Microsoft Research Blog
Reducing Privacy leaks in AI: Two approaches to contextual integrity
Follow Microsoft Research
Subscribe to our newsletter
Sign up to get the latestRecent Posts

Reducing Privacy leaks in AI: Two approaches to contextual integrity
November 25, 2025New research explores two ways to give AI agents stronger privacy safeguards grounded in contextual integrity. One adds lightweight, inference-time checks; the other builds contextual awareness directly into models through reasoning and RL.

Fara-7B: An Efficient Agentic Model for Computer Use
November 24, 2025Fara-7B is our first agentic small language model for computer use. This experimental model includes robust safety measures to aid responsible deployment. Despite its size, Fara-7B holds its own against larger, more resource-intensive agentic systems.

MMCTAgent: Enabling multimodal reasoning over large video and image collections
MMCTAgent enables dynamic multimodal reasoning with iterative planning and reflection. Built on Microsoft’s AutoGen framework, it integrates language, vision, and temporal understanding for complex tasks like long video and image analysis.

BlueCodeAgent: A blue teaming agent enabled by automated red teaming for CodeGen AI
November 11, 2025BlueCodeAgent is an end-to-end blue-teaming framework built to boost code security using automated red-teaming processes, data, and safety rules to guide LLMs’ defensive decisions. Dynamic testing reduces false positives in vulnerability detection.

When industry knowledge meets PIKE-RAG: The innovation behind Signify’s customer service boost
November 6, 2025 |Industry Innovation CenterA collaboration between Signify and Microsoft Research shows how PIKE-RAG improves enterprise knowledge systems, delivering a 12% increase in accuracy and faster, more reliable answers.

Magentic Marketplace: an open-source simulation environment for studying agentic markets
November 5, 2025AI agents are poised to transform digital marketplaces. To explore what can happen when AI agents interact and transact at scale, we built Magentic Marketplace, an open-source simulation environment for studying agentic market designs.

RedCodeAgent: Automatic red-teaming agent against diverse code agents
November 4, 2025Code agents help streamline software development workflows, but may also introduce critical security risks. Learn how RedCodeAgent automates and improves “red-teaming” attack simulations to help uncover real-world threats that other methods overlook.

Tell me when: Building agents that can wait, monitor, and act
October 21, 2025SentinelStep enables AI agents to handle monitoring tasks that run for hours or days, like watching for emails or tracking prices. It works by managing when agents should check and their context, avoiding wasted resources and missed updates.

When AI Meets Biology: Promise, Risk, and Responsibility
October 6, 2025 |Eric HorvitzMicrosoft researchers reveal a confidential research effort that explored how open-source AI tools could be used to bypass biosecurity checks—and helped create fixes now influencing global standards.

Using AI to assist in rare disease diagnosis
September 22, 2025 |Mandi Hall andAshley ConardNew research from Microsoft, Drexel, and the Broad explores how generative AI could support genetic professionals in rare disease diagnosis.

Tool-space interference in the MCP era: Designing for agent compatibility at scale
As agentic AI ushers in a new era marked by tool expansion, systems are converging, and complexity is rising. Microsoft Research explores the Model Context Protocol (MCP) as a new standard for agent collaboration across fragmented tool ecosystems.

RenderFormer: How neural networks are reshaping 3D rendering
September 10, 2025 |Yue DongRenderFormer, from Microsoft Research, is the first model to show that a neural network can learn a complete graphics rendering pipeline. It’s designed to support full-featured 3D rendering using only machine learning—no traditional graphics computation required.
Explore More

Events & conferences
Meet our community of researchers, learn about exciting research topics, and grow your network

Podcasts
Ongoing conversations at the cutting edge of research

Microsoft Research Forum
Join us for a continuous exchange of ideas about research in the era of general AI

