arXiv AI

Coverage-Driven RTL Assertion Generation with Formal Exploration and Neuro-Symbolic Refinement

The paper introduces NeuroAssertion, a coverage-driven framework for generating RTL assertions that integrates formal trace generation, syntax-guided synthesis, and a two-step large language model (LLM) refinement process. It transforms hard-to-reach control-flow conditions into formal reachability goals, uses model checking to produce diverse traces, and mines initial assertions via SyGuS. The refinement stage employs one LLM to propose candidate assertions for uncovered regions and a second LLM to generate repair grammars that guide symbolic synthesis, resulting in roughly twice as many assertions and higher mutation coverage compared to traditional methods.

arXiv AI

Aug 19

NeuroAbs: A Neuro-Symbolic RTL Abstraction Framework for Property Checking Acceleration

NeuroAbs is a neuro‑symbolic framework designed to accelerate property checking in hardware verification by abstracting RTL designs. It employs large language model (LLM) assisted analysis to select signals for abstraction and combines LLM‑based abstraction with an AST‑based symbolic RTL representation to produce sound abstractions verified via SMT solving. When an abstraction is too coarse, NeuroAbs uses counterexample‑guided refinement (CEGAR) to iteratively improve the model, leading to significant efficiency gains across various verification tasks.

By Zhiyuan Yan, Xiaofeng Zhou, Ziyue Zheng, Ziyi Yang, Wenbin Che, Wei Zhang, Yangdi Lyu, Hongce Zhang

llms

arXiv Machine Learning

Aug 3

Open-Source LLM-Driven Formal Verification: A Multi-Agent Pipeline for RTL Repair

arXiv:2607. 28877v1 Announce Type: cross Abstract: Verification consumes the majority of modern chip design effort, yet the formal verification tools that provide mathematical guarantees of correctness remain expensive and restrictively licensed.

By Ha Trung Tran

llms agents benchmarks

arXiv AI

Aug 5

Don't Regenerate, Debug: A Domain-Specific Agent for Repairing Near-Miss Hardware Operators

arXiv:2608. 02712v1 Announce Type: cross Abstract: Kernel generation for hardware accelerators such as GPUs and NPUs has become a proving ground for large language models (LLMs), and state-of-the-art systems raise correctness through pipelines that couple LLMs with agentic reinforcement learning and evolutionary search.

By Yansong Sun, Shenxiu Wu, Siyuan Chen, Runlin Hou, Junhao Qiu, Junming Cao, Shudi Shao, Zhichao Lu, Qingfu Zhang

llms rag agents reinforcement-learning benchmarks

arXiv AI

Jun 9

RTL-BenchLS: A Large-Scale Benchmark for RTL Reasoning and Generation with Large Language Models

arXiv:2606. 08976v1 Announce Type: new Abstract: LLM-based RTL generation and reasoning is a promising direction for hardware design automation.

By Jing Wang, Shang Liu, Wenji Fang, Yuchao Wu, Yugao Zhu, Zhiyao Xie

llms benchmarks

arXiv AI

2d ago

ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem Proving

ProofEvolve is a neuro‑symbolic framework that evolves formally verified symbolic proof structures alongside neural models to expand the knowledge boundary in automated theorem proving. The neural component proposes variation operators such as decompositions, repairs, and schema recombinations, while the Lean kernel verifies every proof transition, ensuring formal soundness. Across three competition‑level Lean benchmarks, ProofEvolve achieves the highest average solve rate among evaluated proof systems.

By Wenqian Ye, Ziwei Guan, Eric Xie, Bohan Liu, Shivani Modi, Buyun Zhang, Ellie Dingqiao Wen, Henry Kautz, Aidong Zhang

benchmarks

arXiv AI

Jul 31

GoGoTB: Agentic RTL Verification with Specification-Grounded Coverage Closure

arXiv:2607. 26181v1 Announce Type: new Abstract: Functional verification dominates integrated circuit (IC) front-end engineering effort, and a single missed bug that escapes to silicon can trigger a costly respin.

By Xin Xin, Jincheng Lou, Junhui Li, Jinglin Yan, Panda Xiao, Di Wu, Haixiao Li, Weicong Lu, Weijian Fan, Xinyu Qu, Yuxiang Zhao, Min Yu, Zhixiong Di, Yibo Lin

llms agents benchmarks

arXiv AI

Jun 19

Interpretable and Verifiable Hardware Generation with LLM-Driven Stepwise Refinement

arXiv:2606. 19387v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success in software development.

By You Li, Samuel Mandell, David Z. Pan

llms agents safety

Hugging Face Trending Papers

Jul 28

GoGoTB: Agentic RTL Verification with Specification-Grounded Coverage Closure

Functional verification dominates integrated circuit (IC) front-end engineering effort, and a single missed bug that escapes to silicon can trigger a costly respin. Recent large language models (LLMs) offer new opportunities to automate this process, yet existing LLM-based approaches generate each component through independent single-turn calls with no shared context, leaving interface mismatches undetected and reported coverage disconnected from specification requirements.

llms agents benchmarks

arXiv AI

Jul 14

Efficient Test-Time Optimization for Multi-Agent Proof Autoformalization

arXiv:2607. 11307v1 Announce Type: new Abstract: Full-proof autoformalization bridges extensive mathematical proofs in natural language with formally validated reasoning, offering a pathway to elevate the ceiling of verifiable mathematical reasoning.

By Tian-Shuo Liu, Shiyuan Zhang, Zijie Geng, Haoyu Liu, Runjie Xu, Pengyuan Wang, Lei Yuan, Yang Yu

agents

arXiv AI

2d ago

HybridProver: Augmenting Theorem Proving with LLM-Driven Proof Synthesis and Refinement

HybridProver is a unified framework that combines whole-proof synthesis and tactic-based generation using proof sketches as an intermediate representation. Implemented in Isabelle/HOL, it employs two 7B-scale LLMs trained on optimized Isabelle datasets. On the miniF2F Isabelle benchmark, HybridProver achieved a 73.8% success rate, surpassing the previous state of the art of 61.9%, and ablation studies examined the effects of dataset quality, training settings, and sampling strategies.

By Jilin Hu, Jianyu Zhang, Yongwang Zhao, Talia Ringer

llms benchmarks

arXiv Machine Learning

Jun 5

CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs

arXiv:2606. 05680v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the automatic synthesis (generation) of register-transfer level (RTL) code from natural language instructions, offering a promising pathway to accelerate chip design.

By Mohammad Akyash, Nowfel Mashnoor, Kimia Azar, Hadi Kamali

llms rag agents fine-tuning safety

arXiv AI

Aug 11

SymDiag: Explainable Diagnosis for LLM Reasoning via Neuro-Symbolic Verification

arXiv:2608. 08786v1 Announce Type: new Abstract: Large language models (LLMs) increasingly serve as data-driven reasoners, yet their chains-of-thought (CoT) can be unfaithful even when final answers are correct.

By Wenyao Cui, Huaping Zhang, Yongyi Huang, Qiuchi Li, Jian Xu, Cheng-Lin Liu, Chunxiao Gao, Juan Wang, Baohua Zhang

llms benchmarks

Related stories