Bridging the gap between algorithm development and hardware realization remains a persistent challenge, particularly in latency- and resource-constrained domains such as wireless communication. While MATLAB provides a mature environment for algorithm prototyping, translating these models into efficient FPGA implementations via High-Level Synthesis (HLS) often requires expert tuning and lengthy iterations. Recent advances in large language models (LLMs) offer new opportunities for automating this process. However, existing approaches suffer from hallucinations, forgetting, limited domain expertise, and often overlook key performance metrics. To address these limitations, we present A2H-MAS, a modular and hierarchical multi-agent system. At the system level, A2H-MAS assigns clearly defined responsibilities to specialized agents and uses standardized interfaces and execution-based validation to ensure correctness and reproducibility. At the algorithmic level, it employs dataflow-oriented modular decomposition and algorithm-hardware co-design, recognizing that the choice of algorithm often has a larger impact on hardware efficiency than pragma-level optimization. Experiments on representative wireless communication algorithms show that A2H-MAS consistently produces functionally correct, resource-efficient, and latency-optimized HLS designs, demonstrating its effectiveness and robustness for complex hardware development workflows.

翻译：弥合算法开发与硬件实现之间的鸿沟仍然是一个持续存在的挑战，在无线通信等对延迟和资源有严格限制的领域中尤其如此。虽然MATLAB为算法原型设计提供了成熟的环境，但通过高层次综合将这些模型转化为高效的FPGA实现通常需要专家级的调优和冗长的迭代。大型语言模型的最新进展为自动化这一过程提供了新的机遇。然而，现有方法存在幻觉、遗忘、领域专业知识有限等问题，并且常常忽视关键的性能指标。为了解决这些局限性，我们提出了A2H-MAS，这是一个模块化、层次化的多智能体系统。在系统层面，A2H-MAS为专门的智能体分配了明确定义的职责，并使用标准化接口和基于执行的验证来确保正确性和可复现性。在算法层面，它采用面向数据流的模块化分解和算法-硬件协同设计，认识到算法的选择通常比pragma级别的优化对硬件效率的影响更大。在代表性无线通信算法上的实验表明，A2H-MAS能够持续生成功能正确、资源高效且延迟优化的HLS设计，证明了其在复杂硬件开发工作流程中的有效性和鲁棒性。