Intermediate · Cognitive

System 2 Reasoning

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. A concept from cognitive science applied to AI, referring to slow, deliberate, logical, and effortful thought processes.

Technical Definition

A concept from cognitive science applied to AI, referring to slow, deliberate, logical, and effortful thought processes.

How it works

Inspired by Daniel Kahneman's dual-process theory, System 2 reasoning in AI implies models that can engage in sequential, explicit reasoning, break down problems, and perform multi-step planning. This contrasts with 'System 1' which is fast, intuitive, and associative. Techniques like Chain of Thought and Tree of Thought aim to imbue LLMs with more System 2 capabilities, enabling complex problem-solving.

Related Concepts

• Chain-of-Thought (CoT) Prompting — Asking models to show step-by-step reasoning before giving a final answer, improving accuracy on complex tasks.
• Reasoning engine — A component of a software system that infers conclusions from existing knowledge using logical methods.
• Tree of Thought (ToT) — A prompting technique that enables LLMs to explore multiple reasoning paths by maintaining and evaluating intermediate 'thought' steps in a tree structure.