mlsanityData to 7 Oct 2026

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

arXiv 2608.23601 ↗First posted 19 Aug 2026cs.AR cs.LG cs.MAcited by 0

Not on the map. Why?

Abstract (arXiv)

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 StateTune, which reformulates LLM-assisted EDA tuning as a closed-loop, state-carrying process. Its optimizer state is a typed, evidence-gated 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 (×) 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 10 of its 26 references that are in the map. First posted on arXiv 19 Aug 2026.

Builds on

10 of 26 references.

References · 10

  1. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  2. 2019Optuna: A Next-generation Hyperparameter Optimization Frameworkcited by 2,455
  3. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,000
  4. 2018BOHB: Robust and Efficient Hyperparameter Optimization at Scalecited by 466
  5. 2024AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basescited by 402
  6. 2020Differentiable Expected Hypervolume Improvement for Parallel Multi-Objective Bayesian Optimizationcited by 176
  7. 2016Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasetscited by 131
  8. 2024Customized Retrieval Augmented Generation and Benchmarking for EDA Tool Documentation QAcited by 28
  9. 2025Coarse-to-Fine Grounded Memory for LLM Agent Planningcited by 16
  10. 2025ORFS-agent: Tool-Using Agents for Chip Design Optimizationcited by 13

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AutoRAGTuner: A Declarative Framework for Automatic Optimization of RAG Pipelines
  2. 2026Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code Optimization
  3. 2026Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-Preferences
  4. 2026Retrieve, Schedule, Reflect: LLM Agents for Chip QoR Optimization
  5. 2025State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models
  6. 2025SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity
  7. 2024Understanding Forgetting in LLM Supervised Fine-Tuning and Preference Learning -- A Convex Optimization Perspective
  8. 2026AutoSG: LLM-Driven Solver Generation Solely from Task Prompts for Expensive Optimization