智能体原生的自适应通信架构
Agent-Native Metamorphic Communication Fabric
浏览论文内容
中文总结 AI 辅助
该研究针对现有通信方法无法覆盖多维度未来组合的问题，提出智能体原生自适应通信架构，通过三级变化机制实现可验证的运行时通信自适应，仿真验证了各级方法的性能优势。
中文摘要 AI 辅助
通信智能正经历两个相互关联的转变：算法开发正从基于手动模型的设计转向由基础模型辅助的生成与评估，而部署系统正从离线优化转向由智能体驱动的在线决策与受保护部署。现有的数据驱动方法和大语言模型（LLM）辅助方法主要仍是设计阶段的工具，无法覆盖服务意图、信道、频谱和硬件状态的所有未来组合。我们提出了智能体原生的自适应通信架构（Agent-Native Metamorphic Communication Fabric），这是一种闭环架构，其中智能体观察运行状态，选择或生成明确的通信候选方案，在数字孪生中对其进行评估，应用硬可行性门限，并部署该方案同时进行监控和设置备用方案。三个级别限定了变化的规模：1级在保留算法拓扑结构的同时调整参数；2级在保留协议和波形的同时切换并配置接收机算法；3级在保留服务契约和安全接口的同时重新配置波形或波形多址链。仿真验证了所有三个级别：1级在固定拓扑结构下提高了速率、信道跟踪或量化能量效率；2级在良好、中等和恶劣的多输入多输出（MIMO）场景中分别选择了三次迭代加权雅可比法、五次迭代对角预处理共轭梯度法和直接最小均方误差（MMSE）法，其硬件代理预测相比直接MMSE法可实现最高67.1%的能量降低和73.3%的延迟减少；3级在五种运行场景中分别选择了循环前缀正交频分复用（CP-OFDM）、单载波频分多址（SC-FDMA）、正交时频空间（OTFS）、滤波OFDM和正交频分多址的稀疏码多址接入（SCMA-over-OFDM），并在多普勒、频谱连续性、负载和射频功率扫描下形成了连续切换边界。这些结果确立了一种可验证的运行时通信自适应的最小可行机制，无需无约束的端到端学习或任意在线代码突变。
英文摘要
Communication intelligence is undergoing two linked transitions: algorithm development is moving from manual model-based design toward foundation-model-assisted generation and evaluation, while deployed systems are moving from offline optimization toward agent-driven online decision and guarded deployment. Existing data-driven and LLM-assisted methods remain primarily design-time tools and cannot cover every future combination of service intent, channel, spectrum, and hardware state. We propose the Agent-Native Metamorphic Communication Fabric, a closed-loop architecture in which an agent observes operating state, selects or generates an explicit communication candidate, evaluates it in a digital twin, applies hard feasibility gates, and deploys it with monitoring and fallback. Three levels bound the scale of change: Level 1 adjusts parameters while preserving algorithm topology; Level 2 switches and configures receiver algorithms while preserving protocol and waveform; and Level 3 reconfigures the waveform or waveform-multiple-access chain while preserving the service contract and safety interface. Simulations validate all three levels. Level 1 improves rate, channel tracking, or quantization energy under fixed topologies. Level 2 selects three-iteration weighted Jacobi, five-iteration diagonally preconditioned conjugate gradient, and direct MMSE in favorable, intermediate, and harsh MIMO regimes; its hardware proxy predicts up to 67.1% energy and 73.3% latency reduction relative to direct MMSE. Level 3 selects CP-OFDM, SC-FDMA, OTFS, filtered OFDM, and SCMA-over-OFDM across five operating regimes and forms continuous switching boundaries under Doppler, spectrum contiguity, load, and RF-power sweeps. These results establish a minimum viable mechanism for verifiable runtime communication adaptation without unconstrained end-to-end learning or arbitrary online code mutation.
发表机构
- National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China（电子科技大学通信科学与技术国家重点实验室）
机构由 AI 辅助整理，请以论文原文为准。
