VeriMind: Agentic LLM for Automated Verilog Generation with a Novel Evaluation Metric

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nadimi, Bardia, Boutaib, Ghali Omar, Zheng, Hao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912330433953792
author Nadimi, Bardia
Boutaib, Ghali Omar
Zheng, Hao
author_facet Nadimi, Bardia
Boutaib, Ghali Omar
Zheng, Hao
contents Designing Verilog modules requires meticulous attention to correctness, efficiency, and adherence to design specifications. However, manually writing Verilog code remains a complex and time-consuming task that demands both expert knowledge and iterative refinement. Leveraging recent advancements in large language models (LLMs) and their structured text generation capabilities, we propose VeriMind, an agentic LLM framework for Verilog code generation that significantly automates and optimizes the synthesis process. Unlike traditional LLM-based code generators, VeriMind employs a structured reasoning approach: given a user-provided prompt describing design requirements, the system first formulates a detailed train of thought before the final Verilog code is generated. This multi-step methodology enhances interpretability, accuracy, and adaptability in hardware design. In addition, we introduce a novel evaluation metric-pass@ARC-which combines the conventional pass@k measure with Average Refinement Cycles (ARC) to capture both success rate and the efficiency of iterative refinement. Experimental results on diverse hardware design tasks demonstrated that our approach achieved up to $8.3\%$ improvement on pass@k metric and $8.1\%$ on pass@ARC metric. These findings underscore the transformative potential of agentic LLMs in automated hardware design, RTL development, and digital system synthesis.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16514
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VeriMind: Agentic LLM for Automated Verilog Generation with a Novel Evaluation Metric
Nadimi, Bardia
Boutaib, Ghali Omar
Zheng, Hao
Hardware Architecture
Artificial Intelligence
Machine Learning
Programming Languages
Designing Verilog modules requires meticulous attention to correctness, efficiency, and adherence to design specifications. However, manually writing Verilog code remains a complex and time-consuming task that demands both expert knowledge and iterative refinement. Leveraging recent advancements in large language models (LLMs) and their structured text generation capabilities, we propose VeriMind, an agentic LLM framework for Verilog code generation that significantly automates and optimizes the synthesis process. Unlike traditional LLM-based code generators, VeriMind employs a structured reasoning approach: given a user-provided prompt describing design requirements, the system first formulates a detailed train of thought before the final Verilog code is generated. This multi-step methodology enhances interpretability, accuracy, and adaptability in hardware design. In addition, we introduce a novel evaluation metric-pass@ARC-which combines the conventional pass@k measure with Average Refinement Cycles (ARC) to capture both success rate and the efficiency of iterative refinement. Experimental results on diverse hardware design tasks demonstrated that our approach achieved up to $8.3\%$ improvement on pass@k metric and $8.1\%$ on pass@ARC metric. These findings underscore the transformative potential of agentic LLMs in automated hardware design, RTL development, and digital system synthesis.
title VeriMind: Agentic LLM for Automated Verilog Generation with a Novel Evaluation Metric
topic Hardware Architecture
Artificial Intelligence
Machine Learning
Programming Languages
url https://arxiv.org/abs/2503.16514