[Summary] From Reasoning to Super-Intelligence: A Search-Theoretic Perspective
TL;DR Popular methods for chain‑of‑thought (CoT) reasoning (e.g supervised fine‑tuning, Tree‑of‑Thoughts) have three challenges: (i) distribution drift where small mistakes spiral with no recovery mechanism, (ii) missing search structure such that there’s no built-in exploration or backtracking, (iii) and explosive computational cost. The proposed Diligent Learner models reasoning as depth-first search guided by a validator. It is trained by building reasoning paths step-by-step, checks each one for correctness, and backtracks when needed....