Structured Personality Control and Adaptation for LLM Agents
This addresses the need for more naturalistic and engaging LLM agents in HCI, though it appears incremental by building on existing personality modeling approaches.
The paper tackles the problem of enabling LLMs to exhibit nuanced and adaptable personality traits for human-computer interaction, presenting a framework based on Jungian psychological types that allows agents to maintain coherent core expression while dynamically adjusting to context and evolving over time, with evaluation using Myers-Briggs Type Indicator questionnaires showing support for coherent, context-sensitive interactions.
Large Language Models (LLMs) are increasingly shaping human-computer interaction (HCI), from personalized assistants to social simulations. Beyond language competence, researchers are exploring whether LLMs can exhibit human-like characteristics that influence engagement, decision-making, and perceived realism. Personality, in particular, is critical, yet existing approaches often struggle to achieve both nuanced and adaptable expression. We present a framework that models LLM personality via Jungian psychological types, integrating three mechanisms: a dominant-auxiliary coordination mechanism for coherent core expression, a reinforcement-compensation mechanism for temporary adaptation to context, and a reflection mechanism that drives long-term personality evolution. This design allows the agent to maintain nuanced traits while dynamically adjusting to interaction demands and gradually updating its underlying structure. Personality alignment is evaluated using Myers-Briggs Type Indicator questionnaires and tested under diverse challenge scenarios as a preliminary structured assessment. Findings suggest that evolving, personality-aware LLMs can support coherent, context-sensitive interactions, enabling naturalistic agent design in HCI.