# HLSDebugger: Identification and Correction of Logic Bugs in HLS Code with LLM Solutions

arXiv: https://arxiv.org/abs/2507.21485 · HTML: https://mlsanity.com/paper/2507.21485/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 29 Jul 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step](https://mlsanity.com/paper/2402.16906/) (2024)
- [RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Models](https://mlsanity.com/paper/2311.16543/) (2023)
- [RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solution](https://mlsanity.com/paper/2312.08617/) (2023)
- [AgentFL: Scaling LLM-based Fault Localization to Project-Level Context](https://mlsanity.com/paper/2403.16362/) (2024)
- [MG-Verilog: Multi-grained Dataset Towards Enhanced LLM-assisted Verilog Generation](https://mlsanity.com/paper/2407.01910/) (2024)
- [HDLdebugger: Streamlining HDL debugging with Large Language Models](https://mlsanity.com/paper/2403.11671/) (2024)
- [HLSPilot: LLM-based High-Level Synthesis](https://mlsanity.com/paper/2408.06810/) (2024)
- [LLM4SecHW: Leveraging Domain Specific Large Language Model for Hardware Debugging](https://mlsanity.com/paper/2401.16448/) (2024)
- [VerilogReader: LLM-Aided Hardware Test Generation](https://mlsanity.com/paper/2406.04373/) (2024)
- [CREF: An LLM-based Conversational Software Repair Framework for Programming Tutors](https://mlsanity.com/paper/2406.13972/) (2024)
- [C2HLSC: Can LLMs Bridge the Software-to-Hardware Design Gap?](https://mlsanity.com/paper/2406.09233/) (2024)
- [LLM-aided explanations of EDA synthesis errors](https://mlsanity.com/paper/2404.07235/) (2024)

## Built on by (most cited first, 5 of 5)

- [FVDebug: An LLM-Driven Debugging Assistant for Automated Root Cause Analysis of Formal Verification Failures](https://mlsanity.com/paper/2510.15906/) (2025)
- [R3A: Reliable RTL Repair Framework with Multi-Agent Fault Localization and Stochastic Tree-of-Thoughts Patch Generation](https://mlsanity.com/paper/2511.20090/) (2025)
- [QiMeng-PRepair: Precise Code Repair via Edit-Aware Reward Optimization](https://mlsanity.com/paper/2604.05963/) (2026)
- [Evidence-Driven LLM Agent for C-to-Synthesizable-C Conversion and Verification](https://mlsanity.com/paper/2606.28409/) (2026)
- [An Executable Benchmark for LLM-Based HLS Repair:Design Complexity and Repair Underconstraint](https://mlsanity.com/paper/2610.03971/) (2026)

## Abstract (arXiv)

High-level synthesis (HLS) accelerates hardware design by enabling the automatic translation of high-level descriptions into efficient hardware implementations. However, debugging HLS code is a challenging and labor-intensive task, especially for novice circuit designers or software engineers without sufficient hardware domain knowledge. The recent emergence of Large Language Models (LLMs) is promising in automating the HLS debugging process. Despite the great potential, three key challenges persist when applying LLMs to HLS logic debugging: 1) High-quality circuit data for training LLMs is scarce, posing a significant challenge. 2) Debugging logic bugs in hardware is inherently more complex than identifying software bugs with existing golden test cases. 3) The absence of reliable test cases requires multi-tasking solutions, performing both bug identification and correction. complicates the multi-tasking required for effective HLS debugging. In this work, we propose a customized solution named HLSDebugger to address the challenges. HLSDebugger first generates and releases a large labeled dataset with 300K data samples, targeting HLS logic bugs. The HLSDebugger model adopts an encoder-decoder structure, performing bug location identification, bug type prediction, and bug correction with the same model. HLSDebugger significantly outperforms advanced LLMs like GPT-4 in bug identification and by more than 3x in bug correction. It makes a substantial advancement in the exploration of automated debugging of HLS code.