.5 is the next iteration of Fara and  

At a glance Vega lets users prove facts from government-issued credentials — age, personhood, professional status — without revealing the credential itself. The credential never leaves the device.  Zero-knowledge proofs are generated in under 100 ms on  

Our recent paper, “LLMs Corrupt Your Documents When You Delegate”, has generated discussion about the reliability of AI systems in delegated workflows. We appreciate the interest in this work and want to clarify several important points about what the paper does—and does not—claim. The research aims to develop robust evaluation methods for long-horizon delegated and collaborative tasks. More broadly, this work reflects an ongoing effort to better understand the gap between strong benchmark performance and certain real-world tasks. Using a […]

Microsoft releases a lightweight foundation model that can predict AC optimal power flow in milliseconds, boosting efficiency and unlocking cost savings in grid analysis. At a glance Microsoft introduces GridSFM, a small foundation model that approximates AC optimal power flow in milliseconds, unlocking decisions  

At a glance Experimental validation: Using high-throughput screening with MatterSim-v1, we previously identified tetragonal tantalum phosphorus (TaP) as a potential high-performance thermal conductor. Now we have experimentally synthesized it and measured its thermal conductivity (152 W/m/K) to be close to the thermal  

At a glance AI agents are moving into social contexts. When agents manage calendars, negotiate purchases, or interact with other agents on a user’s behalf, they need more than task competence—they need social reasoning. SocialReasoning-Bench evaluates that ability. The benchmark tests whether an agent can negotiate for  

At a glance We construct geographically grounded, electrically coherent power grid models entirely from publicly available data and release a dataset spanning 48 U.S. states and multi-state interconnections. The models  

Large-scale networked systems underpin cloud computing, AI, and distributed applications and services. The USENIX Symposium on Networked Systems Design and Implementation 2026 (opens in new tab) (NSDI ’26) is a leading forum where researchers and practitioners share new research, insights, and advances in the design and operation of these systems. Microsoft is proud to support NSDI ’26 as a returning sponsor, reflecting our ongoing commitment to advancing systems  

At a glance Some risks appear only when agents interact, not when tested alone. Actions that seem harmless can cascade causing a chain reaction across an agent network. In our tests, a single malicious message passed from agent to agent, extracting private data at each step  

At a glance Problem: Adapting large language models to specialized, high-stakes domains is slow, expensive, and hard to reproduce.  What we built: AutoAdapt automates planning, strategy selection (e.g., RAG vs. fine-tuning), and tuning under real deployment constraints.  How it works:  A structured configuration graph maps