Artificial Intelligence
Building intelligent machines that complement human reasoning and extend what people can do.
Microsoft Research Blog
Agent Lightning: Adding reinforcement learning to AI agents without code rewrites
By decoupling how agents work from how they’re trained, Agent Lightning turns each step an agent takes into data for reinforcement learning. This makes it easy for developers to improve agent performance with almost zero…
Microsoft Research Blog
Promptions helps make AI prompting more precise with dynamic UI controls
Promptions helps developers add dynamic, context-aware controls to chat interfaces so users can guide generative AI responses. It lets users shape outputs quickly without writing long instructions.
Video
Data Formulator: Vibe with your data, in control
Data Formulator is an AI-powered tool for analysts to iteratively explore and visualize data. Started with data in any format (screenshot, text, csv, or database), users can work with AI agents with a novel blended…
Video
Accelerating MRI image reconstruction with Tyger
The Tyger framework enables faster, more accessible medical imaging by streaming raw data to the cloud for accelerated reconstruction—reducing patient wait times and discomfort—while empowering researchers to rapidly test and deploy new algorithms.
Video
Tool-space Interference: An emerging problem for LLM agents
Tool-space interference occurs when adding an otherwise reasonable agent or tool to a team or agent reduces end-to-end task performance. We study the phenomenon in an analysis of 1470 MCP servers and make practical suggestions…
Video
A brain-inspired agentic architecture to improve planning with LLMs
Inspired by human collective cognition and neuroscience, we conducted two studies showing that a) multi-LLM architectures with mixed communication connectivity lead to better collaborative innovation (Artificial Life 2024), and b) brain-inspired multi-LLM architectures improve multi-step…
