Evolving Personalities in Chaos: An LLM-Augmented Framework for Character Discovery in the Iterated Prisoners Dilemma under Environmental Stress

TL;DR

This paper introduces a new framework combining environmental stressors and LLM-based profiling to evolve and interpret resilient strategies in the Iterated Prisoners Dilemma, enhancing realism and interpretability.

Contribution

It presents a novel approach integrating stochastic environmental perturbations with LLMs to produce and interpret diverse, resilient strategies in evolutionary game theory.

Findings

Strategies evolved under chaos are more resilient.

LLMs can classify behavioral phenotypes effectively.

Genetic strategies remain opaque to manual inspection.

Abstract

Standard simulations of the Iterated Prisoners Dilemma (IPD) operate in deterministic, noise-free environments, producing strategies that may be theoretically optimal but fragile when confronted with real-world uncertainty. This paper addresses two critical gaps in evolutionary game theory research: (1) the absence of realistic environmental stressors during strategy evolution, and (2) the Interpretability Gap, where evolved genetic strategies remain opaque binary sequences devoid of semantic meaning. We introduce a novel framework combining stochastic environmental perturbations (God Mode) with Large Language Model (LLM)-based behavioral profiling to transform evolved genotypes into interpretable character archetypes. Our experiments demonstrate that strategies evolved under chaotic conditions exhibit superior resilience and present distinct behavioral phenotypes, ranging from Ruthless Capitalists to Diplomatic Enforcers. These phenotypes are readily classified by LLMs but remain nearly impossible to interpret through manual genome inspection alone. This work bridges evolutionary computation with explainable AI and provides a template for automated agent characterization in multi-agent systems.