> 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.

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

Yeah, that's what I thought.

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

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.

The repo gives 404?

The abstract says the code will be available.