arXiv Machine Learning By Jing Liang, Hongyao Tang, Yi Ma, Yancheng He, Weixun Wang, Xiaoyang Li, Ju Huang, Wenbo Su, Jinyi Liu, Yan Zheng, Jianye Hao, Bo Zheng

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Read the original on arXiv Machine Learning →

arXiv:2606. 29526v1 Announce Type: new Abstract: Reinforcement learning (RL) has gained growing attention in large language model (LLM) post-training, yet RL training remains fragile and can suffer from instability or collapse.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.