Recent advances in large language models (LLMs) have sparked growing interest in automatic RTL optimization for better performance, power, and area (PPA). However, existing methods are still far from realistic RTL optimization. Their evaluation settings are often unrealistic: they are tested on manually degraded, small-scale RTL designs and rely on weak open-source tools. Their optimization methods are also limited, relying on coarse design-level feedback and simple pre-defined rewriting rules. To address these limitations, we present Dr. RTL, an agentic framework for RTL timing optimization in a realistic evaluation environment, with continual self-improvement through reusable optimization skills. We establish a realistic evaluation setting with more challenging RTL designs and an industrial EDA workflow. Within this setting, Dr. RTL performs closed-loop optimization through a multi-agent framework for critical-path analysis, parallel RTL rewriting, and tool-based evaluation. We further introduce group-relative skill learning, which compares parallel RTL rewrites and distills the optimization experience into an interpretable skill library. Currently, this library contains 47 pattern--strategy entries for cross-design reuse to improve PPA and accelerate convergence, and it can continue evolving over time. Evaluated on 20 real-world RTL designs, Dr. RTL achieves average WNS/TNS improvements of 21\%/17\% with a 6\% area reduction over the industry-leading commercial synthesis tool.

翻译：近年来，大语言模型（LLM）的进步激发了对自动RTL优化（以提升性能、功耗和面积，即PPA）的日益关注。然而，现有方法仍远未达到实际RTL优化的要求。它们的评估设置往往不切实际：仅在人工降质的小规模RTL设计上测试，且依赖性能较弱的开源工具。其优化方法也存在局限，仅依赖粗略的设计级反馈和简单的预定义重写规则。为解决这些局限，我们提出Dr. RTL——一种在真实评估环境中进行RTL时序优化的智能体框架，通过可复用的优化技能实现持续自我改进。我们建立了更贴近实际的评估场景，采用更具挑战性的RTL设计及工业级EDA工作流程。在此场景下，Dr. RTL通过多智能体框架执行闭环优化，涵盖关键路径分析、并行RTL重写及基于工具的评估。我们进一步引入群相对技能学习方法，通过对比并行RTL重写结果，将优化经验提炼为可解释的技能库。目前，该技能库包含47条模式-策略条目，支持跨设计复用以提升PPA并加速收敛，且可随时间持续进化。在20个真实RTL设计上的评估表明，与业界领先的商业综合工具相比，Dr. RTL在平均WNS/TNS上实现21%/17%的提升，同时面积减少6%。