System 2 Reasoning Capabilities Are Nigh
Keywords: reasoning, system 2, LLM, scaling, cognition, psychology, cot, chain of thought
TL;DR: We give an overview of reasoning literature and claim there remains very little additional progress needed to achieve the goal of human-like reasoning in machines.
Abstract: In recent years, machine learning models have made strides towards human-like reasoning capabilities from several directions. In this work, we review the current state of the literature and describe the remaining steps to achieve a neural model which can perform System 2 reasoning analogous to a human. We argue that if current models are insufficient to be classed as performing reasoning, there remains very little additional progress needed to attain that goal.
Submission Number: 80
Loading