跳到正文
arXiv cs.MA· Changyuan Yu, Hongce Zhang·· 23 小时前AI 评分24

FormalFixer:面向意图对齐的硬件自动修复,联合精化规范、断言与 RTL 实现

FormalFixer: Intent-Aligned Automated Hardware Repair via Joint Refinement of Specifications, Assertions, and RTL Implementations

AI 导读

FormalFixer 提出一种多阶段、意图对齐的 Verilog 硬件修复流程,在修复前先对齐规范意图、验证意图与 RTL 行为,再决定修改哪个产物。该方法将原始规范保留为权威基准,追加经置信度过滤的精化以澄清隐含约束,并利用意图不匹配与验证器生成的反例锥图指导迭代 RTL 修补。该工作流显式检查规范—断言—RTL 三者的一致性。

正文 · 原文

View PDF HTML (experimental)

Abstract:Functional errors in hardware designs can compromise correctness and security, and must be fixed before tape-out. Formal property verification (FPV) provides strong guarantees by proving or refuting assertions, but a failed assertion is not always evidence of an RTL defect: the failure may also come from a buggy assertion or from a specification that is semantically correct but too ambiguous or incomplete for direct formalization. This creates a practical repair problem that existing RTL-centric methods do not directly address: the repair loop must align specification intent, verification intent, and RTL behavior before deciding which artifact to change.
\textsc{FormalFixer} addresses this problem with a multi-stage, intent-aligned repair workflow for Verilog designs with assertions. It preserves the original specification as authoritative ground truth and appends confidence-filtered refinements to clarify implicit constraints. \textsc{FormalFixer} uses both intent mismatch and verifier-generated counterexample cone graphs to guide iterative RTL patching. This workflow explicitly checks specification--assertion--RTL correspondence. Results support intent alignment for FPV-based hardware repair.
Subjects: Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.24037 [cs.MA]
  (or arXiv:2611.24037v1 [cs.MA] for this version)
  https://doi.org/10.48550/arXiv.2611.24037

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Changyuan Yu [view email]
[v1] Wed, 18 Nov 2026 08:25:59 UTC (488 KB)

来源:arXiv cs.MA · arxiv.org