Red Hat Research Quarterly

Mingzhi Zhu

About the author

Mingzhi Zhu is a second-year PhD student in Computer Science at Rensselaer Polytechnic Institute, advised by Professor Stacy Patterson. His research focuses on parameter-space model merging techniques for code agents.

Articles by this author

CRANE: teaching code models to think without breaking their tools

Can we enhance AI reasoning without sacrificing the reliability of coding tools? The CRANE method proves it’s possible. A stronger reasoning model is not automatically a better coding agent. For many AI systems, the standard approach is to take a model that can reason longer, plan more carefully, and recover from mistakes, then place it […]