Back to AI News
arxiv

Toward Autonomous RTL and Synthesis Optimization: Benchmarking and Self-Improving Agents

This arXiv paper examines autonomous LLM-agent approaches for RTL and synthesis optimization across realistic benchmarking, tool-grounded RTL rewriting, and synthesis-script tuning. It presents Dr. RTL, a multi-agent framework that automates critical-path analysis, RTL rewriting, and implementation-level evaluation while accumulating reusable optimization skills. On 20 real-world RTL designs, the authors report average WNS/TNS improvements of 21%/17% and a 6% area reduction over commercial synthesis. The paper also outlines a vision for AI-native design automation spanning architectural, RTL, and EDA algorithm spaces.

AI Brief

It offers a concrete agent framework and benchmark direction for applying LLMs to hardware design optimization, with reported synthesis outcomes on real-world RTL designs.

arXiv:2611.13713v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) and autonomous agents are creating new opportunities for hardware design optimization. This paper examines three connected directions toward autonomous RTL and synthesis optimization: (1) Realistic benchmarking. We discuss reference-based and open-ended RTL optimization benchmarks that evaluate optimization opportunities under realistic EDA workflows. (2) Tool-grounded RTL optimization. We present Dr. RTL, a multi-agent framework that automates critical-path analysis, RTL rewriting, and implementation-level evaluation, while continuously improving through reusable optimization skills. Evaluated on 20 real-world RTL designs, Dr.~RTL achieves average WNS/TNS improvements of 21\%/17\% with a 6\% area reduction over commercial synthesis. (3) Design-specific synthesis optimization. We explore agent-driven synthesis script tuning and the discovery of executable synthesis algorithms across intermediate representations, technology-independent optimization, and technology mapping. Finally, we envision AI-native design automation that jointly explores architectural, RTL, and EDA algorithm design spaces, guided by verification constraints and implementation feedback.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!