arXiv:2507.16184cs.AIcs.HC2025-07

一个AI架构意外融合四种心智理论,实现更强推理能力。

Emergent Cognitive Convergence via Implementation: Structured Cognitive Loop Reflecting Four Theories of Mind

  • 五模块循环结构自发契合四大心智理论
  • 任务成功率95.8%,远超基线模型62.3%
  • 适合研究智能系统架构与认知机制的学者

我们发现,四个重要心智理论——卡尼曼双系统理论、弗里斯顿预测加工、明斯基心智社会论和克拉克扩展心智论——在名为Agentic Flow的实用AI架构中意外产生结构性趋同。该架构由检索、认知、控制、行动和记忆五个互锁模块构成,形成可重复的认知循环,最初仅受明斯基和克拉克启发。后续分析显示其结构与四理论的计算特征高度吻合。在可控评估中,该结构化代理达成95.8%的任务成功率,显著优于基线大语言模型的62.3%,表现出更强的约束遵循性与可复现推理能力。我们通过更广泛的描述性元架构PEACE总结其共性模式,如预测建模、关联回忆与误差敏感控制。后期形式化为结构化认知环(SCL),将Agentic Flow中首次实现的原则推广为基于大语言模型代理行为智能的基础。本文主张,智能架构可能因实践需求自然演化出共享结构,而非人为统一。因此,Agentic Flow是结构化认知环的一个实现实例,表明统一认知形态可源于现实推理的必然性,而非抽象推导。

原文摘要 · Abstract (English)

We report a structural convergence among four influential theories of mind: Kahneman dual-system theory, Friston predictive processing, Minsky society of mind, and Clark extended mind, emerging unintentionally within a practical AI architecture known as Agentic Flow. Designed to address limitations of large language models LLMs, Agentic Flow comprises five interlocking modules - Retrieval, Cognition, Control, Action, and Memory - organized into a repeatable cognitive loop. Although originally inspired only by Minsky and Clark, subsequent analysis showed that its structure echoes computational motifs from all four theories. This suggests that theoretical convergence may arise from implementation constraints rather than deliberate synthesis. In controlled evaluations, the structured agent achieved 95.8 percent task success compared to 62.3 percent for baseline LLMs, demonstrating stronger constraint adherence and more reproducible reasoning. We characterize this convergence through a broader descriptive meta-architecture called PEACE, highlighting recurring patterns such as predictive modeling, associative recall, and error-sensitive control. Later formalized as the Structured Cognitive Loop (SCL), this abstraction generalizes principles first realized in Agentic Flow as a foundation for behavioral intelligence in LLM-based agents.Rather than asserting theoretical unification, this position paper proposes that intelligent architectures may evolve toward shared structural patterns shaped by practical demands. Agentic Flow thus functions as an implementation instance of the Structured Cognitive Loop, illustrating how a unified cognitive form can emerge not from abstraction, but from the necessities of real-world reasoning.

认知架构AI代理结构趋同

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。