Everything you care about in one place
Follow feeds: blogs, news, RSS and more. An effortless way to read and digest content of your choice.
Get Feedermicrosoft.com
Microsoft Research
Get the latest updates from Microsoft Research directly as they happen.
Follow now 745 followers
Latest posts
Last updated 6 days ago
SkillOpt: Agent skills as trainable parameters
6 days ago
At a glance AI agents often fail because their instructions, or skills,...
Memora: A Harmonic Memory Representation Balancing Abstraction and Specificity
7 days ago
At a glance Today’s AI agents don’t remember past interactions. They must...
Understanding the brain with AI-driven explanations and experiments
11 days ago
At a glance LLM-based models can predict the human brain’s responses to...
Talos: Scaling rare disease diagnosis with automated, iterative genomic reanalysis
12 days ago
At a glance Talos is an open-source tool for automated, iterative reanalysis...
Ire identifies another LOTUSLITE specimen
24 days ago
At a glance Project Ire identifies a LOTUSLITE variant that shares TTPs...
SocialReasoning-Bench: Measuring whether AI agents act in users??? best interests
about 2 months ago
At a glance AI agents are moving into social contexts. When agents...
Data Formulator 0.7: AI-powered data analytics for enterprise data
about 1 month ago
At a glance Data Formulator 0.7 is an open-source AI-powered system for...
Extending Human Intelligence Through AI
about 1 month ago
At a glance Modern AI systems are powerful not because they replicate...
Extending Human Intelligence Through AI
about 1 month ago
At a glance Modern AI systems are powerful not because they replicate...
MagenticLite, MagenticBrain, Fara1.5: An agentic experience optimized for small models
about 2 months ago
At a glance MagenticLite is an agentic application that works across both...
Vega: Zero-knowledge proofs for digital identity in the age of AI
about 2 months ago
At a glance Vega lets users prove facts from government-issued credentials —...
Further Notes on Our Recent Research on AI Delegation and Long-Horizon Reliability
about 2 months ago
Our recent paper, “LLMs Corrupt Your Documents When You Delegate”, has generated...