paper-with-me

홈 › Papers

HAVEN: Hybrid Automated Verification ENgine for UVM Testbench Synthesis with LLMs

2026-04-30 · Chang-Chih Meng, Yu-Ren Lu, Guan-Yu Lin, Tsung Tai Yeh, Kai-Chiang Wu, I-Chen Wu arxiv

Integrated Circuit (IC) verification consumes nearly 70% of the IC development cycle, and recent research leverages Large Language Models (LLMs) to automatically generate testbenches and reduce verification overhead. However, LLMs have difficulty generating testbenches correctly. Unlike high-level programming languages, Hardware Description Languages (HDLs) are extremely rare in LLMs training data, leading LLMs to produce incorrect code. To overcome challenges when using LLMs to generate Universal Verification Methodology (UVM) testbenches and sequences, wepropose HAVEN (Hybrid Automated Verification ENgine) to prevent LLMs from writing HDL directly. For UVM testbench generation, HAVEN utilizes LLM agents to analyze design specifications to produce a structured architectural plan. The HAVEN Template Engine then combines with predefined and protocol-specific templates to generate all UVM components with correct bus-handshake timing. For UVM sequence generation, HAVEN introduces a Protocol-Aware Sequence Domain-Specific Language (DSL) that decomposes sequences into fine-grained step types. A set of predefined DSL patterns first establishes sequences that achieve a high coverage rate without LLM involvement. HAVEN continues to improve the coverage rate by iteratively leveraging LLM agents to analyze coverage gap reports and compose additional targeted DSL sequences. Unlike previous works, HAVEN is the first system that utilizes pre-defined, protocol-specific Jinja2 templates to generate all UVM components and UVM sequences using our proposed Protocol-Aware DSL and rule-based code generator. Our experimental results on 19 open-source IP designs spanning three interface protocols (Direct, Wishbone, AXI4-Lite) show that HAVEN achieves 100% compilation success, 90.6% code coverage, and 87.9% functional coverage on average, and is SOTA among LLM-assisted testbench generation systems.

📄 PDF Abstract BibTeX arXiv:2604.27643

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Structured Testbench Generation for LLM-Driven HDL Design and Verification-Oriented Data Curation

2026-06-11 · En-Ming Huang, Yu-Hung Kao, Ren-Hao Deng, Wei-Po Hsin 외 arxiv

Automated testbench generation has become a critical bottleneck in large language model (LLM)-driven Register Transfer Level (RTL) workflows, where large numbers of candidate designs must be verified rapidly and reliably…

Exploring LLM-based Verilog Code Generation with Data-Efficient Fine-Tuning and Testbench Automation

2026-04-16 · Mu-Chi Chen, Po-Hsuan Huang, Yu-Hung Kao, Yen-Fu Liu 외 arxiv

Recent advances in large language models have improved code generation, but their use in hardware description languages is still limited. Moreover, training data and testbenches for these models are often scarce. This pa…

Code Generation

PRO-V: An Efficient Program Generation Multi-Agent System for Automatic RTL Verification

2025-06-13 · Yujie Zhao, Zhijing Wu, Hejia Zhang, Zhongming Yu 외

LLM-assisted hardware verification is gaining substantial attention due to its potential to significantly reduce the cost and effort of crafting effective testbenches. It also serves as a critical enabler for LLM-aided e…

Code GenerationIn-Context Learning

A Multi-Agent Generative AI Framework for IC Module-Level Verification Automation

2025-07-29 · Wenbo Liu, Forbes Hou, Jon Zhang, Hong Liu 외 arxiv

As large language models demonstrate enormous potential in the field of Electronic Design Automation (EDA), generative AI-assisted chip design is attracting widespread attention from academia and industry. Although these…

Code Generation

Insights from Verification: Training a Verilog Generation LLM with Reinforcement Learning with Testbench Feedback

2025-04-22 · Ning Wang, Bingkun Yao, Jie zhou, Yuchen Hu 외

Large language models (LLMs) have shown strong performance in Verilog generation from natural language description. However, ensuring the functional correctness of the generated code remains a significant challenge. This…

Code GenerationHallucinationReinforcement Learning (RL)