用多智能体模拟人工意识，让大模型更懂自我与情绪。
Modeling Layered Consciousness with Multi-Agent Large Language Models
- 基于精神分析理论，用智能体互动模拟自我、前意识与无意识。
- 在8种个性化场景中，模型情感深度提升，输出波动减少，71.2%被偏好。
- 适合研究意识建模、个性化对话系统的人参考。
我们提出一种多智能体框架，用于在大型语言模型（LLMs）中建模人工意识，基于精神分析理论。提出的心理动力学模型通过智能体交互模拟自我意识、前意识和无意识，由结合固定特质与动态需求的个性化模块引导。在情感丰富的对话上采用参数高效微调，系统在八个个性化条件下进行评估。以LLM作为评判者的方法显示，微调模型获得71.2%的偏好，表现出更强的情感深度并降低输出方差，证明其在自适应个性化认知中的潜力。
原文摘要 · Abstract (English)
We propose a multi-agent framework for modeling artificial consciousness in large language models (LLMs), grounded in psychoanalytic theory. Our \textbf{Psychodynamic Model} simulates self-awareness, preconsciousness, and unconsciousness through agent interaction, guided by a Personalization Module combining fixed traits and dynamic needs. Using parameter-efficient fine-tuning on emotionally rich dialogues, the system was evaluated across eight personalized conditions. An LLM as a judge approach showed a 71.2\% preference for the fine-tuned model, with improved emotional depth and reduced output variance, demonstrating its potential for adaptive, personalized cognition.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。