Hi, I’m Chenxi Ma

Currently, I am pursuing my studies at Wuhan University of Technology.

My research interests are centered on the optimization of large model inference and decision-making performance through reinforcement learning. I am highly enthusiastic about developing advanced algorithms and frameworks that enhance the reasoning capabilities and decision-making efficiency of foundation models. By leveraging the principles of reinforcement learning, I aim to explore novel approaches that can significantly improve the adaptability and accuracy of large models in complex reasoning and agentic tasks, thereby contributing to the advancement of artificial intelligence in practical applications.