AI RESEARCH
Improving Small Language Models for Code Generation with Reinforcement Learning from Verification Feedback
arXiv CS.CL
•
ArXi:2605.30478v1 Announce Type: cross Reinforcement learning with verifiable rewards (RLVR) trains language models using programmatically checkable signals such as unit-test outcomes, enabling direct optimization for functional correctness in code generation. We conduct an empirical study of RLVR for Python code generation on the MBPP benchmark using two small models (Qwen3-0.6B and Llama3.2-1B) with LoRA fine-tuning.