MAGE: A Multi-Agent Engine for Automated RTL Code Generation
Authors:
Top Cited Papers
- 22 June 2025
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Abstract
The automatic generation of RTL code (e.g., Verilog) through natural language instructions has emerged as a promising direction with the advancement of large language models (LLMs). However, producing RTL code that is both syntactically and functionally correct remains a significant challenge. Existing single-LLM-agent approaches face substantial limitations because they must navigate between various programming languages and handle intricate generation, verification, and modification tasks. To address these challenges, this paper introduces MAGE, the first open-source1 multi-agent AI system designed for robust and accurate Verilog RTL code generation. We propose a novel high-temperature RTL candidate sampling and debugging system that effectively explores the space of code candidates and significantly improves the quality of the candidates. Furthermore, we design a novel Verilog-state checkpoint checking mechanism that enables early detection of functional errors and delivers precise feedback for targeted fixes, significantly enhancing the functional correctness of the generated RTL code. MAGE achieves a 95.7% rate of syntactic and functional correctness code generation on VerilogEval-Human v2 benchmark, surpassing the state-of-the-art Claude-3.5-sonnet by 23.3%, demonstrating a robust and reliable approach for AIdriven RTL design workflows.1MAGE is open-sourced at https://github.com/stable-lab/ MAGE-A-Multi-Agent-Engine-for-Automated-RTL-Code-GenerationKeywords
All Related Versions
This publication has 18 references indexed in Scilit:
- ITERTL: An Iterative Framework for Fine-tuning LLMs for RTL Code Generation2025
- AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs2024
- RTLCoder: Fully Open-Source and Efficient LLM-Assisted RTL Code Generation TechniqueIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2024
- RTL-Repair: Fast Symbolic Repair of Hardware Design Code2024
- On Hardware Security Bug Code Fixes by Prompting Large Language ModelsIEEE Transactions on Information Forensics and Security, 2024
- RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Model2024
- Invited Paper: VerilogEval: Evaluating Large Language Models for Verilog Code Generation2023
- DAVE: Deriving Automatically Verilog from English2020
- A Survey and Evaluation of FPGA High-Level Synthesis ToolsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2015
- C-based SoC design flow and EDA tools: an ASIC and system vendor perspectiveIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2000