Dr.~RTL: Autonomous Agentic RTL Optimization through Tool-Grounded Self-Improvement

2026-04-16

AI Summary

This work addresses the limitations of existing RTL automatic optimization approaches, which often rely on unrealistic evaluation environments and narrow optimization strategies that hinder integration into industrial EDA flows. To bridge this gap, the authors propose a multi-agent framework tailored for real-world RTL timing optimization, enabling closed-loop refinement within an industrial-grade synthesis flow. The framework leverages critical path analysis to guide parallel RTL rewriting and incorporates a population-based relative skill learning mechanism that distills rewriting experiences into an interpretable, design-agnostic optimization skill library, supporting continual improvement. Evaluated on 20 real-world designs, the method achieves an average 21% improvement in worst negative slack (WNS), 17% in total negative slack (TNS), and a 6% reduction in area, significantly outperforming leading commercial tools.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Optimization
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Recent advances in large language models (LLMs) have sparked growing interest in automatic RTL optimization for better performance, power, and area (PPA). However, existing methods are still far from realistic RTL optimization. Their evaluation settings are often unrealistic: they are tested on manually degraded, small-scale RTL designs and rely on weak open-source tools. Their optimization methods are also limited, relying on coarse design-level feedback and simple pre-defined rewriting rules. To address these limitations, we present Dr. RTL, an agentic framework for RTL timing optimization in a realistic evaluation environment, with continual self-improvement through reusable optimization skills. We establish a realistic evaluation setting with more challenging RTL designs and an industrial EDA workflow. Within this setting, Dr. RTL performs closed-loop optimization through a multi-agent framework for critical-path analysis, parallel RTL rewriting, and tool-based evaluation. We further introduce group-relative skill learning, which compares parallel RTL rewrites and distills the optimization experience into an interpretable skill library. Currently, this library contains 47 pattern--strategy entries for cross-design reuse to improve PPA and accelerate convergence, and it can continue evolving over time. Evaluated on 20 real-world RTL designs, Dr. RTL achieves average WNS/TNS improvements of 21\%/17\% with a 6\% area reduction over the industry-leading commercial synthesis tool.

Problem

• RTL optimization
• realistic evaluation
• PPA
• large language models
• EDA workflow

Innovation

• agentic RTL optimization
• tool-grounded self-improvement
• group-relative skill learning
• industrial EDA workflow
• interpretable skill library