Microsoft Research

Everything the estate keeps about it, including what it publishes itself.

Bing Maps at its own address

In its own words

Can AI help build a healthier future?What can AI enable in medicine, and how do we get there? Microsoft Research lead Doug Burger, Microsoft Principal Research Manager Ava Amini, Microsoft Chief Scientific Officer Eric Horvitz, and physician-scientist Eric Topol of Scripps Research explore these questions and more. The post Can AI help build a healthier future? appeared first on Microsoft…Doug Burger, Ava Amini, Eric Horvitz, Dr. Eric Topol microsoft.com TokenEconomizer: Learning from Experience to Make AI Coding Agents More EfficientAI coding agents can waste time and tokens relearning the same lessons. TokenEconomizer is an open-source plugin that builds on past sessions to cut costs while maintaining task success. It’s a path toward coding agents that learn not only how to solve tasks, but also how to spend computation more effectively. The post TokenEconomizer: Learning from…microsoft.com Microsoft Research Focus – Edition #98What's new in research at Microsoft? Host Anson Ho explores the latest, including AI-powered universal translation, a breakthrough in a 31-year-old mathematics challenge, and advances making AI coding agents faster and more efficient.  The post Microsoft Research Focus – Edition #98 appeared first on Microsoft Research.Anson Ho microsoft.com Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI AgentsMicrosoft researchers have discovered “Lazarus,” a backdoor technique that can reprogram dormant neurons in an AI model, causing an otherwise normal AI agent to execute malicious commands when a hidden trigger appears. The threat is especially serious for AI agents with tool or terminal access. A triggered model could quietly download and run attacker…Dimitris Papailiopoulos microsoft.com Do AI coding agents care about SemVer?We gave AI coding agents the same breaking upgrade twice. Labeled 2.0.0, Claude Sonnet 5.5 checked it in all 10 runs. Labeled 1.4.3, it checked in two and often left the app broken. Nearly 1,000 runs show which agents still read your version numbers, and what a patch label talks them out of.Waldek Mastykarz microsoft.com Formally verifying agent-written full-stack web apps with PDD KitAI agents can generate code at a scale that’s hard for humans to review line-by-line. PDD Kit helps ensure the code is doing what the developer intended by creating formal specifications and testing against them. It converts developer intent into a Verus specification, proves AI-generated code meets it for every input, and uses tests where proofs aren't…Alex Lavaee, Matthai Philipose microsoft.com Your best AX fixes are hiding in agent trajectoriesAll five agent runs produced a working script, and nothing in the eval score looked wrong. The trajectories told a different story. Every run read a DLL as raw bytes to find plugin names, and three scripts would quietly reroute a CI runner's network traffic. Here are the patterns to look for in your own agents' trajectories, and what to change in your…Waldek Mastykarz microsoft.com Learn the rules: The hacker mindsetResearch Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.Weishung Liu, Mike Walker microsoft.com From synthetic enterprise data evaluations to real Microsoft Copilot AI confidenceEvaluating Microsoft Copilot at enterprise scale requires test data that captures the full complexity of real organizations, yet real enterprise data contains sensitive information that cannot be used for evaluation under any circumstances. The post From synthetic enterprise data evaluations to real Microsoft Copilot AI confidence appeared first on Microsoft…microsoft.com Does ‘eval’ in the workspace path change what your agent does?Your eval might be telling the agent it’s a test before the agent reads a single instruction. Eval tools need a fresh folder for every run, and the easiest way to get one is a temp directory with a random name like /tmp/eval-7f3a2c. The agent sees that path on every turn, in the system prompt […]Waldek Mastykarz microsoft.com Microsoft Research Focus – Edition #97Host Sowbhagya Suresh shares some of the latest news and cutting-edge research from across Microsoft—from understanding the challenges facing coding agents to uncovering how people use AI at work and improving extended-range weather forecasting. The post Microsoft Research Focus – Edition #97 appeared first on Microsoft Research.Sowbhagya Suresh microsoft.com Publish Visual Studio Marketplace extensions securely with Trusted PublishingPublish Visual Studio Code and Visual Studio extensions from GitHub Actions or Azure Pipelines without storing a long-lived personal access token.Lynn Dai microsoft.com

Named in it

Where they publish