arXiv:2605. 29009v1 Announce Type: new Abstract: Post-training large language models with reinforcement learning is bottlenecked by the reward signal.
Paper
Label-Free Reinforcement Learning via Cross-Model Entropy
Unreadunread
Paper
Unreadunread
arXiv:2605. 29009v1 Announce Type: new Abstract: Post-training large language models with reinforcement learning is bottlenecked by the reward signal.