HomeResearch LibraryLeast-to-Most Prompting Enables Complex Reasoning in La…
Chapter 2 · 2022

Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

Denny Zhou, Nathanael Schärli, Le Hou

Abstract

Least-to-most prompting decomposes complex problems into simpler subproblems and solves them sequentially, enabling generalization to harder problems than seen in demonstrations.

Eigenvector Insight — Zone III / PASF-PADE AnalysisNot part of the original paper
Eigenvector Research — Marco van Hurne
How this paper contributes to solving the Zone III problem (PASF-PADE)

Least-to-most prompting is the decomposition strategy for Zone III workflows. Complex enterprise processes are inherently hierarchical: strategic goals decompose into tactical steps, which decompose into operational actions. An agent that can recursively decompose problems — and solve them from the bottom up — can handle enterprise workflows of arbitrary complexity.

Why AI is not sufficient for Zone III without this

Zone III refers to high-complexity, high-risk, long-running agentic workflows — the class of enterprise AI deployments where a single failure can cascade across hundreds of steps. Standard AI models, trained to predict the next token, are not inherently designed for durable, governed, multi-step execution. This paper addresses one or more of the structural gaps that make Zone III deployments unsafe without explicit architectural intervention.

Topics

task decompositionproblem solvinggeneralizationprompting