The Froggy Team Frogs love to eat bugs

Microsoft Research Montréal

We aim to advance research on Large Language Models (LLMs), with a particular focus on agentic coding LLMs. We build interactive SWE environments and synthetic tasks that facilitate designing, training, and evaluating agentic coding AI systems. We distil teacher LLMs' reasoning and coding capabilities into smaller, more efficient (plug-and-play) student models that can be deployed in real-world settings. We also explore new learning paradigms that leverage interaction and feedback to improve LLM-based coding agents.

News October 2025

The team is looking for PhD Research Interns for Summer 2026 to work on exciting projects in Coding AI.

Blog Post October 2025

BugPilot: Complex Bug Generation For Efficient Learning of SWE Skills

We introduce FrogBoss and FrogMini, a state of the art 32B and 14B model for debugging.

Project March 2025

debug-gym: A Text-Based Environment for Interactive Debugging

A text-based environment for interactive debugging that enables Large Language Models to interactively explore codebases

Contact Us

Interested in collaborating or learning more about our research?
Reach out to us at debug-gym@microsoft.com