MechMem-RTL：用于基于大语言模型的RTL修复的可复用验证机制存储器
MechMem-RTL: Reusing Verified Mechanism Memories for LLM-Based RTL Repair
浏览论文内容
中文总结 AI 辅助
研究针对大语言模型修复RTL设计时，利用任务文本相似性易误导的问题，提出MechMem-RTL框架，复用验证器确认的修复记录，通过严格匹配触发证据来注入记录，实验表明该框架在多个任务上修复效果优于标准反馈修复和任务相似性RAG。
中文摘要 AI 辅助
大语言模型可自动修复寄存器传输级（RTL）设计。然而，修复复杂的时序逻辑错误需要复用过去的调试经验。现有检索增强生成（RAG）依赖任务文本相似性来提供此类经验，这种基于文本的方法常误导模型，因自然语言难以反映周期级硬件执行语义。为此，我们提出MechMem-RTL，一个复用验证器确认的修复记录而非文本相似性的修复框架。每个存储记录严格关联触发证据、诊断出的故障机制、局部修复操作、保留约束和验证总结。对于新故障，仅当确定性验证器证据与存储的触发严格兼容时，MechMem-RTL才注入过去记录，否则仅使用当前验证器证据。我们在六个修复模型的48个公共时序RTL任务上评估了MechMem-RTL。每个任务最多进行两次修复尝试，MechMem-RTL成功解决了288个任务-模型对中的180个，优于标准反馈修复（109对）和任务相似性RAG（107对）。
英文摘要
Large language models (LLMs) can automatically repair register-transfer-level (RTL) designs. However, fixing complex sequential logic errors requires reusing past debugging experience. Existing retrieval-augmented generation (RAG) relies on task-text similarity to provide this experience. This text-based approach often misguides the model because natural language poorly reflects cycle-level hardware execution semantics. To address this, we present MechMem-RTL, a repair framework that reuses verifier-confirmed repair records instead of text similarity. Each stored record strictly links trigger evidence, a diagnosed failure mechanism, a local repair action, preservation constraints, and a verification summary. For a new failure, MechMem-RTL injects a past record only when deterministic verifier evidence is strictly compatible with the stored trigger. Otherwise, the system uses only current verifier evidence. We evaluate MechMem-RTL on 48 public sequential RTL tasks across six repair models. With at most two repair attempts per task, MechMem-RTL successfully resolves 180 out of 288 task-model pairs, outperforming standard feedback repair (109 pairs) and task-similarity RAG (107 pairs).
