StateTune: Transforming LLM-Assisted EDA Flow Tuning into a Stateful, Closed-Loop Process

Researchers introduced StateTune, a closed-loop LLM-assisted EDA flow tuning system with persistent optimization memory, which achieved the strongest final hypervolume on all six benchmark blocks in a Cadence industrial flow, outperforming five baselines including LLM+retrieval-augmented generation and preference-based Bayesian optimization. Ablation showed that removing persistent memory costs 58.5% of the hypervolume, and three-seed reproducibility showed coefficient of variation below 7% on five of six blocks.

arXiv:2608.23601v1 Announce Type: cross Abstract: EDA flow parameter tuning is critical for quality-of-results~ QoR , yet the parameter space is large, tightly coupled, and full evaluations are prohibitively expensive. Prior LLM-assisted tuners mainly use the LLM as an external proposer with transient working context; we instead present \textbf{StateTune}, which reformulates LLM-assisted EDA tuning as a closed-loop, state-carrying process. Its optimizer state is a typed, evidence-gated \emph{persistent optimization memory} that is updated by every evaluation and shared between candidate generation and budget allocation. On top of this optimizer state, an expected hypervolume improvement EHVI -guided, runtime-aware promotion policy ranks quick-stage candidates by expected Pareto frontier gain per unit of runtime cost. Evaluated on a Cadence industrial flow across six benchmark blocks two technology nodes \ \times\ three designs , against five baselines including LLM+retrieval-augmented generation RAG and preference-based Bayesian optimization BO tuners, StateTune achieves the strongest final hypervolume on all six benchmark blocks, showing a stable improvement in frontier quality across the full matrix; it also matches or surpasses the strongest baselines on worst negative slack WNS , area, and power across the same set. Ablation shows persistent memory is the largest contributor: removing it costs 58.5\% of the hypervolume. Dedicated analyses of evidence-gating sensitivity, memory poisoning, cross-design transfer, and three-seed reproducibility CV\,\ <\ \,7\% on five of six blocks further validate the memory design.