Skip to content

LLM-enabled Behavior Driven Development Workflow for Formally Verified Hardware Designs

Sep 2026 · arXiv.org · Vol abs/2609.15318 · 0 citations · 44 references
Computer Science

TL;DR

This work proposes an integrated view on the use of LLMs for EDA and establishes an LLM-enabled behavior driven hardware development workflow, introducing and defining Formal Verification Gherkin Scenarios (FV Gherkin Scenarios), unlocking CNL specifications as the foundation for formally verified hardware designs via Formal Property Verification (FPV).

Abstract

Recently, the use of Large Language Models (LLMs) for different tasks in the Electronic Design Automation (EDA) life-cycle has been studied extensively, but an integrated view is lacking. Specifications are the foundation of this life-cycle, but they suffer from ambiguity when written in natural language, which especially affects the quality of LLM output. Formal specifications mitigate these ambiguities, but they come with their own challenges. On the other hand, Controlled Natural Language (CNL) specifications can serve as a middle-ground, reducing ambiguity while retaining interpretability. In this work, we propose an integrated view on the use of LLMs for EDA and establish an LLM-enabled behavior driven hardware development workflow. We introduce and define Formal Verification Gherkin Scenarios (FV Gherkin Scenarios), unlocking CNL specifications as the foundation for formally verified hardware designs via Formal Property Verification (FPV). Experimental evaluation shows that our workflow is able to outperform other established LLM-based methods by 2.48x in functional correctness of generated Register Transfer Level (RTL) designs and by 2.54x in formal coverage of generated assertions for FPV.

View source

Similar papers

Open access Sep 2026

From Formal Specifications to Simulations: Generating Executable Hardware Models for Early Validation

This work presents a model-driven code generator transforming static USF specifications into executable software simulations that abstract cycle-accurate timing and helps shorten validation cycles, ultimately reducing the risk of costly design flaws.

Robert Kunzelmann, Raphael Kunz, Stephanie Ecker et al. · 0 citations

Path2Spec: Path-Aware Specification Generation via Large Language Models

This work introduces Path2Spec, a divide-and-conquer framework that leverages LLMs to extract all execution paths from an input program, generates path-specific specifications for each, and merges them into a comprehensive overall specification.

Dan Huang, Zhensu Sun, Hui-Hui Huang et al. · 0 citations
Open access 2025

INTEGRATION OF LOGIC-ORIENTED VERIFICATION WITH LARGE LANGUAGE MODELS INTO SOFTWARE DEVELOPMENT

Experimental evaluation shows that increasing the proportion of successful verifications requires additional model training, a broader context, and the integration of mutation and candidate selection operations, while practical limitations of the proposed hybrid approach when using small-class models are identified.

P. Mel'nikov, Andrey Tyugashev · 0 citations

E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch

E2E-SWE is introduced, a benchmark for evaluating whether coding agents can build complete, functional software repositories end to end and finds substantial variation in end-to-end repository generation ability, providing strong model differentiation while leaving considerable headroom for future progress.

Hantian Ding, Chloe Bi, Jia-Cheng Zhu et al. · 0 citations
Book Open access Oct 2026

Beyond Single-run Correctness: Nondeterminism-aware Evaluation of LLM-based Model Transformations

Model transformation is a core model-driven engineering (MDE) operation in which reproducibility is expected: under fixed metamodels, source model, and transformation rules, a deterministic engine should produce a stable target model. Large Language Models (LLMs) are increasingly explored for MDE tasks, but evaluations...

Riccardo Rubei, Alessio Bucaioni, A. Di Salle · 0 citations
Review Open access Sep 2026

State space-based methods for validating model transformations in model checkers

Formal methods, including model checking, are rapidly gaining importance, especially in safety-critical domains like aerospace and automotive. Consequently, the systems to be verified are growing more complex and are described in diverse design languages, often expressive and ambiguous. However, model checkers oper...

Zsófia Ádám, Z. Micskei · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.