# Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It

> Source: <https://aiflash.com/news/128206/>
> Published: 2026-09-29 02:00:10+00:00

We study training-inference mismatch in reinforcement learning with verifiable rewards (RLVR) for large language models, where rollouts are sampled by an inference engine while gradients are computed by a training engine, and the two engines assign different probabilities to the same tokens. To acco