VeriInteresting: An Empirical Study of Model Prompt Interactions in Verilog Code Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Collini, Luca, Hennesee, Andrew, Yubeaton, Patrick, Garg, Siddharth, Karri, Ramesh
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908956570419200
author Collini, Luca
Hennesee, Andrew
Yubeaton, Patrick
Garg, Siddharth
Karri, Ramesh
author_facet Collini, Luca
Hennesee, Andrew
Yubeaton, Patrick
Garg, Siddharth
Karri, Ramesh
contents Rapid advances in language models (LMs) have created new opportunities for automated code generation while complicating trade-offs between model characteristics and prompt design choices. In this work, we provide an empirical map of recent trends in LMs for Verilog code generation, focusing on interactions among model reasoning, specialization, and prompt engineering strategies. We evaluate a diverse set of small and large LMs, including general-purpose, reasoning, and domain-specific variants. Our experiments use a controlled factorial design spanning benchmark prompts, structured outputs, prompt rewriting, chain-of-thought reasoning, in-context learning, and evolutionary prompt optimization via Genetic-Pareto. Across two Verilog benchmarks, we identify patterns in how model classes respond to structured prompts and optimization, and we document which trends generalize across LMs and benchmarks versus those that are specific to particular model-prompt combinations.
format Preprint
id arxiv_https___arxiv_org_abs_2603_08715
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle VeriInteresting: An Empirical Study of Model Prompt Interactions in Verilog Code Generation
Collini, Luca
Hennesee, Andrew
Yubeaton, Patrick
Garg, Siddharth
Karri, Ramesh
Hardware Architecture
Computation and Language
Rapid advances in language models (LMs) have created new opportunities for automated code generation while complicating trade-offs between model characteristics and prompt design choices. In this work, we provide an empirical map of recent trends in LMs for Verilog code generation, focusing on interactions among model reasoning, specialization, and prompt engineering strategies. We evaluate a diverse set of small and large LMs, including general-purpose, reasoning, and domain-specific variants. Our experiments use a controlled factorial design spanning benchmark prompts, structured outputs, prompt rewriting, chain-of-thought reasoning, in-context learning, and evolutionary prompt optimization via Genetic-Pareto. Across two Verilog benchmarks, we identify patterns in how model classes respond to structured prompts and optimization, and we document which trends generalize across LMs and benchmarks versus those that are specific to particular model-prompt combinations.
title VeriInteresting: An Empirical Study of Model Prompt Interactions in Verilog Code Generation
topic Hardware Architecture
Computation and Language
url https://arxiv.org/abs/2603.08715