EstRTL: Functional Estimation Guided RTL Code Generation

2026-05-31

AI Summary

Existing large language models often generate RTL code lacking functional correctness, rendering it unsuitable for practical hardware design. To address this limitation, this work proposes EstRTL, a framework that integrates generation, functional evaluation, and correction through a coordinated three-stage mechanism. Central to EstRTL is a functional estimation agent that guides the model toward producing functionally correct and interpretable RTL code by combining static functional scoring with readability constraints. The approach is compatible with various RTL-specialized large language models and achieves a 3.2%–9.0% improvement in functional correctness over general-purpose models, substantially enhancing the reliability and practicality of AI-generated hardware code.

Abstract

Optimizing register transfer level (RTL) code is of vital importance in hardware design. Large language models (LLMs) provide new methods for the automatic generation and optimization of RTL code, offering the potential to significantly accelerate the design process and reduce human effort. However, existing methods for generating RTL code often focus on model fine-tuning and the use of various expansion techniques to enhance the RTL code generation capabilities, lacking attention to the functional correctness. Ensuring that the generated RTL code not only compiles successfully but also behaves as intended in real hardware implementations remains a critical challenge. To address this issue, we propose EstRTL, an LLM-powered collaborative agent framework for RTL code generation based on static functional score estimation. EstRTL operates a three-stage paradigm: Generation, Estimation and Correction. During the stages, the functional estimation agent statically evaluates the generated code based on score and assessment results, and decides whether to output the code directly, return it for regeneration, or forward it to the code correction agent. This framework can be applied to various LLMs that designed for RTL code generation, further enhancing the correctness of the generated code. By providing quantitative scores and human-readable requirements comparisons, it improves the transparency of AI-assisted RTL code generation. Experiments show that EstRTL significantly improves the correctness of RTL code generation by generic LLM by 3.2\%-9.0\%, demonstrating the practical value of our system. The codes and experimental results are open-sourced at link: https://anonymous.4open.science/status/EstRTL-E200/.

Problem

• RTL code generation
• functional correctness
• hardware design
• large language models
• code correctness

Innovation

• RTL code generation
• functional correctness
• large language models
• static estimation
• collaborative agent framework