StateTune is presented, which reformulates LLM-assisted EDA tuning as a closed-loop, state-carrying process that achieves the strongest final hypervolume on all six benchmark blocks, showing a stable improvement in frontier quality across the full matrix.
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.
OptiCom is proposed, a unified framework that represents LLM-driven optimizers within a shared configuration space: C=(A,Q,O,E,M,S), corresponding to artifact, query, operator, evaluation, memory, and strategy, corresponding to artifact, query, operator, evaluation, memory, and strategy.
Chen-Xing Wei, Si-Chen Liu, Lizzie Liu et al.· 0 citations
Dynamic Retrieval-based Policy Generation (DRPG) is proposed, a framework that integrates memory-based retrieval with a dynamic policy generator, leveraging historical data and environment feedback to produce task-specific policies for continual LLM improvement.
TicTacBench is proposed, a benchmark specifically designed to evaluate coding agents' capabilities for RTL-level timing closure under post-place-and-route (post-PnR) evaluation, and TicTacSkill is proposed, a new method that guides agents to follow standard timing-closure procedures and improves the Timing Closure Rate...
Bo-Wei Wang, Zhigang Fang, Zhi-Jie Yang et al.· 0 citations
Cedar is presented, which extends equality saturation to RTL an order of magnitude beyond prior e-graph work through an LLM-driven optimization loop that accumulates formally verified rewrite rules across designs : rules discovered while optimizing one circuit are reused on future, unseen ones.
LLM-based code generation fails when correctness depends on execution-dependent coupling: the meaning of one routine is defined by the runtime behavior of another, a relationship that cannot be resolved from textual descriptions alone. This limitation, which we call static binding, is not confined to explicitly coupled...
Gnaneswar Villuri, Hashmath Shaik, Alex Doboli· 1 citation
In the agentic flow, the PRISM codegen outperforms other baselines when optimizing complex code and drives the average normalized improvement across the HLS-Eval suite to 26.4\%.
Hao-Cheng Xu, Ye Qiao, Phyo Pyae Moe Aung et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.