paperbot · PL 论文追踪

全部论文 待读 收藏

P2 Root Cause Analysis of RISC-V Build Failures via LLM and MCTS Reasoning

基于 LLM 与 MCTS 推理的 RISC-V 构建失败根因分析
ASE 2025 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)2025匹配度 3/10 · 论文用 LLM 与 MCTS 做 RISC-V 构建失败的根因分析，属于 LLM 辅助软件调试/修复，而非用户核心关注的静态分析、形式化验证、浮点程序分析或贝叶斯程序分析；与“AI→PL 改进静态分析”方向仅间接相关。引用 1 inbox
Weipeng Shuai, Jie Liu, Zhirou Ma, Liangyi Kang, Zehua Wang, Shuai Wang, Dan Ye, Hui Li, Wei Wang, Jiaxin Zhu
机器学习与程序语言测试、调试与修复
crossref: 2026-09-12

AI 速览

一句话：提出 RV-LAD 与 MCTS-RCA 两阶段框架，用少样本 LLM 与蒙特卡洛树搜索自动诊断 RISC-V 构建失败根因。

RISC-V 软件迁移中的构建失败往往涉及日志、配置与环境的多源复杂交互，日志非结构化且跨越多个阶段，传统诊断工具缺乏语义推理能力。本文提出两阶段自动化根因分析框架：RV-LAD 通过模板化过滤压缩日志，并利用少样本 LLM 提示进行阶段感知的异常检测；MCTS-RCA 将领域知识库与蒙特卡洛树搜索结合，在分类约束下执行 LLM 引导的多源推理。为支持评估，作者构建了包含 117 个真实 RISC-V 构建失败的数据集，每个样本标注日志、spec 文件与修复记录。实验表明该方法诊断准确率达 75.2%，优于此前的 LLM 与规则方法，并能给出可解释的推理轨迹。

问题
RISC-V 软件迁移中的构建失败日志非结构化、跨阶段且涉及日志、配置与环境等多源信息，传统诊断工具难以进行语义层面的根因定位。
方法
RV-LAD 用模板化过滤压缩日志并进行阶段感知的少样本 LLM 异常检测；MCTS-RCA 将领域知识库与蒙特卡洛树搜索结合，在分类约束下执行 LLM 引导的多源推理。
评估
在自建的 117 个真实 RISC-V 构建失败数据集（含日志、spec 文件与修复记录）上进行评估，诊断准确率达 75.2%，超过已有 LLM 与规则方法，并能输出可解释的推理轨迹。
原文摘要（Abstract）

Build failures are a major obstacle in RISC-V software migration, often involving complex interactions across logs, configurations, and environments. Traditional diagnostic tools struggle with the unstructured, multi-phase nature of build logs and lack semantic reasoning.We propose a two-stage framework for automated root cause analysis. RV-LAD compresses logs using template-based filtering and applies phase-aware anomaly detection via few-shot LLM prompting. MCTS-RCA integrates a domain-specific knowledge base with Monte Carlo Tree Search to perform LLM-guided multi-source reasoning under classification constraints.To support evaluation, we construct a curated dataset of 117 real-world RISC-V build failures, each annotated with logs, spec files, and repair records. Experiments show our approach achieves 75.2% diagnosis accuracy, surpassing previous LLM-based and rule-based methods. It also offers interpretable reasoning traces, enabling practical and transparent diagnosis. This work provides an effective and extensible solution for RCA in emerging software ecosystems like RISC-V, bridging large language models with domain-aware inference.

链接与引用

DOI 原文 ·

BibTeX 
@inproceedings{paperbot9553,
  title = {Root Cause Analysis of RISC-V Build Failures via LLM and MCTS Reasoning},
  author = {Weipeng Shuai and Jie Liu and Zhirou Ma and Liangyi Kang and Zehua Wang and Shuai Wang and Dan Ye and Hui Li and Wei Wang and Jiaxin Zhu},
  booktitle = {ASE},
  year = {2025},
  doi = {10.1109/ase63991.2025.00227}
}