ReflexiCoder: Teaching Large Language Models to Self-Reflect on Generated Code and Self-Correct It via Reinforcement Learning
Paper • 2603.05863 • Published • 6
Sungju Kim
goddoe
AI & ML interests
Code LLM, Code Agent, Post-training
Recent Activity
liked a dataset 28 days ago
nvidia/Nemotron-Cascade-2-RL-data liked a dataset 29 days ago
nvidia/Nemotron-Terminal-Synthetic-Tasks liked a dataset about 1 month ago
allenai/MolmoPoint-GUISynOrganizations
authored a
paper about 1 month ago