Faver: Boosting LLM-based RTL Generation with Function Abstracted Verifiable Middleware

2025-10-09 · Jianan Mu, Mingyu Shi, Yining Wang, Tianmeng Yang, Bin Sun, Xing Hu, Jing Ye, Huawei Li arxiv

LLM-based RTL generation is an interesting research direction, as it holds the potential to liberate the least automated stage in the current chip design. However, due to the substantial semantic gap between high-level specifications and RTL, coupled with limited training data, existing models struggle with generation accuracy. Drawing on human experience, design with verification helps improving accuracy. However, as the RTL testbench data are even more scarce, it is not friendly for LLMs. Although LLMs excel at higher-level languages like Python/C, they have a huge semantic gap from RTL. When implementing the same functionality, Python/C code and hardware code differ significantly in the spatiotemporal granularity, requiring the LLM not only to consider high-level functional semantics but also to ensure the low-level details align with the circuit code. It is not an easy task. In this paper, we propose a function abstracted verifiable middleware (Faver) that streamlines RTL verification in LLM-based workflows. By mixing LLM-friendly code structures with a rule-based template, Faver decouples the details of circuit verification, allowing the LLM to focus on the functionality itself. In our experiments on the SFT model and open-source models, Faver improved the model's generation accuracy by up to 14%.

📄 PDF Abstract BibTeX arXiv:2510.08664

Code (0)

등록된 구현이 없습니다.

FAVER: Blind Quality Prediction of Variable Frame Rate Videos

2022-01-05 · Qi Zheng, Zhengzhong Tu, Pavan C. Madhusudana, Xiaoyang Zeng 외

Video quality assessment (VQA) remains an important and challenging problem that affects many applications at the widest scales. Recent advances in mobile devices and cloud computing techniques have made it possible to c…

Cloud Computing Video Quality Assessment Visual Question Answering (VQA)

Verification of Bit-Flip Attacks against Quantized Neural Networks

2025-02-22 · Yedi Zhang, Lei Huang, Pengfei Gao, Fu Song 외

In the rapidly evolving landscape of neural network security, the resilience of neural networks against bit-flip attacks (i.e., an attacker maliciously flips an extremely small amount of bits within its parameter storage…

Neural Network Security Quantization

Generation of Policy-Level Explanations for Reinforcement Learning

2019-05-28 · Nicholay Topin, Manuela Veloso

Though reinforcement learning has greatly benefited from the incorporation of neural networks, the inability to verify the correctness of such systems limits their use. Current work in explainable deep learning focuses o…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

RTLSeek: Boosting the LLM-Based RTL Generation with Multi-Stage Diversity-Oriented Reinforcement Learning

2026-03-29 · Xinyu Zhang, Zhiteng Chao, Yonghao Wang, Bin Sun 외 arxiv

Register Transfer Level (RTL) design translates high-level specifications into hardware using HDLs such as Verilog. Although LLM-based RTL generation is promising, the scarcity of functionally verifiable high-quality dat…

Reinforcement Learning

Reward Machines for Cooperative Multi-Agent Reinforcement Learning

2020-07-03 · Cyrus Neary, Zhe Xu, Bo Wu, Ufuk Topcu

In cooperative multi-agent reinforcement learning, a collection of agents learns to interact in a shared environment to achieve a common goal. We propose the use of reward machines (RM) -- Mealy machines used as structur…

Multi-agent Reinforcement Learning Q-Learning reinforcement-learning Reinforcement Learning+1