VeriThoughts: Enabling Automated Verilog Code Generation using Reasoning and Formal Verification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yubeaton, Patrick, Nakkab, Andre, Xiao, Weihua, Collini, Luca, Karri, Ramesh, Hegde, Chinmay, Garg, Siddharth
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908662981722112
author Yubeaton, Patrick
Nakkab, Andre
Xiao, Weihua
Collini, Luca
Karri, Ramesh
Hegde, Chinmay
Garg, Siddharth
author_facet Yubeaton, Patrick
Nakkab, Andre
Xiao, Weihua
Collini, Luca
Karri, Ramesh
Hegde, Chinmay
Garg, Siddharth
contents This paper introduces VeriThoughts, a novel dataset designed for reasoning-based Verilog code generation. We establish a new benchmark framework grounded in formal verification methods to evaluate the quality and correctness of generated hardware descriptions. Additionally, we present a suite of specialized small-scale models optimized specifically for Verilog generation. Our work addresses the growing need for automated hardware design tools that can produce verifiably correct implementations from high-level specifications, potentially accelerating the hardware development process while maintaining rigorous correctness guarantees. Our code and data are available at \href{https://github.com/wilyub/VeriThoughts}{this URL}.
format Preprint
id arxiv_https___arxiv_org_abs_2505_20302
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VeriThoughts: Enabling Automated Verilog Code Generation using Reasoning and Formal Verification
Yubeaton, Patrick
Nakkab, Andre
Xiao, Weihua
Collini, Luca
Karri, Ramesh
Hegde, Chinmay
Garg, Siddharth
Programming Languages
Artificial Intelligence
Logic in Computer Science
This paper introduces VeriThoughts, a novel dataset designed for reasoning-based Verilog code generation. We establish a new benchmark framework grounded in formal verification methods to evaluate the quality and correctness of generated hardware descriptions. Additionally, we present a suite of specialized small-scale models optimized specifically for Verilog generation. Our work addresses the growing need for automated hardware design tools that can produce verifiably correct implementations from high-level specifications, potentially accelerating the hardware development process while maintaining rigorous correctness guarantees. Our code and data are available at \href{https://github.com/wilyub/VeriThoughts}{this URL}.
title VeriThoughts: Enabling Automated Verilog Code Generation using Reasoning and Formal Verification
topic Programming Languages
Artificial Intelligence
Logic in Computer Science
url https://arxiv.org/abs/2505.20302