AgenticPD: A Stage-Aware Agentic Framework for Physical Design QoR Optimization
For EDA practitioners, AgenticPD reduces the cost of physical design optimization by enabling efficient search across stages, though the improvement is incremental over existing methods.
AgenticPD introduces a stage-aware agentic framework for physical design QoR optimization that reuses intermediate checkpoints to avoid full-flow re-runs, achieving strong post-route timing while remaining competitive in power and area.
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.