Code Hunt - Microsoft Research

At a glance
Today’s multimodal AI systems can give answers that sound right but may not be grounded in what they actually observe over time, leading to unpredictable errors and safety risks in real-world settings.
Argos is a verification framework for multimodal reinforcement learning that trains models by rewarding not just correct answers, but correct answers grounded in visual and temporal evidence, using automated verification rather than human labeling. It...

At a glance
Many real-world business problems can benefit from optimization, but translating decisions, constraints, and goals from natural language into optimization algorithms is slow.
OptiMind is a small language model designed to convert business problems described in natural language into the mathematical formulations needed by optimization software....

AI agents are reshaping software development, from writing code to carrying out complex instructions. Yet LLM-based agents are prone to errors and often perform poorly on complicated, multi-step tasks. Reinforcement learning (RL) is an approach where...

Anyone who uses AI systems knows the frustration: a prompt is given, the response misses the mark, and the cycle repeats. This trial-and-error loop can feel unpredictable and discouraging. To address this, we are excited to introduce Promptions (prompt...