Branch intermediate steps and search for the best path—not just the best final guess.
While Self-Consistency varies the final answer, Tree of Thoughts varies the steps of reasoning at each point and then picks the best path overall.
At every reasoning step, the model explores multiple possible directions. These branches form a tree, and a separate process evaluates which path seems the most promising at a particular timestamp.
Think of it like a search algorithm over reasoning paths, where we try to find the most logical and coherent trail to the solution.
It’s more compute-intensive, but in most cases, it significantly outperforms basic CoT.
CoT, Self-Consistency, and ToT all improve how the model reasons through a problem.
But they still rely on free-form thinking, which breaks down in long, rule-heavy tasks.
That’s where ARQ comes in.
