Year: 2024
Type: preprint
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.
Source: arXiv (Cornell University)
Authors: Zhang, Yadong, Mao, Shaoguang, Ge, Tao, Wang, Xun, de Wynter, Adrian, Xia, Yan, Wu, Wenshan, Song, Ting, Lan, Man, Wei, Furu
Institutions: East China Normal University, Microsoft (United States)
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4393905140