paper-with-me

홈 › Papers

Exploring the Agentic Frontier of Verilog Code Generation

2026-03-19 · Patrick Yubeaton, Siddharth Garg, Chinmay Hegde arxiv

Large language models (LLMs) have made rapid advancements in code generation for popular languages such as Python and C++. Many of these recent gains can be attributed to the use of ``agents'' that wrap domain-relevant tools alongside LLMs. Hardware design languages such as Verilog have also seen improved code generation in recent years, but the impact of agentic frameworks on Verilog code generation tasks remains unclear. In this work, we present the first systematic evaluation of agentic LLMs for Verilog generation, using the recently introduced CVDP benchmark. We also introduce several open-source hardware design agent harnesses, providing a model-agnostic baseline for future work. Through controlled experiments across frontier models, we study how structured prompting and tool design affect performance, analyze agent failure modes and tool usage patterns, compare open-source and closed-source models, and provide qualitative examples of successful and failed agent runs. Our results show that naive agentic wrapping around frontier models can degrade performance (relative to standard forward passes with optimized prompts), but that structured harnesses meaningfully match and in some cases exceed non-agentic baselines. We find that the performance gap between open and closed source models is driven by both higher crash rates and weaker tool output interpretation. Our exploration illuminates the path towards designing special-purpose agents for verilog generation in the future.

📄 PDF Abstract BibTeX arXiv:2603.19347

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

VeriMind: Agentic LLM for Automated Verilog Generation with a Novel Evaluation Metric

2025-03-15 · Bardia Nadimi, Ghali Omar Boutaib, Hao Zheng

Designing Verilog modules requires meticulous attention to correctness, efficiency, and adherence to design specifications. However, manually writing Verilog code remains a complex and time-consuming task that demands bo…

ARCCode GenerationText Generation

ReChisel: Effective Automatic Chisel Code Generation by LLM with Reflection

2025-05-26 · Juxin Niu, Xiangfeng Liu, Dan Niu, Xi Wang 외

Coding with hardware description languages (HDLs) such as Verilog is a time-intensive and laborious task. With the rapid advancement of large language models (LLMs), there is increasing interest in applying LLMs to assis…

Code Generation

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

Comprehensive Verilog Design Problems: A Next-Generation Benchmark Dataset for Evaluating Large Language Models and Agents on RTL Design and Verification

2025-06-17 · Nathaniel Pinckney, Chenhui Deng, Chia-Tung Ho, Yun-Da Tsai 외

We present the Comprehensive Verilog Design Problems (CVDP) benchmark, a new dataset and infrastructure to advance LLM and agent research in hardware design and verification. CVDP includes 783 problems across 13 task cat…

Code Generation

CoopetitiveV: Leveraging LLM-powered Coopetitive Multi-Agent Prompting for High-quality Verilog Generation

2024-12-15 · Zhendong Mi, Renming Zheng, Haowen Zhong, Yue Sun 외

Recent advances in agentic LLMs have demonstrated great capabilities in Verilog code generation. However, existing approaches either use LLM-assisted single-agent prompting or cooperation-only multi-agent learning, which…

Code GenerationPrompt Learning