collaborators

11 papers

cs.AR2026

Rtl2lean: Automated RTL-to-Lean Translation with Hierarchical Theorem Generation and Lemma Reuse

Hongqin Lyu, Junxing Dong, Yonghao Wang +3

Formal verification with interactive theorem provers can provide strong correctness guarantees for register transfer level designs, but applying it to existing SystemVerilog code r…

cs.AI2026

Arcane: An Assertion Reduction Framework through Semantic Clustering and MCTS-Guided Rule Exploring

Hongqin Lyu, Yonghao Wang, Zhiteng Chao +2

Assertion-based Verification (ABV) is essential for ensuring that hardware designs conform to their intended specifications. However, existing automated assertion-generation approa…

cs.AR2026

CoverAssert: Iterative LLM Assertion Generation Driven by Functional Coverage via Syntax-Semantic Representations

Yonghao Wang, Yang Yin, Hongqin Lyu +8

LLMs can generate SystemVerilog assertions (SVAs) from natural language specs, but single-pass outputs often lack functional coverage due to limited IC design understanding. We pro…

cs.AR2026

From Indiscriminate to Targeted: Functionally Critical Signal-Driven Assertion Generation using LLMs for Efficient RTL Verification

Yonghao Wang, Hongqin Lyu, Boling Chen +9

Functional verification has become the most time-consuming phase in IC development, and Assertion-Based Verification (ABV) is key to reducing debugging time. However, existing LLM-…

cs.AR2026

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

Xinyu Zhang, Zhiteng Chao, Yonghao Wang +6

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…

cs.AR2026

Iterative LLM-Based Assertion Generation Using Syntax-Semantic Representations for Functional Coverage-Guided Verification

Yonghao Wang, Jiaxin Zhou, Yang Yin +6

While leveraging LLMs to automatically generate SystemVerilog assertions (SVAs) from natural language specifications holds great potential, existing techniques face a key challenge…