Personality-Driven Decision-Making in LLM-Based Autonomous Agents

The embedding of Large Language Models (LLMs) into autonomous agents is a rapidly developing field which enables dynamic, configurable behaviours without the need for extensive domain-specific training. In our previous work, we introduced SANDMAN, a Deceptive Agent architecture leveraging the Five-Factor OCEAN personality model, demonstrating that personality induction significantly influences agent task planning. Building on these findings, this study presents a novel method for measuring and evaluating how induced personality traits affect task selection processes - specifically planning, scheduling, and decision-making - in LLM-based agents. Our results reveal distinct task-selection patterns aligned with induced OCEAN attributes, underscoring the feasibility of designing highly plausible Deceptive Agents for proactive cyber defense strategies.

@article{newsham2025_2504.00727,
  title={ Personality-Driven Decision-Making in LLM-Based Autonomous Agents },
  author={ Lewis Newsham and Daniel Prince },
  journal={arXiv preprint arXiv:2504.00727},
  year={ 2025 }
}