Rapid advances in Large Language Models (LLMs) create new opportunities by enabling efficient exploration of broad, complex design spaces. This is particularly valuable in computer architecture, where performance depends on microarchitectural designs and policies drawn from vast combinatorial spaces. We introduce Agentic Architect, an agentic AI framework for computer architecture design exploration and optimization that combines LLM-driven code evolution with cycle-accurate simulation. The human architect specifies the optimization target, seed design, scoring function, simulator interface, and benchmark split, while the LLM explores implementations within these constraints. Across cache replacement, data prefetching, and branch prediction, Agentic Architect matches or exceeds state-of-the-art designs. Our best evolved cache replacement design achieves a 1.062x geomean IPC speedup over LRU, 0.6% over Mockingjay (1.056x). Our evolved branch predictor achieves a 1.100x geomean IPC speedup over Bimodal, 1.5% over its Hashed Perceptron seed (1.085x). Finally, our evolved prefetcher achieves a 1.76x geomean IPC speedup over no prefetching, 17% over its VA/AMPM Lite seed (1.59x) and 21% over SMS (1.55x). Our analysis surfaces several findings about agentic AI-driven microarchitecture design. Across evolved designs, components often correspond to known techniques; the novelty lies in how they are coordinated. The architect's role is shifting, but the human remains central. Seed quality bounds what search can achieve: evolution can refine and extend an existing mechanism, but cannot compensate for a weak foundation. Likewise, objectives, constraints, and prompt guidance affect reliability and generalization. Overall, Agentic Architect is the first end-to-end open-source framework for agentic AI architecture exploration and optimization.

翻译：大型语言模型（LLM）的快速进步通过高效探索广泛而复杂的设计空间带来了新的机遇。这在计算机体系结构中尤为宝贵——性能取决于从巨大组合空间中选取的微架构设计与策略。我们提出智能架构师（Agentic Architect），一个将LLM驱动的代码进化与周期精确仿真相结合的智能体AI框架，用于计算机架构设计探索与优化。人类架构师指定优化目标、初始设计、评分函数、仿真器接口及基准测试划分，而LLM在这些约束内探索实现方案。在缓存替换、数据预取和分支预测任务中，智能架构师达到或超越了最先进的设计。我们进化出的最佳缓存替换设计相对LRU获得1.062x的几何平均IPC加速比，比Mockingjay（1.056x）提升0.6%；进化出的分支预测器相对Bimodal获得1.100x的加速比，比其哈希感知机初始设计（1.085x）提升1.5%；进化出的预取器相对无预取获得1.76x的加速比，比VA/AMPM Lite初始设计（1.59x）提升17%，比SMS（1.55x）提升21%。我们的分析揭示了智能体AI驱动的微架构设计的若干发现：在进化出的设计方案中，组件往往对应已知技术，其新颖性在于如何协调这些组件。架构师的角色正在转变，但人类仍然处于核心地位。初始设计质量决定了搜索所能达到的边界：进化可以优化和扩展现有机制，但无法弥补薄弱的基础。同样，目标、约束和提示指导影响可靠性和泛化能力。总体而言，智能架构师是首个面向智能体AI架构探索与优化的端到端开源框架。