标题： 前缀代理：一种用于高效前缀加法器优化的LLM驱动设计框架 显示英文标题

标题： PrefixAgent: An LLM-Powered Design Framework for Efficient Prefix Adder Optimization

摘要： 前缀加法器是基本的算术电路，但其设计空间随着位宽的增加呈指数增长，带来了显著的优化挑战。 以往的工作在性能、泛化能力和可扩展性方面存在局限性。 为了解决这些挑战，我们提出了PrefixAgent，这是一个由大型语言模型（LLM）驱动的框架，能够实现高效的前缀加法器优化。 具体而言，PrefixAgent将问题重新表述为包括骨干合成和结构优化在内的子任务，这有效地减少了搜索空间。 更重要的是，这种新的设计视角使我们能够高效地收集大量高质量的数据和推理轨迹，通过E图，这进一步导致了LLM的有效微调。 实验结果表明，与基线方法相比，PrefixAgent合成的前缀加法器具有更小的面积，同时在商业EDA流程中保持了可扩展性和泛化能力。 显示英文摘要

摘要： Prefix adders are fundamental arithmetic circuits, but their design space grows exponentially with bit-width, posing significant optimization challenges. Previous works face limitations in performance, generalization, and scalability. To address these challenges, we propose PrefixAgent, a large language model (LLM)-powered framework that enables efficient prefix adder optimization. Specifically, PrefixAgent reformulates the problem into subtasks including backbone synthesis and structure refinement, which effectively reduces the search space. More importantly, this new design perspective enables us to efficiently collect enormous high-quality data and reasoning traces with E-graph, which further results in an effective fine-tuning of LLM. Experimental results show that PrefixAgent synthesizes prefix adders with consistently smaller areas compared to baseline methods, while maintaining scalability and generalization in commercial EDA flows.