rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking(arxiv.org)

39 pointsby roboboffinhace 2 años7 comments

rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking

https://arxiv.org/abs/2501.04519

5 comments

s-mackehace 2 años

> Notably, no self-reflection training data or prompt was included, suggesting that advanced System 2 reasoning can foster intrinsic self-reflection.

They suggest, that self-reflection is an emergent phenomena of reasoning. Impressive. Can't wait to see the code.

throwaway81523hace 2 años

Abstract is impressive. I'm surprised this post hasn't gotten more attention.

roboboffinhace 2 años

Yeah, that's what I thought.

helltonehace 2 años

Off topic but how is MCTS usually implemented efficiently? It has a branching structure that doesn't seem parallelizable (GPU).

fabmilohace 2 años

I was just about to submit this link and redirected me to this page. I am shocked that it received only four comments. If you are working in the LLMs/Agent space ( you are, right?) and you don't understand the significance of this paper, you are set for failure.

dantodorhace 2 años

The repo gives 404?

funcDropShadowhace 2 años

The abstract says the code will be available.