LLM as a Mastermind: A Survey of Strategic Reasoning with Large Language Models

TL;DR

This survey reviews the current state and potential of Large Language Models in strategic reasoning, emphasizing their role in multi-agent interactions, decision-making, and future research directions.

Contribution

It systematically consolidates scattered literature on LLMs in strategic reasoning, highlighting methodologies, applications, and evaluation metrics in this emerging field.

Findings

LLMs are increasingly capable of strategic reasoning tasks.

Interdisciplinary approaches enhance LLM decision-making.

Future research should focus on improving multi-agent interaction understanding.

Abstract

This paper presents a comprehensive survey of the current status and opportunities for Large Language Models (LLMs) in strategic reasoning, a sophisticated form of reasoning that necessitates understanding and predicting adversary actions in multi-agent settings while adjusting strategies accordingly. Strategic reasoning is distinguished by its focus on the dynamic and uncertain nature of interactions among multi-agents, where comprehending the environment and anticipating the behavior of others is crucial. We explore the scopes, applications, methodologies, and evaluation metrics related to strategic reasoning with LLMs, highlighting the burgeoning development in this area and the interdisciplinary approaches enhancing their decision-making performance. It aims to systematize and clarify the scattered literature on this subject, providing a systematic review that underscores the importance of strategic reasoning as a critical cognitive capability and offers insights into future research directions and potential improvements.