# Evaluating Counterfactual Strategic Reasoning in Large Language Models

arXiv: https://arxiv.org/abs/2603.19167 · HTML: https://mlsanity.com/paper/2603.19167/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 5 of its 29 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 5 of 5)

- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Nicer Than Humans: How do Large Language Models Behave in the Prisoner's Dilemma?](https://mlsanity.com/paper/2406.13605/) (2024)
- [TMGBench: A Systematic Game Benchmark for Evaluating Strategic Reasoning Abilities of LLMs](https://mlsanity.com/paper/2410.10479/) (2024)
- [CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Models](https://mlsanity.com/paper/2502.11008/) (2025)
- [Causal Consistency Regularization: Training Verifiably Sensitive Reasoning in Large Language Models](https://mlsanity.com/paper/2509.01544/) (2025)

## Built on by (most cited first, 1 of 1)

- [Recognition, Simulation, and Refusal: A Contamination-Aware Study of Classic Psychological Effects in LLM Agents](https://mlsanity.com/paper/2609.22090/) (2026)

## Abstract (arXiv)

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.