Automated QoR improvement in OpenROAD with coding agents

2026-01-09

arXiv.org

AI Summary

This work addresses the longstanding bottleneck in electronic design automation (EDA) caused by the scarcity of expert resources, which hampers the efficiency and innovation of physical design optimization. We propose AuDoPEDA, the first end-to-end autonomous framework for EDA tool development and optimization, built upon large language models to establish a closed-loop development pipeline. By analyzing the OpenROAD codebase, AuDoPEDA autonomously decomposes tasks, generates research directions, produces executable code modifications, and iteratively refines them based on power, performance, and area (PPA) metrics. With minimal human intervention, the system achieves up to a 5.9% reduction in wirelength and up to a 10.0% shortening of the critical path clock period within OpenROAD, significantly enhancing physical design quality.

Technology Category

• Search and Optimization: Learning to Search
• Humans and AI: Game Design — Virtual Humans, NPCs and Autonomous Characters
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

EDA development and innovation has been constrained by scarcity of expert engineering resources. While leading LLMs have demonstrated excellent performance in coding and scientific reasoning tasks, their capacity to advance EDA technology itself has been largely untested. We present AuDoPEDA, an autonomous, repository-grounded coding system built atop OpenAI models and a Codex-class agent that reads OpenROAD, proposes research directions, expands them into implementation steps, and submits executable diffs. Our contributions include (i) a closed-loop LLM framework for EDA code changes; (ii) a task suite and evaluation protocol on OpenROAD for PPA-oriented improvements; and (iii) end-to-end demonstrations with minimal human oversight. Experiments in OpenROAD achieve routed wirelength reductions of up to 5.9%, effective clock period reductions of up to 10.0%, and power reductions of up to 19.4%.

Problem

• EDA
• QoR improvement
• expert scarcity
• automated coding
• OpenROAD

Innovation

• LLM-driven EDA
• autonomous code generation
• PPA optimization
• OpenROAD
• closed-loop coding agent