Sep 2026· Coins· pp. 1-6· 0 citations· 43 references
TL;DR
A reliability-oriented framework for LLM-assisted verification artifact generation in EDA is proposed, integrating contextual grounding, structured generation, and verification-aware feedback to improve artifact quality across multiple abstraction levels.
Abstract
Large Language Models (LLMs) are increasingly being explored for design and verification tasks in Electronic Design Automation (EDA), including the generation of assertions, test scenarios, coverage-driven methodologies, and other verification artifacts. While early results are promising, practical adoption remains limited by concerns over reliability, semantic correctness, and the overall usefulness of generated outputs within real verification flows. This paper proposes a reliability-oriented framework for LLM-assisted verification artifact generation in EDA, integrating contextual grounding, structured generation, and verification-aware feedback to improve artifact quality across multiple abstraction levels. The two case studies demonstrate that assertion quality can vary substantially across modules, reinforcing the need for systematic quality assessment of LLM-generated assertions.
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...
Requirements specification is a pivotal activity in software development. The use of structured templates for specifying requirements can improve their clarity, consistency, and analyzability, which is particularly important in safety-critical domains such as avionics to support verification and certification activitie...
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.· arXiv.org· 0 citations
Large language model (LLM) features are difficult to predict upfront. Their useful behavior, failure modes, and acceptable boundaries often become visible only through situated interaction. This Industry Experience paper reports a stakeholder-led quality assurance process used in the development of an LLM-enabled websi...
Leevi Vahvelainen, Prompat Amy Järvisalo· Adjunct Proceedings of the 1...· 0 citations
BRIDGE is presented, a structured prompting framework that decomposes verification into three interconnected domains: Code (implementations), Specifications (formal intent), and Theorem State-ments (constructive correctness claims), and elicits domain-specific intermediate reasoning to connect them.
Robert Joseph George, Carson Eisenach, Udaya Ghai et al.· 0 citations
The Provable Representation Of Original Functionality (PROOF) is introduced, which manages codebases indirectly via structured specifications via structured specifications to enable full-lifecycle codebase management strictly through these specifications.
XinHao Zhang, Jing-Jie Lu, Kun-Peng Liu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.