{"ID":5937292,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-09T07:52:46.28543944Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04758","arxiv_id":"2607.04758","title":"AgenticPD: A Stage-Aware Agentic Framework for Physical Design QoR 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. 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.","short_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 presen...","url_abs":"https://arxiv.org/abs/2607.04758","url_pdf":"https://arxiv.org/pdf/2607.04758v1","authors":"[\"Shuo Ren\",\"Zijin Cheng\",\"Yaohui Han\",\"Libo Shen\",\"Leilei Jin\",\"Wanting Tian\",\"Rongliang Fu\",\"Chao Wang\",\"Bei Yu\",\"Tsung-Yi Ho\"]","published":"2026-07-06T07:55:34Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Large Language Model\",\"Generative Adversarial Network\"]","has_code":false}