A Multi-Agent Generative AI Framework for IC Module-Level Verification Automation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913964825247744 |
|---|---|
| author | Liu, Wenbo Hou, Forbes Zhang, Jon Liu, Hong Lei, Allen |
| author_facet | Liu, Wenbo Hou, Forbes Zhang, Jon Liu, Hong Lei, Allen |
| contents | As large language models demonstrate enormous potential in the field of Electronic Design Automation (EDA), generative AI-assisted chip design is attracting widespread attention from academia and industry. Although these technologies have made preliminary progress in tasks such as code generation, their application in chip verification -- a critical bottleneck in the chip development cycle -- remains at an exploratory stage. This paper proposes an innovative Multi-Agent Verification Framework (MAVF) aimed at addressing the limitations of current single-LLM approaches in complex verification tasks. Our framework builds an automated transformation system from design specifications to testbench through the collaborative work of multiple specialized agents, including specification parsing, verification strategy generation, and code implementation. Through verification experiments on multiple chip modules of varying complexity, results show that MAVF significantly outperforms traditional manual methods and single-dialogue generative AI approaches in verification document parsing and generation, as well as automated testbench generation. This research opens new directions for exploring generative AI applications in verification automation, potentially providing effective approaches to solving the most challenging bottleneck issues in chip design. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21694 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Multi-Agent Generative AI Framework for IC Module-Level Verification Automation Liu, Wenbo Hou, Forbes Zhang, Jon Liu, Hong Lei, Allen Hardware Architecture Artificial Intelligence B.5.2; I.2.11 As large language models demonstrate enormous potential in the field of Electronic Design Automation (EDA), generative AI-assisted chip design is attracting widespread attention from academia and industry. Although these technologies have made preliminary progress in tasks such as code generation, their application in chip verification -- a critical bottleneck in the chip development cycle -- remains at an exploratory stage. This paper proposes an innovative Multi-Agent Verification Framework (MAVF) aimed at addressing the limitations of current single-LLM approaches in complex verification tasks. Our framework builds an automated transformation system from design specifications to testbench through the collaborative work of multiple specialized agents, including specification parsing, verification strategy generation, and code implementation. Through verification experiments on multiple chip modules of varying complexity, results show that MAVF significantly outperforms traditional manual methods and single-dialogue generative AI approaches in verification document parsing and generation, as well as automated testbench generation. This research opens new directions for exploring generative AI applications in verification automation, potentially providing effective approaches to solving the most challenging bottleneck issues in chip design. |
| title | A Multi-Agent Generative AI Framework for IC Module-Level Verification Automation |
| topic | Hardware Architecture Artificial Intelligence B.5.2; I.2.11 |
| url | https://arxiv.org/abs/2507.21694 |