Psychologically Enhanced AI Agents
This work addresses the need for interpretable and controllable AI agents in applications like narrative generation and multi-agent systems, though it is incremental as it builds on existing prompt engineering techniques without fine-tuning.
The paper tackles the problem of controlling Large Language Model (LLM) agent behavior by introducing MBTI-in-Thoughts, a framework that uses psychological personality conditioning via prompt engineering, resulting in consistent behavioral biases such as emotionally expressive agents excelling in narrative generation and analytically primed agents adopting stable strategies in game-theoretic settings.
We introduce MBTI-in-Thoughts, a framework for enhancing the effectiveness of Large Language Model (LLM) agents through psychologically grounded personality conditioning. Drawing on the Myers-Briggs Type Indicator (MBTI), our method primes agents with distinct personality archetypes via prompt engineering, enabling control over behavior along two foundational axes of human psychology, cognition and affect. We show that such personality priming yields consistent, interpretable behavioral biases across diverse tasks: emotionally expressive agents excel in narrative generation, while analytically primed agents adopt more stable strategies in game-theoretic settings. Our framework supports experimenting with structured multi-agent communication protocols and reveals that self-reflection prior to interaction improves cooperation and reasoning quality. To ensure trait persistence, we integrate the official 16Personalities test for automated verification. While our focus is on MBTI, we show that our approach generalizes seamlessly to other psychological frameworks such as Big Five, HEXACO, or Enneagram. By bridging psychological theory and LLM behavior design, we establish a foundation for psychologically enhanced AI agents without any fine-tuning.