Spec2Cov: An Agentic Framework for Code Coverage Closure of Digital Hardware Designs

2026-04-16

AI Summary

This work addresses the inefficiency and high cost of manual effort in achieving coverage convergence during hardware verification. The authors propose an intelligent agent framework that, for the first time, deeply integrates large language models (LLMs) with hardware simulators to enable fully automated, closed-loop coverage-driven verification without requiring LLM fine-tuning. The framework automatically parses design specifications, generates test stimuli, handles errors, and iteratively optimizes coverage by synergistically combining LLMs, constrained-random testing, coverage analysis, and agent-based workflows. Evaluated across 26 designs of varying complexity, the approach achieves 100% coverage on simple designs and up to 49% on complex ones, demonstrating a significant advance in verification automation.

Technology Category

• Machine Learning: Hardware-aware ML
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Hardware verification is one of the most challenging stages of the hardware design process, requiring significant time and resources to ensure a design is fully validated and production-ready. Verification teams aim to maximize design coverage while ensuring correct behavior and alignment with the specification. Coverage closure, which relies on iterative constrained-random and directed testing, is still largely manual and therefore slow and labor-intensive. Recent advances show that the code generation capabilities of Large Language Models (LLMs) can be integrated with external tools to build agentic workflows that autonomously perform hardware design and verification tasks. In this work, we introduce Spec2Cov, an agentic framework that automatically and iteratively generates test stimulus directly from design specifications to accelerate coverage closure. Spec2Cov coordinates interactions between an LLM and a hardware simulator, managing compilation and simulation errors, parsing coverage reports, and feeding results back to the model for refinement. We present features that improve Spec2Cov's effectiveness without additional fine-tuning and evaluate their impact. Across 26 designs of varying size and complexity, including problems from the CVDP benchmark suite, Spec2Cov demonstrates promising performance, achieving 100% coverage on simpler designs and up to 49% on more complex designs.

Problem

• hardware verification
• coverage closure
• test stimulus generation
• design specification
• code coverage

Innovation

• agentic framework
• code coverage closure
• Large Language Models
• hardware verification
• test stimulus generation