AgenticPD: A Stage-Aware Agentic Framework for Closed-Loop Physical Design Optimization

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 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.

7 pages, 7 figures. Accepted at ASP-DAC 2027. Updated manuscript

Artificial Intelligence (cs.AI)

arXiv:2607.04758 [cs.AI]

(or arXiv:2607.04758v3 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2607.04758 Focus to learn more arXiv-issued DOI via DataCite

https://doi.org/10.1145/3840404.3848213 Focus to learn more DOI(s) linking to related resources

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.