用知识树结构化硬件调试经验，提升大模型修复断言失败的准确率。
Learning to Debug: LLM-Organized Knowledge Trees for Solving RTL Assertion Failures
- 构建可配置深度的知识树，每节点包含可复用的调试知识与适用条件。
- 在多个断言失败案例上，pass@1和pass@5指标均显著提升。
- 适合硬件验证工程师和希望提升调试效率的大模型应用者。
硬件验证中调试成本最高，断言失败是最常见且昂贵的问题。尽管大语言模型（LLM）展现出潜力，但常无法捕捉工程师所需的精确、可复用的专业知识，导致回复不准确。本文提出GROVE，一种分层知识管理框架，将过往调试案例中的知识提炼并组织成由LLM构建的知识树。GROVE通过并行、无梯度的循环训练，让LLM以结构化JSON编辑方式学习树的修改。测试时，采用预算感知的迭代式逐层探索，从树中检索少量适用知识，指导基础LLM生成假设和修复建议。在一组断言失败案例上评估，GROVE在pass@1和pass@5上均实现稳定提升，证明了结构化知识演化的价值。
原文摘要 · Abstract (English)
Debugging is the dominant cost in modern hardware verification, where assertion failures are among the most frequent and expensive to resolve. While Large Language Models (LLMs) show promise, they often fail to capture the precise, reusable expertise that engineers apply, leading to inaccurate responses. We propose GROVE, a hierarchical knowledge management framework that learns and organizes reusable debugging expertise into an LLM-organized knowledge tree for solving assertion failures. GROVE distills debugging knowledge from prior cases and organizes it into a vertical tree of configurable depth, with each node encoding a concise knowledge item and explicit applicability conditions. During training, GROVE uses a parallel, gradient-free loop where an LLM proposes tree modifications as structured JSON edits by learning from the cases. At test time, a budget-aware iterative zoom is performed to navigate the tree, retrieving a small set of applicable knowledge items that guide a base LLM's hypothesis generation and fix proposals. Evaluated on a suite of assertion-failure cases, GROVE delivers consistent gains in pass@1 and pass@5, demonstrating the value of structured knowledge evolution.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。