online-reflection

Procedural Memory Distillation (PMD) converts cross-episode signals from reinforcement learning rollouts into reusable procedural memory that is distilled into the policy weights during training, enabling self-improving language models without memory at inference. Experiments show PMD outperforms SDPO by 3.8-5.5% on SCIKNOWEVAL and 7.9-13.6% on LIVECODEBENCH.