Large language model agents suffer from fundamental architectural problems: entangled reasoning and execution, memory volatility, and uncontrolled action sequences. We introduce Structured Cognitive Loop (SCL), a modular architecture that explicitly separates agent cognition into five phases: Retrieval, Cognition, Control, Action, and Memory (R-CCAM). At the core of SCL is Soft Symbolic Control, an adaptive governance mechanism that applies symbolic constraints to probabilistic inference, preserving neural flexibility while restoring the explainability and controllability of classical symbolic systems. Through empirical validation on multi-step conditional reasoning tasks, we demonstrate that SCL achieves zero policy violations, eliminates redundant tool calls, and maintains complete decision traceability. These results address critical gaps in existing frameworks such as ReAct, AutoGPT, and memory-augmented approaches. Our contributions are threefold: (1) we situate SCL within the taxonomy of hybrid intelligence, differentiating it from prompt-centric and memory-only approaches; (2) we formally define Soft Symbolic Control and contrast it with neuro-symbolic AI; and (3) we derive three design principles for trustworthy agents: modular decomposition, adaptive symbolic governance, and transparent state management. We provide a complete open-source implementation demonstrating the R-CCAM loop architecture, alongside a live GPT-4o-powered travel planning agent. By connecting expert system principles with modern LLM capabilities, this work offers a practical and theoretically grounded path toward reliable, explainable, and governable AI agents.

翻译：大语言模型智能体存在根本性的架构问题：推理与执行相互纠缠、记忆易失性以及不可控的动作序列。本文提出结构化认知循环（SCL），这是一种模块化架构，将智能体认知明确划分为五个阶段：检索、认知、控制、行动与记忆（R-CCAM）。SCL的核心是软符号控制，这是一种自适应治理机制，它将符号约束应用于概率推理，在保持神经灵活性的同时，恢复了经典符号系统的可解释性与可控性。通过在多步条件推理任务上的实证验证，我们证明SCL实现了零策略违规、消除了冗余工具调用，并保持了完整的决策可追溯性。这些结果解决了现有框架（如ReAct、AutoGPT及记忆增强方法）中的关键缺陷。我们的贡献包括三个方面：（1）将SCL置于混合智能的分类体系中，将其与以提示为中心及纯记忆方法区分开来；（2）正式定义软符号控制，并将其与神经符号AI进行对比；（3）推导出可信智能体的三项设计原则：模块化分解、自适应符号治理以及透明状态管理。我们提供了一个完整的开源实现，展示了R-CCAM循环架构，并附带一个基于GPT-4o的实时旅行规划智能体。通过将专家系统原理与现代LLM能力相结合，这项工作为构建可靠、可解释且可治理的AI智能体提供了一条实用且具有理论依据的路径。