Systems & networking
Researching next-generation systems and networks that power reliable, scalable, and efficient computing.
Publication
Optimizing Agentic Workflows using Meta-tools
Vidéo
Microsoft Research India 2025 Highlights
Here are some highlights of the research and impact at Microsoft Research India in 2025, along with some glimpses of the lab milieu.
Publication
Terabyte-Scale Analytics in the Blink of an Eye
Outil
Model-based Testing using LLMs
This repsitory contains the code for our paper Eywa: Automating Model-based Testing using LLMs. Our framework uses LLMs to automatically construct modular protocol models from natural-language specifications and applies symbolic execution and differential testing to…
Outil
MetaEase
MetaEase is a framework for automatically finding worst-case inputs of heuristics by maximizing the gap between heuristic and optimal solutions. It combines symbolic execution (KLEE) with gradient-based optimization to efficiently explore the input space. This…
Blog de recherche Microsoft
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…
