ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mao, Shaoguang, Cai, Yuzhe, Xia, Yan, Wu, Wenshan, Wang, Xun, Wang, Fengyi, Ge, Tao, Wei, Furu
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910297682345984
author Mao, Shaoguang
Cai, Yuzhe
Xia, Yan
Wu, Wenshan
Wang, Xun
Wang, Fengyi
Ge, Tao
Wei, Furu
author_facet Mao, Shaoguang
Cai, Yuzhe
Xia, Yan
Wu, Wenshan
Wang, Xun
Wang, Fengyi
Ge, Tao
Wei, Furu
contents This paper introduces Alympics (Olympics for Agents), a systematic simulation framework utilizing Large Language Model (LLM) agents for game theory research. Alympics creates a versatile platform for studying complex game theory problems, bridging the gap between theoretical game theory and empirical investigations by providing a controlled environment for simulating human-like strategic interactions with LLM agents. In our pilot case study, the "Water Allocation Challenge," we explore Alympics through a challenging strategic game focused on the multi-round auction on scarce survival resources. This study demonstrates the framework's ability to qualitatively and quantitatively analyze game determinants, strategies, and outcomes. Additionally, we conduct a comprehensive human assessment and an in-depth evaluation of LLM agents in strategic decision-making scenarios. Our findings not only expand the understanding of LLM agents' proficiency in emulating human strategic behavior but also highlight their potential in advancing game theory knowledge, thereby enriching our understanding of both game theory and empowering further research into strategic decision-making domains with LLM agents. Codes, prompts, and all related resources are available at https://github.com/microsoft/Alympics.
format Preprint
id arxiv_https___arxiv_org_abs_2311_03220
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents
Mao, Shaoguang
Cai, Yuzhe
Xia, Yan
Wu, Wenshan
Wang, Xun
Wang, Fengyi
Ge, Tao
Wei, Furu
Computation and Language
Artificial Intelligence
Computer Science and Game Theory
This paper introduces Alympics (Olympics for Agents), a systematic simulation framework utilizing Large Language Model (LLM) agents for game theory research. Alympics creates a versatile platform for studying complex game theory problems, bridging the gap between theoretical game theory and empirical investigations by providing a controlled environment for simulating human-like strategic interactions with LLM agents. In our pilot case study, the "Water Allocation Challenge," we explore Alympics through a challenging strategic game focused on the multi-round auction on scarce survival resources. This study demonstrates the framework's ability to qualitatively and quantitatively analyze game determinants, strategies, and outcomes. Additionally, we conduct a comprehensive human assessment and an in-depth evaluation of LLM agents in strategic decision-making scenarios. Our findings not only expand the understanding of LLM agents' proficiency in emulating human strategic behavior but also highlight their potential in advancing game theory knowledge, thereby enriching our understanding of both game theory and empowering further research into strategic decision-making domains with LLM agents. Codes, prompts, and all related resources are available at https://github.com/microsoft/Alympics.
title ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents
topic Computation and Language
Artificial Intelligence
Computer Science and Game Theory
url https://arxiv.org/abs/2311.03220