RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Model
The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Abstract
This paper presents RTLFixer, a novel framework enabling automatic syntax errors fixing for Verilog code with Large Language Models (LLMs). Despite LLM's promising capabilities, our analysis indicates that approximately 55% of errors in LLM-generated Verilog are syntax-related, leading to compilation failures. To tackle this issue, we introduce a novel debugging framework that employs Retrieval-Augmented Generation (RAG) and ReAct prompting, enabling LLMs to act as autonomous agents in interactively debugging the code with feedback. This framework demonstrates exceptional proficiency in resolving syntax errors, successfully correcting about 98.5% of compilation errors in our debugging dataset, comprising 212 erroneous implementations derived from the VerilogEval benchmark. Our method leads to 32.3% and 10.1% increase in pass@1 success rates in the VerilogEval-Machine and VerilogEval-Human benchmarks, respectively. The source code and benchmark are available at https://github.com/NVlabs/RTLFixer.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“It iteratively retrieves errors and paired solutions, and combines reasoning and action planning into prompts for LLMs.”
From Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024) · cites this paper as [247]
In the citing paper
“RTLFixer [247] leverages ReAct [132] to implement an agent fixing errors in Verilog codes.”
From Retrieval-Augmented Generation for AI-Generated Content: A Survey (2024) · cites this paper as [247]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025
Research works printed but not linked: 18
- Jason Blocklove et al. 2023. Chip-Chat: Challenges and Opportunities in Conversational Hardware Design. arXiv preprint arXiv:2305.13243 (2023). · DOI · Paper page
- Mark Chen et al. 2021. Evaluating large language models trained on code. arXiv preprint arXiv:2107.03374 (2021). · arXiv
- Xinyun Chen et al. 2023. Teaching large language models to self-debug. arXiv preprint arXiv:2304.05128 (2023). · arXiv
- Shuyang Jiang et al. 2023. SelfEvolve: A Code Evolution Framework via Large Language Models. arXiv preprint arXiv:2306.02907 (2023). · arXiv
- Patrick Lewis et al. 2021. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv:cs.CL/2005.11401
- Mingjie Liu et al. 2023. ChipNeMo: Domain-Adapted LLMs for Chip Design. arXiv:cs.CL/2311.00176
- Mingjie Liu et al. 2023. VerilogEval: Evaluating Large Language Models for Verilog Code Generation. arXiv preprint arXiv:2309.07544 (2023). · arXiv
- Shuai Lu et al. 2022. ReACC: A Retrieval-Augmented Code Completion Framework. arXiv:cs.SE/2203.07722
- Yao Lu, et al. 2023. RTLLM: An Open-Source Benchmark for Design RTL Generation with Large Language Model. arXiv preprint arXiv:2308.05345 (2023). · arXiv
- Suphakit Niwattanakul, et al. 2013. Using of Jaccard coefficient for keywords similarity. In Proceedings of the international multiconference of engineers and computer scientists, Vol. 1. 380--384.
- 10.1145/3380446.3430634 · DOI · Paper page
- Yujia Qin, et al. 2023. Toolllm: Facilitating large language models to master 16000+ real-world apis. arXiv preprint arXiv:2307.16789 (2023). · arXiv
- 10.1145/3068335 · DOI · Paper page
- Shailja Thakur et al. 2023. VeriGen: A Large Language Model for Verilog Code Generation. arXiv preprint arXiv:2308.00708 (2023). · arXiv
- Jason Wei et al. 2023. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. arXiv:cs.CL/2201.11903
- Stephen Williams et al. 2002. Icarus verilog: open-source verilog more than a year later. Linux Journal 2002, 99 (2002), 3.
- Shunyu Yao, et al. 2022. ReAct: Synergizing Reasoning and Acting in Language Models. In The Eleventh International Conference on Learning Representations.
- Fengji Zhang, et al. 2023. Repocoder: Repository-level code completion through iterative retrieval and generation. arXiv preprint arXiv:2303.12570 (2023). · arXiv
Cited by
A Survey on the Memory Mechanism of Large Language Model based Agents
Zhang, Z., Bo, X., Ma, C., Li, R., Chen, X., Dai, Q., Zhu, J., Dong, Z., & Wen, J.-R. (2024) · arXiv · doi:10.48550/arxiv.2404.13501 · Cited by 149
Retrieval-Augmented Generation for AI-Generated Content: A Survey
Zhao, P., Zhang, H., Yu, Q., Wang, Z., Geng, Y., Fu, F., Yang, L., Zhang, W., Jiang, J., & Cui, B. (2024) · arXiv · doi:10.48550/arxiv.2402.19473 · Cited by 240
KARMA: Augmenting Embodied AI Agents with Long-and-Short Term Memory Systems
Wang, Z., Yu, B., Zhao, J., Sun, W., Hou, S., Liang, S., Hu, X., Han, Y., & Gan, Y. (2025) · 2025 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra55743.2025.11128047 · Cited by 11
LLM-Assisted Circuit Verification: A Comprehensive Survey
Liu, H., Lu, Y., Wang, M., Yao, X., & Yu, B. (2026) · 2026 31st Asia and South Pacific Design Automation Conference (ASP-DAC) · doi:10.1109/asp-dac66049.2026.11420692
Metadata
- Authors
- Tsai, Y., Liu, M., & Ren, H.
- Affiliations
- NVIDIA, Taipei, Taipei, Taiwan
- NVIDIA Corporation, Austin, TX, United States
- Venue
- Proceedings of the 61st ACM/IEEE Design Automation Conference
- Publisher
- ACM
- Published
- 2024-06-23
- Pages
- 1-6
- Cited by
- 116
- References
- 1
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.