Agent based on the Monte Carlo Tree with SOTA results in math

[leo-gan]

Checked

• I searched existing ideas and did not find a similar one
• I added a very descriptive title
• I've clearly described the feature request and motivation for it

Feature request

Accessing GPT-4 level Mathematical Olympiad Solutions via Monte Carlo Tree Self-refine with LLaMa-3 8B: A Technical Report - It is quite an interesting Agent based on the Monte Carlo Tree.
I am not sure if it is possible to implement it with LangGraph and LangChain.

Motivation

To implement SOTA agent in LangGraph

Proposal (If applicable)

No response