Abstract
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 an LLM-based script generation task, we present AgenticPD, a stage-aware agentic framework for physical design QoR optimization.
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.
Blogger's Review: AgenticPD significantly enhances optimization efficiency by segmenting the physical design process into multiple stages, thus avoiding redundant computations inherent in traditional methods. Its structured agent management and local decision-making mechanisms present an innovative approach to tackling complex design challenges, making it worthy of broader application in the design field.