提出人机共进化模型，解释长期互动中社会智能如何自然涌现。
Human-AI Coevolution Dynamics: A Formal Theory of Social Intelligence Emergence Through Long-Term Interaction
- 构建统一动力学框架，整合情感、记忆、人格等社会认知要素。
- 发现社会智能与认知能量负相关，互动轨迹呈现能量递减规律。
- 适合研究人机关系、社会智能演化或长期对话系统的设计者。
当前对话式AI在语言生成、个性化和长上下文交互方面取得显著进展，但多数方法仅通过孤立模块（如情绪建模、记忆检索或人格设定）模拟社会行为，缺乏统一框架解释长期人机互动中稳定人际关系与社会智能的形成。为此，我们提出人类-人工智能共进化动态框架（HACD-H），将情感适应、关系组织、社会记忆与人格一致性整合为一个自组织的社会认知系统。该框架引入多时间尺度社会认知、关系吸引子、信任盆地、发展相变及社会认知能量动力学等原则。基于约14,700轮对话构建数据集，并开发理论驱动的实证评估体系。结果揭示社会认知存在层级时间持久性、稳定关系吸引子、类相变式发展模式以及结构化的社会认知能量景观。社会智能与社会认知能量显著负相关（r = -0.391, p < 0.001），互动轨迹随时间呈现持续能量降低趋势。这些发现表明，社会智能源于长期社会认知共进化，而非孤立对话能力。HACD-H为建模自适应人机社会互动提供了统一理论基础，助力发展真正具备社会智能的AI系统。
原文摘要 · Abstract (English)
Current conversational AI systems have made significant progress in language generation, personalization, and long-context interaction. However, most existing methods model social behavior through isolated components such as emotion modeling, memory retrieval, or persona conditioning, lacking a unified framework to explain the emergence of stable social relationships and social intelligence in long-term human-AI interaction.To address this, we propose the Human-AI Coevolution Dynamics Framework (HACD-H), a formal model of human-AI interaction as a self-organizing social cognitive system. HACD-H integrates emotional adaptation, relational organization, social memory, and personality consistency into a unified dynamical framework and introduces principles including multi-timescale social cognition, relational attractors, trust basins, developmental phase transitions, and social cognitive energy dynamics.We construct a conversational dataset with approximately 14,700 interaction turns and develop a theory-driven empirical evaluation framework. Results reveal a hierarchy of temporal persistence in social cognition, stable relational attractors, phase-transition-like developmental patterns, and a structured social cognitive energy landscape. Social intelligence shows a significant negative correlation with social cognitive energy (r = -0.391, p < 0.001), and interaction trajectories exhibit progressive energy reduction over time.These findings suggest that social intelligence emerges from long-term social cognitive coevolution rather than isolated conversational capabilities. HACD-H provides a unified theoretical foundation for modeling adaptive human-AI social interaction and developing socially intelligent AI systems.
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。