Frontier Best path Pruned
⚠ Couldn't load the 3D engineThree.js failed to load from the CDN. Check your connection and reload.

Tree-of-Thought Beam Search Pruning Lab (3D)

Modern reasoning models don't decode a single chain of tokens and stop β€” 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 simulator grows that tree in real 3D: 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 β€” the same tree, with backtracking removed.