AI 中文总结
针对物理设计QoR优化难题，现有方法欠佳。提出AgenticPD框架，围绕物理设计流程阶段边界组织，利用Judge Agent引导搜索，阶段专用智能体借助本地工具做决策，提升优化效果。
AI 中文摘要
物理设计结果质量（QoR）优化既困难又昂贵。一个阶段做出的选择会对后续阶段产生影响。每次评估都需要通过完整流程进行昂贵的EDA运行。虽然现有方法仍将优化视为扁平参数调整或基于大语言模型的脚本生成任务，但我们提出了AgenticPD，这是一个用于物理设计QoR优化的阶段感知智能体框架。AgenticPD不是在每次试验后重新运行完整流程，而是围绕物理设计流程的阶段边界进行组织，其中一个Judge Agent引导搜索，阶段专用智能体使用阶段本地工具在其自己的阶段内做出本地决策。此外，AgenticPD中的智能体工具提供结构化观察、执行历史和智能体上下文管理。因此，系统可以从先前的中间状态分支并重用检查点以继续优化过程，并且每个候选方案都在布线后签收时进行评估。在这些基线中，AgenticPD在布线后实现了强大的时序，同时在功耗和面积方面保持竞争力。
英文摘要
Physical design quality-of-results (QoR) optimization is hard and expensive. Choices made at one stage can help or hurt later stages. Each evaluation requires a costly EDA run through the full flow. While existing methods still treat optimization as flat parameter tuning or a LLM-based script generation task, we present AgenticPD, a stage-aware agentic framework for physical design QoR optimization. Instead of re-running the full flow after every trial, AgenticPD is organized around the stage boundaries of the physical design flow, where a Judge Agent navigates the search and stage-specialized agents make local decisions within their own stage using stage-local tools. Additionally, the agent harness in AgenticPD provides structured observations, execution history, and agent context management. Experimental results show that AgenticPD achieves the best timing performance among the evaluated PD tuners while maintaining competitive power and area.
Comments7 pages, 7 figures. Accepted at ASP-DAC 2027. Updated manuscript
