WGSR-Bench: Wargame-based Game-theoretic Strategic Reasoning Benchmark for Large Language Models

TL;DR

WGSR-Bench is a novel benchmark using wargame scenarios to evaluate large language models' strategic reasoning, including multi-agent decision-making and counterfactual reasoning, addressing a critical gap in AI capabilities.

Contribution

This paper introduces WGSR-Bench, the first strategic reasoning benchmark for LLMs based on wargame environments, integrating core tasks for comprehensive assessment.

Findings

LLMs show strengths in environmental awareness and opponent modeling.

The benchmark reveals limitations in strategic adaptability of current LLMs.

WGSR-Bench provides a systematic framework for evaluating multi-agent strategic reasoning.

Abstract

Recent breakthroughs in Large Language Models (LLMs) have led to a qualitative leap in artificial intelligence' s performance on reasoning tasks, particularly demonstrating remarkable capabilities in mathematical, symbolic, and commonsense reasoning. However, as a critical component of advanced human cognition, strategic reasoning, i.e., the ability to assess multi-agent behaviors in dynamic environments, formulate action plans, and adapt strategies, has yet to be systematically evaluated or modeled. To address this gap, this paper introduces WGSR-Bench, the first strategy reasoning benchmark for LLMs using wargame as its evaluation environment. Wargame, a quintessential high-complexity strategic scenario, integrates environmental uncertainty, adversarial dynamics, and non-unique strategic choices, making it an effective testbed for assessing LLMs' capabilities in multi-agent decision-making, intent inference, and counterfactual reasoning. WGSR-Bench designs test samples around three core tasks, i.e., Environmental situation awareness, Opponent risk modeling and Policy generation, which serve as the core S-POE architecture, to systematically assess main abilities of strategic reasoning. Finally, an LLM-based wargame agent is designed to integrate these parts for a comprehensive strategy reasoning assessment. With WGSR-Bench, we hope to assess the strengths and limitations of state-of-the-art LLMs in game-theoretic strategic reasoning and to advance research in large model-driven strategic intelligence.