arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.03175cs.AI
收藏

Saarthi 用于 AGI:迈向形式验证的领域特定通用智能

Saarthi for AGI: Towards Domain-Specific General Intelligence for Formal Verification

1 Infineon Technologies India Private Limited, India 2 Infineon Technologies Dresden AG \& Co. KG, Germany 3 Infineon Technologies Vietnam Company Ltd., Vietnam

Aman Kumar, Deepak Narayan Gadde, Luu Danh Minh, Vaisakh Naduvodi Viswambharan, Keerthan Kopparam Radhakrishna, Sivaram Pothireddypalli

AI总结:

Saarthi 通过结构化规则书和 RAG 技术提升形式验证的准确性和效率

摘要:

Saarthi 是一个基于多智能体协作的 AI 框架,用于执行端到端的形式验证。尽管该框架提供了从规范到覆盖率关闭的完整流程,其效率约为 40%,但仍需解决一系列挑战以使其更加稳健和可靠。人工通用智能(AGI)仍然是一个遥远的目标,而当前基于大语言模型(LLM)的智能体容易产生幻觉并犯错,尤其是在处理复杂任务如形式验证时。然而,通过适当的增强和改进,我们认为 Saarthi 可以成为实现形式验证领域特定通用智能的重要一步。特别是对于需要短期、短上下文(STSC)能力的问题,如形式验证,Saarthi 可以成为协助验证工程师工作的强大工具。在本文中,我们提出了两个关键的增强措施:(1)结构化的规则书和规范语法,以提高 SystemVerilog 断言(SVA)生成的准确性和可控性;(2)集成先进的检索增强生成(RAG)技术,如 GraphRAG,以使智能体能够访问技术知识和最佳实践,从而进行迭代细化和改进输出。我们还通过 NVIDIA 的 CVDP 评估基准中的具有挑战性的测试用例对整个 Saarthi 框架进行了基准测试,这些测试用例针对形式验证。我们的基准测试结果突出显示,生成断言的准确性提高了 70%,达到覆盖率关闭所需的迭代次数减少了 50%。

英文摘要:

Saarthi is an agentic AI framework that uses multi-agent collaboration to perform end-to-end formal verification. Even though the framework provides a complete flow from specification to coverage closure, with around 40% efficacy, there are several challenges that need to be addressed to make it more robust and reliable. Artificial General Intelligence (AGI) is still a distant goal, and current Large Language Model (LLM)-based agents are prone to hallucinations and making mistakes, especially when dealing with complex tasks such as formal verification. However, with the right enhancements and improvements, we believe that Saarthi can be a significant step towards achieving domain-specific general intelligence for formal verification. Especially for problems that require Short Term, Short Context (STSC) capabilities, such as formal verification, Saarthi can be a powerful tool to assist verification engineers in their work. In this paper, we present two key enhancements to the Saarthi framework: (1) a structured rulebook and specification grammar to improve the accuracy and controllability of SystemVerilog Assertion (SVA) generation, and (2) integration of advanced Retrieval Augmented Generation (RAG) techniques, such as GraphRAG, to provide agents with access to technical knowledge and best practices for iterative refinement and improvement of outputs. We also benchmark these enhancements for the overall Saarthi framework using challenging test cases from NVIDIA's CVDP benchmark targeting formal verification. Our benchmark results stand out with a 70% improvement in the accuracy of generated assertions, and a 50% reduction in the number of iterations required to achieve coverage closure.

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。

↑