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 23 days ago
internlm/SWE-Fixer-Train-110K new activity 24 days ago
nvidia/Nemotron-SFT-SWE-v3:No tool list liked a dataset about 2 months ago
nvidia/Nemotron-SFT-SWE-v2Organizations
authored a
paper 4 months ago