VeriMoA: A Mixture-of-Agents Framework for Spec-to-HDL Generation

TL;DR

VeriMoA introduces a training-free, multi-agent framework with quality-guided caching and multi-path generation to improve HDL synthesis from specifications, outperforming existing methods.

Contribution

The paper presents VeriMoA, a novel mixture-of-agents approach with quality-based caching and multi-path strategies, enhancing HDL generation without additional training.

Findings

Achieves 15-30% improvements in Pass@1 on benchmarks.

Enables smaller models to match larger models' performance.

Reduces reliance on costly training for HDL synthesis.

Abstract

Automation of Register Transfer Level (RTL) design can help developers meet increasing computational demands. Large Language Models (LLMs) show promise for Hardware Description Language (HDL) generation, but face challenges due to limited parametric knowledge and domain-specific constraints. While prompt engineering and fine-tuning have limitations in knowledge coverage and training costs, multi-agent architectures offer a training-free paradigm to enhance reasoning through collaborative generation. However, current multi-agent approaches suffer from two critical deficiencies: susceptibility to noise propagation and constrained reasoning space exploration. We propose VeriMoA, a training-free mixture-of-agents (MoA) framework with two synergistic innovations. First, a quality-guided caching mechanism to maintain all intermediate HDL outputs and enables quality-based ranking and selection across the entire generation process, encouraging knowledge accumulation over layers of reasoning. Second, a multi-path generation strategy that leverages C++ and Python as intermediate representations, decomposing specification-to-HDL translation into two-stage processes that exploit LLM fluency in high-resource languages while promoting solution diversity. Comprehensive experiments on VerilogEval 2.0 and RTLLM 2.0 benchmarks demonstrate that VeriMoA achieves 15--30% improvements in Pass@1 across diverse LLM backbones, especially enabling smaller models to match larger models and fine-tuned alternatives without requiring costly training.