arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.10218cs.ARcs.LG
收藏

ACE-RTL:当代理上下文进化与专为RTL设计的LLM相遇

ACE-RTL: When Agentic Context Evolution Meets RTL-Specialized LLMs

Chenhui Deng, Zhongzhi Yu, Guan-Ting Liu, Nathaniel Pinckney, Brucek Khailany, Haoxing Ren

AI总结:

ACE-RTL结合代理上下文进化与专为RTL设计的LLM,通过生成器、反射器和协调器三部分提升RTL代码的正确性,实现41.02%的通过率提升。

摘要:

近期LLM的进步激发了将其应用于硬件设计自动化的兴趣,特别是在准确生成RTL代码方面。先前的工作遵循两条独立路径:(i)训练领域适应的RTL模型以内部化硬件语义,(ii)开发利用前沿通用LLM的代理系统,通过模拟反馈进行指导。然而,这两条路径具有互补的优势和劣势。在本文中,我们提出了ACE-RTL,通过代理上下文进化(ACE)统一了这两个方向。ACE-RTL集成了一个在大规模170万RTL样本上训练的专为RTL设计的LLM,以及一个前沿推理LLM,通过三个协同组件:生成器、反射器和协调器。这些组件通过迭代优化RTL代码以实现功能正确性。我们进一步分析了一种并行扩展策略,通过探索多样化的调试轨迹,将墙钟迭代次数减少到首次成功。在CVDP基准测试中,ACE-RTL在14个竞争基线上实现了高达41.02%的通过率提升。

英文摘要:

Recent advances in LLMs have sparked growing interest in applying them to hardware design automation, particularly for accurate RTL code generation. Prior efforts follow two largely independent paths: (i) training domain-adapted RTL models to internalize hardware semantics, (ii) developing agentic systems that leverage frontier generic LLMs guided by simulation feedback. However, these two paths exhibit complementary strengths and weaknesses. In this work, we present ACE-RTL that unifies both directions through Agentic Context Evolution (ACE). ACE-RTL integrates an RTL-specialized LLM, trained on a large-scale dataset of 1.7 million RTL samples, with a frontier reasoning LLM through three synergistic components: the generator, reflector, and coordinator. These components iteratively refine RTL code toward functional correctness. We further analyze a parallel scaling strategy that reduces wall-clock iterations to first success by exploring diverse debugging trajectories concurrently. On the CVDP benchmark, ACE-RTL achieves up to a 41.02% pass rate improvement over 14 competitive baselines.

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。

↑