Is One Layer Enough? A Single Transformer Layer Can Match Full-Parameter RL Training

arXiv·high signal

New arXiv work (2607.01232, cs.LG/cs.CL) shows that training only a single transformer layer during RL post-training can match full-parameter RL fine-tuning of an LLM, challenging assumptions about how much of the network RL actually needs to touch. If it holds, it points to dramatically cheaper RLHF/RLVR post-training. This was also surfacing on Hacker News, a signal of practitioner interest.