让大模型智能体更可靠：用模块化设计分离思考与执行。
Bridging Symbolic Control and Neural Reasoning in LLM Agents -- The Structured Cognitive Loop
- 将认知拆分为五模块，用符号控制约束推理过程。
- 零策略违规、避免重复调用工具、全程可追溯决策。
- 适合追求可解释性与可控性的智能体开发者。
大型语言模型智能体存在推理与执行纠缠、记忆易失、动作序列失控等架构缺陷。本文提出结构化认知环（SCL），一种模块化智能体架构，将认知分解为检索、认知、控制、行动和记忆（R-CCAM）五个部分。SCL引入调控层，通过软符号控制对概率推理施加符号约束，同时保留独立的确定性控制引擎，用于防止重复调用、设置错误上限和判断终止。多步条件推理实验表明，SCL实现零策略违规、杜绝冗余工具调用，并保持完整的决策可追溯性。本文将SCL定位为混合智能，区别于以提示为中心、仅依赖记忆或神经符号的方法，提炼出三个可信智能体的设计原则：模块化分解、自适应符号治理和透明状态管理。项目开源并提供基于GPT-4o的实时旅行规划代理，为构建可靠、可解释、可管控的LLM智能体提供实用路径。
原文摘要 · Abstract (English)
Large language model agents suffer from architectural fragilities such as entangled reasoning and execution, memory volatility, and uncontrolled action sequences. We introduce Structured Cognitive Loop (SCL), a modular agent architecture that separates cognition into Retrieval, Cognition, Control, Action, and Memory (R-CCAM). SCL introduces Regulation as a dedicated governance layer through which Soft Symbolic Control applies symbolic constraints to probabilistic inference, while Control remains a distinct deterministic runtime engine for duplicate-call prevention, error limits, and termination judgment. Through multi-step conditional reasoning experiments, we show that SCL achieves zero policy violations, prevents redundant tool calls, and maintains complete decision traceability. We position SCL within hybrid intelligence, distinguish it from prompt-centric, memory-only, and neuro-symbolic approaches, and derive three design principles for trustworthy agents: modular decomposition, adaptive symbolic governance, and transparent state management. With an open-source implementation and a live GPT-4o-powered travel planning agent, this work offers a practical path toward reliable, explainable, and governable LLM agents.
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。