结构化人格控制与适应用于大语言模型代理
Structured Personality Control and Adaptation for LLM Agents
AI总结：
本文提出基于荣格心理学类型模型的结构化人格控制框架，通过协调、强化补偿和反思机制实现LLM人格的细腻表达与动态适应，提升人机交互中的自然代理设计。
摘要：
大语言模型（LLMs）正在越来越多地塑造人机交互（HCI），从个性化助手到社会模拟。除了语言能力之外，研究人员正在探索LLMs是否能够表现出人类特征，从而影响参与度、决策和感知的现实性。人格尤其关键，但现有方法往往难以实现细腻且适应性的表达。我们提出了一种框架，通过荣格心理学类型模型LLM的人格，整合三种机制：主导-辅助协调机制用于一致的核心表达，强化-补偿机制用于临时适应上下文，以及驱动长期人格演化的反思机制。这种设计使代理能够在保持细腻特征的同时动态调整以适应交互需求，并逐渐更新其底层结构。人格匹配通过迈尔斯-布里格斯类型指标问卷进行评估，并在多样化的挑战场景中测试作为初步结构评估。研究结果表明，演化的、具有人格意识的LLMs可以支持一致的、情境敏感的交互，从而在HCI中实现自然的代理设计。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
