面向自主 RTL 与综合优化的基准评测与自我改进智能体
Toward Autonomous RTL and Synthesis Optimization: Benchmarking and Self-Improving Agents
AI 导读
该 ASP-DAC'27 邀请论文探讨迈向自主 RTL 与综合优化的三个方向：真实基准评测、基于工具的 RTL 优化与设计专用综合优化。其多智能体框架 Dr. RTL 自动化关键路径分析、RTL 重写和实现级评估，并可通过可复用的优化技能持续改进。在 20 个真实 RTL 设计上，Dr. RTL 相比商业综合工具平均改善 WNS/TNS 21%/17%，面积减少 6%。
正文 · 原文
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.
| Comments: | ASP-DAC'27 Invited Paper |
| Subjects: | Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR) |
| Cite as: | arXiv:2611.13713 [cs.AI] |
| (or arXiv:2611.13713v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13713 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Wenji Fang [view email]
[v1]
Tue, 10 Nov 2026 08:07:31 UTC (7,748 KB)
来源：arXiv cs.AI · arxiv.org