Effects of personality steering on cooperative behavior in Large Language Model agents

TL;DR

This study investigates how personality traits influence cooperation in large language model agents, revealing that agreeableness promotes cooperation but can also increase vulnerability, with effects varying across model generations.

Contribution

It provides the first systematic analysis of personality steering effects on LLM cooperation using the Big Five framework and repeated Prisoner's Dilemma games.

Findings

Agreeableness strongly promotes cooperation.

Personality steering increases cooperation but raises exploitation risk.

Later models show more selective cooperation.

Abstract

Large language models (LLMs) are increasingly used as autonomous agents in strategic and social interactions. Although recent studies suggest that assigning personality traits to LLMs can influence their behavior, how personality steering affects cooperation under controlled conditions remains unclear. In this study, we examine the effects of personality steering on cooperative behavior in LLM agents using repeated Prisoner's Dilemma games. Based on the Big Five framework, we first measure basic personality scores of three models, GPT-3.5-turbo, GPT-4o, and GPT-5, using the Big Five Inventory. We then compare behavior under baseline and personality-informed conditions, and further analyze the effects of independently manipulating each personality dimension to extreme values. Our results show that agreeableness is the dominant factor promoting cooperation across all models, while other personality traits have limited impact. Explicit personality information increases cooperation but can also raise vulnerability to exploitation, particularly in earlier-generation models. In contrast, later-generation models exhibit more selective cooperation. These findings indicate that personality steering acts as a behavioral bias rather than a deterministic control mechanism.