CodeScaler: Scaling Code LLM Training and Test-Time Inference via Execution-Free Reward Models
arXiv:2602.17684v1 Announce Type: cross Abstract: Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from …
Xiao Zhu, Xinyu Zhou, Boyu Zhu, Hanxu Hu, Mingzhe Du, Haotian Zhang, Huiming Wang, Zhijiang Guo
조회수 24회