显式认知分配：一种用于受控和可审计的大语言模型推理的原则
Explicit Cognitive Allocation: A Principle for Governed and Auditable Inference in Large Language Models
AI总结：
本文提出显式认知分配原则，通过认知通用代理架构实现结构化推理，提升大语言模型在高责任场景下的可追溯性和可审计性。
摘要：
大语言模型（LLMs）的快速采用已在科学、技术和社会组织领域催生了新的AI辅助推理形式。然而，现有的LLM使用方式仍然缺乏认知结构：问题框架、知识探索、检索、方法论意识和解释通常被折叠成一个生成过程。这种认知崩溃限制了可追溯性，削弱了认知控制，并破坏了可重复性，尤其是在高责任设置中。我们引入了显式认知分配，这是一种用于通过显式分离和协调认知功能来结构化AI辅助推理的一般原则。我们通过认知通用代理（CUA）架构实现了这一原则，该架构将推理分为探索和框架阶段、认知锚定、工具性和方法性映射以及解释性综合。这一框架的核心概念是通用认知工具（UCIs），它们通过计算、实验、组织、监管和教育工具等异质手段，将抽象问题转化为可研究的问题。我们通过在匹配执行条件下比较CUA引导的推理与基线LLM推理进行受控比较，评估显式认知和工具分配的效果。在多个农业领域的提示中，CUA推理表现出更早且结构化的认知收敛，更高的语义扩展下的认知一致性，以及系统暴露了探究的工具景观。相比之下，基线LLM推理在一致性上表现出更大的变异性，并未能显式揭示工具结构。
英文摘要：
The rapid adoption of large language models (LLMs) has enabled new forms of AI-assisted reasoning across scientific, technical, and organizational domains. However, prevailing modes of LLM use remain cognitively unstructured: problem framing, knowledge exploration, retrieval, methodological awareness, and explanation are typically collapsed into a single generative process. This cognitive collapse limits traceability, weakens epistemic control, and undermines reproducibility, particularly in high-responsibility settings. We introduce Explicit Cognitive Allocation, a general principle for structuring AI-assisted inference through the explicit separation and orchestration of epistemic functions. We instantiate this principle in the Cognitive Universal Agent (CUA), an architecture that organizes inference into distinct stages of exploration and framing, epistemic anchoring, instrumental and methodological mapping, and interpretive synthesis. Central to this framework is the notion of Universal Cognitive Instruments (UCIs), which formalize heterogeneous means, including computational, experimental, organizational, regulatory, and educational instruments, through which abstract inquiries become investigable. We evaluate the effects of explicit cognitive and instrumental allocation through controlled comparisons between CUA-orchestrated inference and baseline LLM inference under matched execution conditions. Across multiple prompts in the agricultural domain, CUA inference exhibits earlier and structurally governed epistemic convergence, higher epistemic alignment under semantic expansion, and systematic exposure of the instrumental landscape of inquiry. In contrast, baseline LLM inference shows greater variability in alignment and fails to explicitly surface instrumental structure.
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。
