Iteration / Round
One complete cycle of: MCTS search → solution verification → data collection → model training.
One complete cycle of: MCTS search → solution verification → data collection → model training. rStar-Math runs 4 rounds.
One complete cycle of: MCTS search → solution verification → data collection → model training.
One complete cycle of: MCTS search → solution verification → data collection → model training. rStar-Math runs 4 rounds.