arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.02895cs.ARcs.PL
收藏

SpecLoop:一种带有形式验证反馈循环的代理RTL到规范框架

SpecLoop: An Agentic RTL-to-Specification Framework with Formal Verification Feedback Loop

National Taiwan University(国立台湾大学);MediaTek Inc(联发科技股份有限公司)

Fu-Chieh Chang, Yu-Hsin Yang, Hung-Ming Huang, Yun-Chia Hsu, Yin-Yu Lin, Ming-Fang Tsai, Chun-Chih Yang, Pei-Yuan Wu

AI总结:

SpecLoop通过形式验证驱动的反馈循环提升RTL到规范生成的准确性和鲁棒性。

摘要:

RTL实现经常缺乏最新或一致的规范,这使得理解和维护以及验证成本高且容易出错。尽管先前的工作已经探索了使用大型语言模型(LLMs)从RTL生成规范,但确保生成的文档忠实于设计意图仍然是一个重大挑战。我们提出了SpecLoop,一种用于RTL到规范生成的代理框架,具有由形式验证驱动的迭代反馈循环。SpecLoop首先生成候选规范,然后从这些规范中重建RTL;它使用重建的RTL与原始设计之间的形式等价性检查工具来验证功能一致性。当发现不一致时,反例会被反馈以迭代地优化规范,直到证明等价性或无法进一步进展。在多个LLM和RTL基准上的实验表明,结合形式验证反馈显著提高了规范的正确性和鲁棒性,优于仅使用LLM的基线,证明了验证引导的规范生成的有效性。

英文摘要:

RTL implementations frequently lack up-to-date or consistent specifications, making comprehension, maintenance, and verification costly and error-prone. While prior work has explored generating specifications from RTL using large language models (LLMs), ensuring that the generated documents faithfully capture design intent remains a major challenge. We present SpecLoop, an agentic framework for RTL-to-specification generation with a formal-verification-driven iterative feedback loop. SpecLoop first generates candidate specifications and then reconstructs RTL from these specifications; it uses formal equivalence checking tools between the reconstructed RTL and the original design to validate functional consistency. When mismatches are detected, counterexamples are fed back to iteratively refine the specifications until equivalence is proven or no further progress can be made. Experiments across multiple LLMs and RTL benchmarks show that incorporating formal verification feedback substantially improves specification correctness and robustness over LLM-only baselines, demonstrating the effectiveness of verification-guided specification generation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑