As Large Language Model (LLM) based Multi-Agent Systems (MAS) evolve from experimental pilots to complex, persistent ecosystems, the limitations of direct agent-to-agent communication have become increasingly apparent. Current architectures suffer from fragmented context, stochastic hallucinations, rigid security boundaries, and inefficient topology management. This paper introduces Cognitive Fabric Nodes (CFN), a novel middleware layer that creates an omnipresent "Cognitive Fabric" between agents. Unlike traditional message queues or service meshes, CFNs are not merely pass-through mechanisms; they are active, intelligent intermediaries. Central to this architecture is the elevation of Memory from simple storage to an active functional substrate that informs four other critical capabilities: Topology Selection, Semantic Grounding, Security Policy Enforcement, and Prompt Transformation. We propose that each of these functions be governed by learning modules utilizing Reinforcement Learning (RL) and optimization algorithms to improve system performance dynamically. By intercepting, analyzing, and rewriting inter-agent communication, the Cognitive Fabric ensures that individual agents remain lightweight while the ecosystem achieves coherence, safety, and semantic alignment. We evaluate the effectiveness of the CFN on the HotPotQA and MuSiQue datasets in a multi-agent environment and demonstrate that the CFN improves performance by more than 10\% on both datasets over direct agent to agent communication.

翻译：基于大语言模型（LLM）的多智能体系统（MAS）正从实验性原型演化为复杂、持久的生态系统，在此过程中，智能体间直接通信的局限性日益凸显。当前架构面临上下文碎片化、随机幻觉、僵化安全边界及低效拓扑管理等挑战。本文提出认知织物节点（Cognitive Fabric Nodes, CFN），这是一种新型中间件层，可在智能体间构建无所不在的"认知织物"。与传统消息队列或服务网格不同，CFN并非单纯的透传机制，而是主动智能的中间节点。该架构的核心在于将记忆从简单存储提升为主动功能基板，支撑拓扑选择、语义锚定、安全策略执行与提示转换四项关键能力。我们提出采用强化学习与优化算法驱动的学习模块来动态调控每项功能。通过拦截、分析并重写智能体间通信，认知织物能够在保持单个智能体轻量化的同时，确保系统整体在语义一致性、安全性与逻辑连贯性上达成协调。我们在多智能体环境中的HotPotQA和MuSiQue数据集上验证了CFN的有效性，结果表明，相较于直接智能体间通信，CFN在两个数据集上的性能提升均超过10%。