Shall We Play a Game? Language Models for Open-ended Wargames

AI
Security
Wargaming
An exploration of language models for open-ended wargames, investigating AI systems’ ability to influence large-scale decisions with implications for safety and interpretability.
Authors

Glenn Matlin

Parv Mahajan

Isaac Song

Yixiong Hao

Ryan Bard

Stu Topp

Evan Montoya

M. Rehan Parwani

Soham Shetty

Mark Riedl

Published

September 21, 2025

Publication

Shall We Play a Game? Language Models for Open-ended Wargames

An exploration of language models for open-ended wargames, investigating AI systems’ ability to influence large-scale decisions with implications for safety and interpretability.

Published

September 21, 2025

Authors

Glenn Matlin, Parv Mahajan, Isaac Song, Yixiong Hao, Ryan Bard, Stu Topp, Evan Montoya, M. Rehan Parwani, Soham Shetty, Mark Riedl

Venue

Wordplay: When Language Meets Games Workshop at the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP) 2025

Read on arXiv All Publications

Abstract

The ability for AI systems to influence large-scale decisions motivates additional research into the safety, interpretability, and explainability of AI in open-ended wargames. This paper explores the use of language models for open-ended wargaming scenarios, examining how LMs reason, plan, and interact in complex strategic environments.

Continue exploring

Return to the publication archive or step back to the broader research agenda.

Publications Research