ChatSVA: Bridging SVA Generation for Hardware Verification via Task-Specific LLMs

2026-04-03

AI Summary

This work addresses the inefficiency and error-proneness of manually writing SystemVerilog Assertions (SVA) and the inadequacy of general-purpose large language models (LLMs) due to insufficient domain-specific data and limited functional accuracy. To overcome these limitations, the authors propose a specialized multi-agent LLM framework tailored for hardware verification. Leveraging the AgentBridge platform, the framework generates high-fidelity training data, enabling end-to-end SVA synthesis under extremely low-data regimes. By integrating task-specific modeling, multi-agent collaboration, and a high-purity data generation mechanism, the approach achieves a 98.66% syntactic pass rate and a 96.12% functional pass rate across 24 RTL designs, producing an average of 139.5 SVAs per design. It attains a functional coverage of 82.50%, improving functional correctness by 33.3 percentage points and surpassing the current state-of-the-art in coverage by a factor of 11.

Abstract

Functional verification consumes over 50% of the IC development lifecycle, where SystemVerilog Assertions (SVAs) are indispensable for formal property verification and enhanced simulation-based debugging. However, manual SVA authoring is labor-intensive and error-prone. While Large Language Models (LLMs) show promise, their direct deployment is hindered by low functional accuracy and a severe scarcity of domain-specific data. To address these challenges, we introduce ChatSVA, an end-to-end SVA generation system built upon a multi-agent framework. At its core, the AgentBridge platform enables this multi-agent approach by systematically generating high-purity datasets, overcoming the data scarcity inherent to few-shot scenarios. Evaluated on 24 RTL designs, ChatSVA achieves 98.66% syntax and 96.12% functional pass rates, generating 139.5 SVAs per design with 82.50% function coverage. This represents a 33.3 percentage point improvement in functional correctness and an over 11x enhancement in function coverage compared to the previous state-of-the-art (SOTA). ChatSVA not only sets a new SOTA in automated SVA generation but also establishes a robust framework for solving long-chain reasoning problems in few-shot, domain-specific scenarios. An online service has been publicly released at https://www.nctieda.com/CHATDV.html.

Problem

• SystemVerilog Assertions
• Hardware Verification
• Large Language Models
• Functional Verification
• Domain-Specific Data Scarcity

Innovation

• SVA generation
• multi-agent LLMs
• hardware verification
• few-shot learning
• domain-specific data synthesis