AI Frontiers - Microsoft Research: News Updates

background pattern

Microsoft Research
AI Frontiers

Video

MagenticLite: A full-stack agentic experience powered by Small Models

May 14, 2026 | Harkirat Behl, Weili Shi, Hussein Mozannar

Microsoft Research Forum S2E4 | Harkirat Behl, Weili Shi, Hussein Mozannar | MagenticLite

Microsoft Research Blog

SocialReasoning-Bench: Measuring whether AI agents act in users’ best interests

May 11, 2026 | Tyler Payne, Will Epperson, Safoora Yousefi, Zachary Huang, Gagan Bansal, Wenyue Hua, Maya Murad, Asli Celikyilmaz (opens in new tab), Saleema Amershi

Social Reasoning Bench | four icons on a blue to green gradient | person icon, chat bubble icon, chart icon, checklist icon

Article

Whimsical Strategies Break AI Agents: Generating Out-of-Distribution Adversarial Strategies at Scale

May 6, 2026

A scale showing coffee is worth more than gold

Article

Webwright: A Terminal Is All You Need For Web Agents

May 4, 2026

Webwright architecture

Microsoft Research Blog

Red-teaming a network of agents: Understanding what breaks when AI agents interact at scale

April 30, 2026 | Gagan Bansal, Shujaat Mirza, Keegan Hines, Will Epperson, Zachary Huang, Whitney Maxwell, Pete Bryan, Tyler Payne, Adam Fourney, Amanda Swearngin, Wenyue Hua, Tori Westerhoff (opens in new tab), Amanda Minnich, Maya Murad, Ece Kamar, Ram Shankar Siva Kumar, Saleema Amershi

three icons on a blue to green gradient background | connected node icon, document with an 'x' icon, shield with a checkmark icon

Article

The Art of Building Verifiers for Computer Use Agents

April 21, 2026

graphical user interface, application

Podcast

Ideas: Steering AI toward the work future we want

April 9, 2026

New Future of Work 2026 | Jaime Teevan, Jenna Butler, Jake Hofman, Rebecca Janssen

Article

Memento: Teaching LLMs to Manage Their Own Context

April 8, 2026

diagram

Publication

AI Scientist via Synthetic Task Scaling

Ziyang Cai, Harkirat Behl

March 2026

Publication

Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces

Karan Gupta, Pranav Vajreshwari, Yash Pandya, Raghav Magazine, Akshay Nambi, Ahmed Awadallah

ICLR Agents in the Wild (Spotlight) | March 2026

Your Privacy Choices