ARSP: Automated Repair of Verilog Designs via Semantic Partitioning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yao, Bingkun, Wang, Ning, Liu, Xiangfeng, Du, Yuxin, Hu, Yuchen, Gao, Hong, Jiang, Zhe, Guan, Nan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909749326381056
author Yao, Bingkun
Wang, Ning
Liu, Xiangfeng
Du, Yuxin
Hu, Yuchen
Gao, Hong
Jiang, Zhe
Guan, Nan
author_facet Yao, Bingkun
Wang, Ning
Liu, Xiangfeng
Du, Yuxin
Hu, Yuchen
Gao, Hong
Jiang, Zhe
Guan, Nan
contents Debugging functional Verilog bugs consumes a significant portion of front-end design time. While Large Language Models (LLMs) have demonstrated great potential in mitigating this effort, existing LLM-based automated debugging methods underperform on industrial-scale modules. A major reason for this is bug signal dilution in long contexts, where a few bug-relevant tokens are overwhelmed by hundreds of unrelated lines, diffusing the model's attention. To address this issue, we introduce ARSP, a two-stage system that mitigates dilution via semantics-guided fragmentation. A Partition LLM splits a module into semantically tight fragments; a Repair LLM patches each fragment; edits are merged without altering unrelated logic. A synthetic data framework generates fragment-level training pairs spanning bug types, design styles, and scales to supervise both models. Experiments show that ARSP achieves 77.92% pass@1 and 83.88% pass@5, outperforming mainstream commercial LLMs including Claude-3.7 and SOTA automated Verilog debugging tools Strider and MEIC. Also, semantic partitioning improves pass@1 by 11.6% and pass@5 by 10.2% over whole-module debugging, validating the effectiveness of fragment-level scope reduction in LLM-based Verilog debugging.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16517
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ARSP: Automated Repair of Verilog Designs via Semantic Partitioning
Yao, Bingkun
Wang, Ning
Liu, Xiangfeng
Du, Yuxin
Hu, Yuchen
Gao, Hong
Jiang, Zhe
Guan, Nan
Software Engineering
Programming Languages
Debugging functional Verilog bugs consumes a significant portion of front-end design time. While Large Language Models (LLMs) have demonstrated great potential in mitigating this effort, existing LLM-based automated debugging methods underperform on industrial-scale modules. A major reason for this is bug signal dilution in long contexts, where a few bug-relevant tokens are overwhelmed by hundreds of unrelated lines, diffusing the model's attention. To address this issue, we introduce ARSP, a two-stage system that mitigates dilution via semantics-guided fragmentation. A Partition LLM splits a module into semantically tight fragments; a Repair LLM patches each fragment; edits are merged without altering unrelated logic. A synthetic data framework generates fragment-level training pairs spanning bug types, design styles, and scales to supervise both models. Experiments show that ARSP achieves 77.92% pass@1 and 83.88% pass@5, outperforming mainstream commercial LLMs including Claude-3.7 and SOTA automated Verilog debugging tools Strider and MEIC. Also, semantic partitioning improves pass@1 by 11.6% and pass@5 by 10.2% over whole-module debugging, validating the effectiveness of fragment-level scope reduction in LLM-based Verilog debugging.
title ARSP: Automated Repair of Verilog Designs via Semantic Partitioning
topic Software Engineering
Programming Languages
url https://arxiv.org/abs/2508.16517