Skip to content
TL;DR
Search over a tree of partial reasoning paths with lookahead and backtracking, using the LLM to both generate branches and evaluate them. Big wins on puzzles that trip up linear CoT.
BACKLOG · WORK IN PROGRESS

This paper is being written.

The metadata and shape of this page are stable, but the body content isn't ready yet. We'll publish it once it meets the bar of teaching something new with worked examples and real tools.