CorrectHDL: Agentic HDL Design with LLMs Leveraging High-Level Synthesis as Reference

• URL: http://arxiv.org/abs/2511.16395v1
• Date: Thu, 20 Nov 2025 14:13:38 GMT
• Title: CorrectHDL: Agentic HDL Design with LLMs Leveraging High-Level Synthesis as Reference
• Authors: Kangwei Xu, Grace Li Zhang, Ulf Schlichtmann, Bing Li,
• Abstract summary: Large Language Models (LLMs) have demonstrated remarkable potential in hardware front-end design using hardware description languages (HDLs)<n>Their inherent tendency toward hallucination often introduces functional errors into the generated HDL designs.<n>We propose the framework CorrectHDL that leverages high-level synthesis (HLS) results as functional references to correct potential errors.
• Score: 8.207258785260722
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Models (LLMs) have demonstrated remarkable potential in hardware front-end design using hardware description languages (HDLs). However, their inherent tendency toward hallucination often introduces functional errors into the generated HDL designs. To address this issue, we propose the framework CorrectHDL that leverages high-level synthesis (HLS) results as functional references to correct potential errors in LLM-generated HDL designs.The input to the proposed framework is a C/C++ program that specifies the target circuit's functionality. The program is provided to an LLM to directly generate an HDL design, whose syntax errors are repaired using a Retrieval-Augmented Generation (RAG) mechanism. The functional correctness of the LLM-generated circuit is iteratively improved by comparing its simulated behavior with an HLS reference design produced by conventional HLS tools, which ensures the functional correctness of the result but can lead to suboptimal area and power efficiency. Experimental results demonstrate that circuits generated by the proposed framework achieve significantly better area and power efficiency than conventional HLS designs and approach the quality of human-engineered circuits. Meanwhile, the correctness of the resulting HDL implementation is maintained, highlighting the effectiveness and potential of agentic HDL design leveraging the generative capabilities of LLMs and the rigor of traditional correctness-driven IC design flows.

Related papers

• Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models [48.83701310501069]
  Large Language Models (LLMs) offer a transformative approach to Neural Architecture Search (NAS)<n>We formulate the search as a sequence of conditional code generation tasks, where an LLM refines architectural specifications based on performance telemetry.<n>We generate a vast corpus of valid, shape-consistent architectures via Abstract Syntax Tree (AST) mutations.<n> Experimental results on CIFAR-100 validate the efficacy of this approach, demonstrating that the model yields statistically significant improvements in accuracy.
  arXiv  Detail & Related papers  (2026-01-13T13:00:30Z)
• MAHL: Multi-Agent LLM-Guided Hierarchical Chiplet Design with Adaptive Debugging [30.305211001929496]
  Large Language Models (LLMs) are promising to extend their abilities to 2.5D integration.<n>LLMs face challenges such as flatten design, high validation cost and imprecise parameter optimization.<n>We propose MAHL, a hierarchical LLM-based chiplet design generation framework.
  arXiv  Detail & Related papers  (2025-08-08T05:47:31Z)
• ReChisel: Effective Automatic Chisel Code Generation by LLM with Reflection [10.897328608123772]
  ReChisel is an agentic system designed to enhance the effectiveness of Chisel code generation.<n> Experiments demonstrate that ReChisel significantly improves the success rate of Chisel code generation.
  arXiv  Detail & Related papers  (2025-05-26T09:20:07Z)
• HDLCoRe: A Training-Free Framework for Mitigating Hallucinations in LLM-Generated HDL [8.078194378107936]
  HDLCoRe is a training-free framework that enhances large language models' HDL generation capabilities.<n>Our framework achieves superior performance on the RTLLM2.0 benchmark.
  arXiv  Detail & Related papers  (2025-03-18T07:09:39Z)
• Exploring Code Language Models for Automated HLS-based Hardware Generation: Benchmark, Infrastructure and Analysis [14.458529723566379]
  Large language models (LLMs) can be employed for programming languages such as Python and C++.<n>This paper explores leveraging LLMs to generate High-Level Synthesis (HLS)-based hardware design.
  arXiv  Detail & Related papers  (2025-02-19T17:53:59Z)
• HiVeGen -- Hierarchical LLM-based Verilog Generation for Scalable Chip Design [24.46771930751068]
  HiVeGen is a hierarchical Verilog generation framework that decomposes generation tasks into hierarchical submodules.<n> automatic Design Space Exploration (DSE) into hierarchy-aware prompt generation, introducing weight-based retrieval to enhance code reuse.<n>Real-time human-computer interaction to lower error-correction cost, significantly improving the quality of generated designs.
  arXiv  Detail & Related papers  (2024-12-06T19:37:53Z)
• Are LLMs Any Good for High-Level Synthesis? [1.3927943269211591]
  Large Language Models (LLMs) can streamline or replace the High-Level Synthesis (HLS) process. LLMs can understand natural language specifications and translate C code or natural language specifications. This study aims to illuminate the role of LLMs in HLS, identifying promising directions for optimized hardware design in applications such as AI acceleration, embedded systems, and high-performance computing.
  arXiv  Detail & Related papers  (2024-08-19T21:40:28Z)
• Directed Exploration in Reinforcement Learning from Linear Temporal Logic [59.707408697394534]
  Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning.<n>We show that the synthesized reward signal remains fundamentally sparse, making exploration challenging.<n>We show how better exploration can be achieved by further leveraging the specification and casting its corresponding Limit Deterministic B"uchi Automaton (LDBA) as a Markov reward process.
  arXiv  Detail & Related papers  (2024-08-18T14:25:44Z)
• Case2Code: Scalable Synthetic Data for Code Generation [105.89741089673575]
  Large Language Models (LLMs) have shown outstanding breakthroughs in code generation.<n>Recent work improves code LLMs by training on synthetic data generated by some powerful LLMs.<n>We propose a textbfCase2Code task by exploiting the expressiveness and correctness of programs.
  arXiv  Detail & Related papers  (2024-07-17T11:35:00Z)
• GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval [80.96706764868898]
  We present a new Low-light Image Enhancement (LLIE) network via Generative LAtent feature based codebook REtrieval (GLARE) We develop a generative Invertible Latent Normalizing Flow (I-LNF) module to align the LL feature distribution to NL latent representations, guaranteeing the correct code retrieval in the codebook. Experiments confirm the superior performance of GLARE on various benchmark datasets and real-world data.
  arXiv  Detail & Related papers  (2024-07-17T09:40:15Z)
• Classification-Based Automatic HDL Code Generation Using LLMs [9.630310313347657]
  Large language models (LLMs) have demonstrated the ability to generate hardware description language (HDL) code for digital circuits. LLMs suffer from the hallucination problem, which leads to the generation of incorrect HDL code or misunderstanding of specifications. We introduce a human-expert-inspired method to mitigate the hallucination of LLMs and improve the performance in HDL code generation.
  arXiv  Detail & Related papers  (2024-07-04T09:00:13Z)
• Q*: Improving Multi-step Reasoning for LLMs with Deliberative Planning [53.6472920229013]
  Large Language Models (LLMs) have demonstrated impressive capability in many natural language tasks. LLMs are prone to produce errors, hallucinations and inconsistent statements when performing multi-step reasoning. We introduce Q*, a framework for guiding LLMs decoding process with deliberative planning.
  arXiv  Detail & Related papers  (2024-06-20T13:08:09Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)
• StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback [58.20547418182074]
  We introduce StepCoder, a novel framework for code generation, consisting of two main components. CCCS addresses the exploration challenge by breaking the long sequences code generation task into a Curriculum of Code Completion Subtasks. FGO only optimize the model by masking the unexecuted code segments to provide Fine-Grained Optimization. Our method improves the ability to explore the output space and outperforms state-of-the-art approaches in corresponding benchmarks.
  arXiv  Detail & Related papers  (2024-02-02T13:14:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.