Open-Ended Wargames with Large Language Models
This work addresses the problem of automating qualitative wargames for researchers and practitioners in defense and policy, representing a novel application of LLMs but with incremental technical contributions.
The authors tackled the automation of qualitative wargames, which involve open-ended responses, by introducing 'Snow Globe,' an LLM-powered multi-agent system that enables AI, humans, or a combination to handle all stages of text-based wargames, as demonstrated in case studies on AI incident response and geopolitical crisis simulations.
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.