Agentic AI-based Coverage Closure for Formal Verification
arXiv:2603.03147v1 Announce Type: new Abstract: Coverage closure is a critical requirement in Integrated Chip (IC) development process and key metric for verification sign-off. However, traditional exhaustive approaches often fail to achieve full coverage within project timelines. This study presents an agentic AI-driven workflow that utilizes Large Language Model (LLM)-enabled Generative AI (GenAI) to automate coverage analysis for formal verification, identify coverage gaps, and generate the required formal properties. The framework accelerates verification efficiency by systematically addressing coverage holes. Benchmarking open-source and internal designs reveals a measurable increase in coverage metrics, with improvements correlated to the complexity of the design. Comparative analysis validates the effectiveness of this approach. These results highlight the potential of agentic AI-based techniques to improve formal verification productivity and support comprehensive coverage clo
arXiv:2603.03147v1 Announce Type: new Abstract: Coverage closure is a critical requirement in Integrated Chip (IC) development process and key metric for verification sign-off. However, traditional exhaustive approaches often fail to achieve full coverage within project timelines. This study presents an agentic AI-driven workflow that utilizes Large Language Model (LLM)-enabled Generative AI (GenAI) to automate coverage analysis for formal verification, identify coverage gaps, and generate the required formal properties. The framework accelerates verification efficiency by systematically addressing coverage holes. Benchmarking open-source and internal designs reveals a measurable increase in coverage metrics, with improvements correlated to the complexity of the design. Comparative analysis validates the effectiveness of this approach. These results highlight the potential of agentic AI-based techniques to improve formal verification productivity and support comprehensive coverage closure.
Executive Summary
This article introduces an innovative approach to coverage closure in Integrated Chip development using agentic AI-driven workflows. By leveraging Large Language Model-enabled Generative AI, the framework automates coverage analysis, identifies gaps, and generates formal properties, resulting in improved verification efficiency and increased coverage metrics. Benchmarking results demonstrate the effectiveness of this approach, highlighting its potential to enhance formal verification productivity and support comprehensive coverage closure.
Key Points
- ▸ Agentic AI-driven workflow for coverage closure
- ▸ Utilization of Large Language Model-enabled Generative AI
- ▸ Improved verification efficiency and coverage metrics
Merits
Efficient Coverage Closure
The proposed framework accelerates verification efficiency by systematically addressing coverage holes, leading to improved coverage metrics.
Demerits
Complexity and Scalability
The approach may face challenges in terms of complexity and scalability, particularly for large and complex designs, which could impact its effectiveness.
Expert Commentary
The integration of agentic AI-driven workflows in coverage closure marks a significant advancement in the field of formal verification. By automating coverage analysis and generating formal properties, this approach has the potential to revolutionize the IC development process. However, further research is needed to address the challenges of complexity and scalability, and to fully realize the benefits of this innovative approach. The article's findings have important implications for the industry, highlighting the need for continued investment in AI-driven technologies to enhance formal verification productivity and support comprehensive coverage closure.
Recommendations
- ✓ Further research on scalability and complexity
- ✓ Industry-wide adoption and integration of agentic AI-driven workflows in formal verification processes