用分阶段智能体框架优化芯片物理设计，减少重复计算。
AgenticPD: A Stage-Aware Agentic Framework for Physical Design QoR Optimization
- 按物理设计流程分阶段部署专用智能体，局部决策更高效。
- 相比基线方法，时序表现显著提升，功耗与面积保持竞争力。
- 支持从中间状态恢复并复用检查点，节省大量EDA运行时间。
物理设计质量（QoR）优化困难且成本高昂，各阶段决策相互影响，每次评估需完成全流程EDA运行。现有方法多将优化视为参数调优或基于大模型的脚本生成任务。本文提出AgenticPD——一种面向物理设计流程的阶段感知型智能体框架。该框架围绕物理设计流程的阶段边界组织，由裁判智能体统筹搜索，各阶段专用智能体使用本地工具进行局部决策。同时，智能体系统提供结构化观测、执行历史与上下文管理机制，支持从先前中间状态分支并复用检查点，持续优化流程。所有候选方案均在布线后签核阶段进行评估。实验表明，相比基线方法，AgenticPD在布线后时序方面表现优异，功耗与面积仍保持竞争力。
原文摘要 · Abstract (English)
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. As a result, the system can branch from prior intermediate states and reuse checkpoints to continue the optimization procedure, and every candidate is evaluated at the post-route signoff. Across these baselines, AgenticPD achieves strong post-route timing while remaining competitive in power and area.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。