Saved in:
Bibliographic Details
Main Authors: Hogan, Daniel P., Brennen, Andrea
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2404.11446
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911844159979520
author Hogan, Daniel P.
Brennen, Andrea
author_facet Hogan, Daniel P.
Brennen, Andrea
contents Wargames are a powerful tool for understanding and rehearsing real-world decision making. Automated play of wargames using artificial intelligence (AI) enables possibilities beyond those of human-conducted games, such as playing the game many times over to see a range of possible outcomes. There are two categories of wargames: quantitative games, with discrete types of moves, and qualitative games, which revolve around open-ended responses. Historically, automation efforts have focused on quantitative games, but large language models (LLMs) make it possible to automate qualitative wargames. We introduce "Snow Globe," an LLM-powered multi-agent system for playing qualitative wargames. With Snow Globe, every stage of a text-based qualitative wargame from scenario preparation to post-game analysis can be optionally carried out by AI, humans, or a combination thereof. We describe its software architecture conceptually and release an open-source implementation alongside this publication. As case studies, we simulate a tabletop exercise about an AI incident response and a political wargame about a geopolitical crisis. We discuss potential applications of the approach and how it fits into the broader wargaming ecosystem.
format Preprint
id arxiv_https___arxiv_org_abs_2404_11446
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Open-Ended Wargames with Large Language Models
Hogan, Daniel P.
Brennen, Andrea
Computation and Language
Artificial Intelligence
Computers and Society
Wargames are a powerful tool for understanding and rehearsing real-world decision making. Automated play of wargames using artificial intelligence (AI) enables possibilities beyond those of human-conducted games, such as playing the game many times over to see a range of possible outcomes. There are two categories of wargames: quantitative games, with discrete types of moves, and qualitative games, which revolve around open-ended responses. Historically, automation efforts have focused on quantitative games, but large language models (LLMs) make it possible to automate qualitative wargames. We introduce "Snow Globe," an LLM-powered multi-agent system for playing qualitative wargames. With Snow Globe, every stage of a text-based qualitative wargame from scenario preparation to post-game analysis can be optionally carried out by AI, humans, or a combination thereof. We describe its software architecture conceptually and release an open-source implementation alongside this publication. As case studies, we simulate a tabletop exercise about an AI incident response and a political wargame about a geopolitical crisis. We discuss potential applications of the approach and how it fits into the broader wargaming ecosystem.
title Open-Ended Wargames with Large Language Models
topic Computation and Language
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2404.11446