| ▲ | haickernews 5 hours ago | |
If you can be persuaded, looking into how modern LLMs are trained with reinforcement learning may change your views. | ||
| ▲ | oedemis 5 hours ago | parent [-] | |
https://arxiv.org/abs/2510.07364 event rl isn't necessary for LLMs to develop reasoning capabilities in some cases | ||