Psychologically Enhanced AI Agents

2025-09-04

AI Summary

This study addresses the challenge of enhancing behavioral controllability and task adaptability of LLM-based agents through personality psychology. We propose MBTI-in-Thoughts, the first framework to systematically inject classical personality theories—including MBTI, Big Five, HEXACO, and Enneagram—into LLMs via prompt engineering, enabling fine-tuning-free, psychologically grounded agent modeling across cognitive and affective dimensions. The method supports multi-agent collaboration and reflexive interaction, with personality trait stability empirically validated using the 16Personalities benchmark. Experiments demonstrate that agents instantiated with distinct personality profiles exhibit interpretable behavioral preferences in narrative generation and game-theoretic decision-making; integrating self-reflection further improves cooperative efficiency and reasoning quality. Our core contributions are threefold: (1) establishing a psychology-driven paradigm for LLM personalization, (2) ensuring theoretical rigor through alignment with established personality models, and (3) achieving engineering lightweightness and behavioral interpretability without architectural modification or parameter updates.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Adversarial Agents
• Humans and AI: Learning Human Values and Preferences

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

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.

Problem

• Enhancing LLM agents with psychological personality conditioning
• Controlling AI behavior through cognition and affect axes
• Ensuring trait persistence across diverse psychological frameworks

Innovation

• Personality conditioning via MBTI prompt engineering
• Automated trait verification using 16Personalities test
• Generalizable framework for multiple psychological frameworks