English

Evaluating Counterfactual Strategic Reasoning in Large Language Models

Computation and Language 2026-05-25 v2

Abstract

We evaluate Large Language Models (LLMs) in repeated game-theoretic settings to assess whether strategic performance reflects genuine reasoning or reliance on memorized patterns. We consider two canonical games, Prisoner's Dilemma (PD) and Rock-Paper-Scissors (RPS), upon which we introduce counterfactual variants that alter payoff structures and action labels, breaking familiar symmetries and dominance relations. Our multi-metric evaluation framework compares default and counterfactual instantiations, showcasing LLM limitations in incentive sensitivity, structural generalization and strategic reasoning within counterfactual environments.

Keywords

Cite

@article{arxiv.2603.19167,
  title  = {Evaluating Counterfactual Strategic Reasoning in Large Language Models},
  author = {Dimitrios Georgousis and Maria Lymperaiou and Angeliki Dimitriou and Giorgos Filandrianos and Giorgos Stamou},
  journal= {arXiv preprint arXiv:2603.19167},
  year   = {2026}
}

Comments

Accepted at GEM@ACL 2026

R2 v1 2026-07-01T11:28:34.741Z