Monte Carlo Tree Search (MCTS)

Appears in 1 paper

A search algorithm that explores a decision tree by: (1) selecting promising nodes using UCB, (2) expanding the tree with new candidate moves, (3) running rollouts to simulate outcomes, (4) backing up the results to update node statistics.

As used in Paper 24 — rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking →

A search algorithm that explores a decision tree by: (1) selecting promising nodes using UCB, (2) expanding the tree with new candidate moves, (3) running rollouts to simulate outcomes, (4) backing up the results to update node statistics. Used to find high-quality solutions in domains with large solution spaces.