~ similar to 2608.01045· 20 results
The paper introduces ProofLoop, a novel ReAct agent that uses a solver-in-the-loop approach to automatically generate and formally verify SystemVerilog Assertions (SVA) from natural language specifica…
This paper surveys the use of hardware emulation for security verification in System-on-Chip (SoC) design, positioning emulation as a critical, high-fidelity pre-silicon assurance technology.
StepPRM-RTL is a novel framework that enhances LLM-based RTL code generation for digital hardware designs.
The first formal verification of an out-of-order multiprocessor against an in-order, weak-memory ISA using a core specification and mechanized proofs in Rocq.
The paper presents Agentic-IC3, an improved hardware model checker that uses a language-model agent to guide proof search and exploit high-level design structure and semantics.
The paper introduces FVSpec, a large-scale benchmark that translates thousands of real-world Python property-based tests into formal Lean 4 specifications to evaluate AI models for formal software ver…
Jiaying Zhu, Zhengyuan Shi, Mengxia Tao, Kezhi Li +2 more
A new framework for Logic Equivalence Checking (LEC) is proposed, which strategically formulates the problem before solving by constructing a LUT-based miter and integrating equivalence-preserving map…
Yijun Shen, Minghao Shao, Yichen Zhao, Zhuoyan Yu +3 more
The paper introduces VHDLSuite, an infrastructure for evaluating Large Language Models in VHDL, including a data pipeline, benchmark, and evaluation framework.
This paper presents VerIbmc, a neuro-symbolic pipeline for loop invariant synthesis that uses open-weight language models and can be deployed locally without relying on cloud APIs.
Shams Tarek, Dipayan Saha, Khan Thamid Hasan, Sujan Kumar Saha +2 more
Assertain is an automated framework that uses large language models and design analysis to generate high-quality, executable security assertions for hardware designs, significantly outperforming state…
This survey reviews the integration of AI and LLMs into hardware security verification, demonstrating its potential to automate complex stages while stressing the necessity of grounding AI outputs in…
Ryan G. Scott, Ivan Perez, Alwyn E. Goodloe, Mike Dodds +1 more
This paper presents CopilotVerifier, a tool that generates proofs of correctness for the compiled output of the Copilot runtime verification framework.
This review analyzes the dual impact of integrating Large Language Models (LLMs) into hardware design, detailing both their transformative potential in EDA and the critical security vulnerabilities th…