Compositional Reasoning in Language Models under Reinforcement Learning Post-Training
Compositional reasoning is critical for real-world problem solving: since training data is necessarily limited, models must generalize by composing learned skills in new ways. While post-training methods such as reinforcement learning (RL) have substantially improved the reasoning abilities of language models (LMs), th...
Yu He, Ying-Xi Li, Yi-Fei Wang et al.
· 0 citations