Tree-of-Thought Reasoning Search (2D)

Modern reasoning models don't decode a single chain of tokens and stop — they explore a branching tree of candidate reasoning steps, score each one, and keep only the most promising branches alive, exactly like a best-first search over a state space. This 2D diagram view grows that tree step by step: pick a problem, expand nodes one step or run the search continuously, and watch a value estimate decide which thoughts survive as the beam narrows toward a solution. Switching to Chain-of-Thought mode collapses the beam to width 1, showing the single committed path a standard (non-reasoning) LLM would generate instead — the same tree, with backtracking removed. A live sparkline underneath tracks the winning branch's value and the cumulative pruned count across the run, and the tree itself is pannable/zoomable so wide, deep searches stay readable.