作者位次 #3/4ACL 2026Poster· Natural Language Processing
R e C ode: Reinforcing Code Generation with Reasoning-Process Rewards
Lishui Fan · Yu Zhang · Mouxiang Chen · Zhongxin Liu
摘要
In practice, rigorous reasoning is often a key driver of correct code, while Reinforcement Learning (RL) for code generation often neglects optimizing reasoning quality. Bringing process-level supervision into RL is appealing, but it faces two challenges. First, training reliable reward models to...