# Escalation Risks from Language Models in Military and Diplomatic Decision-Making

arXiv: https://arxiv.org/abs/2401.03408 · HTML: https://mlsanity.com/paper/2401.03408/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 27 references that are in the map.
- First posted on arXiv 7 Jan 2024.

## Builds on (most cited first, 1 of 1)

- [Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations](https://mlsanity.com/paper/2301.07255/) (2023)

## Built on by (most cited first, 30 of 63)

- [BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices](https://mlsanity.com/paper/2411.12990/) (2024)
- [Feedback Loops With Language Models Drive In-Context Reward Hacking](https://mlsanity.com/paper/2402.06627/) (2024)
- [Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents](https://mlsanity.com/paper/2505.02077/) (2025)
- [Risks from Language Models for Automated Mental Healthcare: Ethics and Structure for Implementation](https://mlsanity.com/paper/2406.11852/) (2024)
- [(Ir)rationality and Cognitive Biases in Large Language Models](https://mlsanity.com/paper/2402.09193/) (2024)
- [Human vs. Machine: Behavioral Differences Between Expert Humans and Language Models in Wargame Simulations](https://mlsanity.com/paper/2403.03407/) (2024)
- [On Large Language Models in National Security Applications](https://mlsanity.com/paper/2407.03453/) (2024)
- [Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems](https://mlsanity.com/paper/2602.15198/) (2026)
- [AI Risk Management Should Incorporate Both Safety and Security](https://mlsanity.com/paper/2405.19524/) (2024)
- [The LLM Effect: Are Humans Truly Using LLMs, or Are They Being Influenced By Them Instead?](https://mlsanity.com/paper/2410.04699/) (2024)
- [AI-Powered Autonomous Weapons Risk Geopolitical Instability and Threaten AI Research](https://mlsanity.com/paper/2405.01859/) (2024)
- [Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities](https://mlsanity.com/paper/2410.09114/) (2024)
- [Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia](https://mlsanity.com/paper/2512.03318/) (2025)
- [Measuring Free-Form Decision-Making Inconsistency of Language Models in Military Crisis Simulations](https://mlsanity.com/paper/2410.13204/) (2024)
- [Societal Adaptation to Advanced AI](https://mlsanity.com/paper/2405.10295/) (2024)
- [OpenEval: Benchmarking Chinese LLMs across Capability, Alignment and Safety](https://mlsanity.com/paper/2403.12316/) (2024)
- [Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility](https://mlsanity.com/paper/2507.11630/) (2025)
- [The Role of Social Learning and Collective Norm Formation in Fostering Cooperation in LLM Multi-Agent Systems](https://mlsanity.com/paper/2510.14401/) (2025)
- [Open-Ended Wargames with Large Language Models](https://mlsanity.com/paper/2404.11446/) (2024)
- [A Survey of Theory of Mind in Large Language Models: Evaluations, Representations, and Safety Risks](https://mlsanity.com/paper/2502.06470/) (2025)
- [Critical Foreign Policy Decisions (CFPD)-Benchmark: Measuring Diplomatic Preferences in Large Language Models](https://mlsanity.com/paper/2503.06263/) (2025)
- [AI Arms and Influence: Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises](https://mlsanity.com/paper/2602.14740/) (2026)
- [Large Language Models in Politics and Democracy: A Comprehensive Survey](https://mlsanity.com/paper/2412.04498/) (2024)
- [Markovian Transformers for Informative Language Modeling](https://mlsanity.com/paper/2404.18988/) (2024)
- [Military AI Needs Technically-Informed Regulation to Safeguard AI Research and its Applications](https://mlsanity.com/paper/2505.18371/) (2025)
- [The Prompt War: How AI Decides on a Military Intervention](https://mlsanity.com/paper/2507.06277/) (2025)
- [Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities](https://mlsanity.com/paper/2604.05339/) (2026)
- [Integrators at War: Mediating in AI-assisted Resort-to-Force Decisions](https://mlsanity.com/paper/2501.06861/) (2025)
- [Identifying Cooperative Personalities in Multi-agent Contexts through Personality Steering with Representation Engineering](https://mlsanity.com/paper/2503.12722/) (2025)
- [Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii](https://mlsanity.com/paper/2505.01372/) (2025)

## Abstract (arXiv)

Governments are increasingly considering integrating autonomous AI agents in high-stakes military and foreign-policy decision-making, especially with the emergence of advanced generative AI models like GPT-4. Our work aims to scrutinize the behavior of multiple AI agents in simulated wargames, specifically focusing on their predilection to take escalatory actions that may exacerbate multilateral conflicts. Drawing on political science and international relations literature about escalation dynamics, we design a novel wargame simulation and scoring framework to assess the escalation risks of actions taken by these agents in different scenarios. Contrary to prior studies, our research provides both qualitative and quantitative insights and focuses on large language models (LLMs). We find that all five studied off-the-shelf LLMs show forms of escalation and difficult-to-predict escalation patterns. We observe that models tend to develop arms-race dynamics, leading to greater conflict, and in rare cases, even to the deployment of nuclear weapons. Qualitatively, we also collect the models' reported reasonings for chosen actions and observe worrying justifications based on deterrence and first-strike tactics. Given the high stakes of military and foreign-policy contexts, we recommend further examination and cautious consideration before deploying autonomous language model agents for strategic military or diplomatic decision-making.