No One Wins in Nuclear War: A Social Simulation of Military Decision-making
Glenn Matlin, Isaac Song, Anthony Wen-Ming Zang, Mark Riedl
cs.CY, cs.AI, cs.CL, cs.MA
Submitted: 2026-08-03
Comments: 16 pages, 11 figures. Published at the Social Sim'26 Workshop at COLM 2026. Code and replay data: https://github.com/eilab-gt/wopr
Code: https://github.com/eilab-gt/wopr
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: WOPR is a social-simulation environment for studying how organizations make high-stakes decisions, built on a deterministic, replay-validated rules engine and using wargames as the vehicle.
Terminology
Abstract
WOPR is a social-simulation environment for studying how organizations make high-stakes decisions, built on a deterministic, replay-validated rules engine and using wargames as the vehicle. We instantiate it first with the published card game Nuclear War, traced against its published rules. We start with military decision-making because of its safety implications and because it needs further study, but the design is not specific to it: the decision-point contract that exposes the engine to agents is reusable across verifiable rule systems. Existing social-simulation work emphasizes persona fidelity and synthetic opinion, but lacks a verifiable rules engine with replay-checkable mechanics and private-channel negotiation. WOPR supplies that engine, and its contract makes every strategic choice an explicit agent decision. The method is agnostic to social-simulation frameworks; we adopt Concordia as the default harness for driving the game. On the same engine, WOPR layers a four-rung press ladder from silence to private single-recipient channels with structured commitments, and instantiates each faction as a collective command-and-control system rather than a single agent. We make all code, example configurations, and replay data publicly available at https://github.com/eilab-gt/wopr.
Sources
- Open-Ended Wargames with Large Language Models
- SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors
- War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars
- Human vs. Machine: Behavioral Differences Between Expert Humans and Language Models in Wargame Simulations
- NegotiationGym: Self-Optimizing Agents in a Multi-Agent Social Simulation Environment
- Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents
- Escalation Risks from Language Models in Military and Diplomatic Decision-Making
- Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia
- SocialMaze: A Benchmark for Evaluating and Enhancing Social Reasoning in Large Language Models in Complex Social Environments
Related papers
- GenAIT: Development and Validation of an Objective Generative AI Literacy Test for High School Students
- Reasoning Enhances Robustness to Prompt Injection in LLM-Based Consensus
- Generative AI Purpose-built for Social and Mental Health: A Real-World Pilot
- Comparative analysis of privacy-preserving open-source LLMs regarding extraction of diagnostic information from clinical CMR imaging reports
- PersonaMem-v3: Toward Omni-Platform Personal Intelligence for Holistic User Understanding, Recommendation, and Agentic Tasks
- What is an intelligent system?