# Position: AI Is Not Ready for Strategic Conflicts

arXiv: https://arxiv.org/abs/2609.16189 · HTML: https://mlsanity.com/paper/2609.16189/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 85 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 30 of 34)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.04388/) (2023)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Towards Understanding Sycophancy in Language Models](https://mlsanity.com/paper/2310.13548/) (2023)
- [Measuring Faithfulness in Chain-of-Thought Reasoning](https://mlsanity.com/paper/2307.13702/) (2023)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Measurement and Fairness](https://mlsanity.com/paper/1912.05511/) (2019)
- [AI Agents That Matter](https://mlsanity.com/paper/2407.01502/) (2024)
- [BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games](https://mlsanity.com/paper/2411.13543/) (2024)
- [Analyzing the Generalization and Reliability of Steering Vectors](https://mlsanity.com/paper/2407.12404/) (2024)
- [Mastering the Game of Stratego with Model-Free Multiagent Reinforcement Learning](https://mlsanity.com/paper/2206.15378/) (2022)
- [NoLiMa: Long-Context Evaluation Beyond Literal Matching](https://mlsanity.com/paper/2502.05167/) (2025)
- [ForecastBench: A Dynamic Benchmark of AI Forecasting Capabilities](https://mlsanity.com/paper/2409.19839/) (2024)
- [Systematic Biases in LLM Simulations of Debates](https://mlsanity.com/paper/2402.04049/) (2024)
- [GameBench: Evaluating Strategic Reasoning Abilities of LLM Agents](https://mlsanity.com/paper/2406.06613/) (2024)
- [Human-centered Explainable AI: Towards a Reflective Sociotechnical Approach](https://mlsanity.com/paper/2002.01092/) (2020)
- [Escalation Risks from Language Models in Military and Diplomatic Decision-Making](https://mlsanity.com/paper/2401.03408/) (2024)
- [Safety Cases: How to Justify the Safety of Advanced AI Systems](https://mlsanity.com/paper/2403.10462/) (2024)
- [Dungeons and Dragons as a Dialog Challenge for Artificial Intelligence](https://mlsanity.com/paper/2210.07109/) (2022)
- [SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?](https://mlsanity.com/paper/2503.12349/) (2025)
- [CALYPSO: LLMs as Dungeon Masters' Assistants](https://mlsanity.com/paper/2308.07540/) (2023)
- [Human vs. Machine: Behavioral Differences Between Expert Humans and Language Models in Wargame Simulations](https://mlsanity.com/paper/2403.03407/) (2024)
- [Measuring Free-Form Decision-Making Inconsistency of Language Models in Military Crisis Simulations](https://mlsanity.com/paper/2410.13204/) (2024)
- [Evaluating LLM Agent Collusion in Double Auctions](https://mlsanity.com/paper/2507.01413/) (2025)
- [Too Good to be Bad: On the Failure of LLMs to Role-Play Villains](https://mlsanity.com/paper/2511.04962/) (2025)
- [Why Would You Suggest That? Human Trust in Language Model Responses](https://mlsanity.com/paper/2406.02018/) (2024)
- [Open-Ended Wargames with Large Language Models](https://mlsanity.com/paper/2404.11446/) (2024)
- [Detecting and Adapting to Novelty in Games](https://mlsanity.com/paper/2106.02204/) (2021)

## Abstract (arXiv)

Open-ended strategic wargames are high-stakes LM-based social simulations: they model adversaries, institutions, escalation, plan brittleness, doctrine, and crisis response. Language models (LMs) are attractive because they can play agents, generate scenario branches, adjudicate ambiguous actions, and summarize lessons, but the same affordances make open-ended roles dangerous: model language determines both what an actor attempts and what becomes simulated reality. This position paper argues that no LM-enabled wargame should inform planning, doctrine, policy, or crisis response without an auditable safety case, and that the proper use of open-ended wargames today is to stress-test decision-influencing LM agents. We identify five failure modes: decision laundering, adjudication opacity, role collapse, escalation-through-adjudication, and failure of strategic imagination. Ordinary benchmarks cannot establish safety for these settings. Wargames can expose failures as stress tests; they are not themselves safety cases for consequential use.