Preprint
Aug 2026
Toward Plasticity-Preserving KL Regularization for Capability Retention in LLM Reinforcement Learning
Experiments in controlled multi-solution environments and continual post-training settings across multiple model scales demonstrate that CoKL achieves a more favorable balance between target-task improvement and prior-capability retention than existing regularization methods.
Li Wang, Xiao-Dong Lu, Xiao-Han Wang et al.
· 0 citations