News for hackers. Stuff that matters.
Re:R-Zero: Self-Evolving Reasoning LLM from Zero Data by vineethy on Sunday August 10, 2025 @12:16AM (#44852708)
Interesting twist on automated curriculum learning. This paper is using an LLM for the environment and the policy. Other papers use LLMs for policy/value fn. Would be cool to see other reward strategies tying all these threads together