一句话：提出TAAF，用时间索引知识图谱与大语言模型把海量执行轨迹转为可自然语言查询的洞察，并发布TraceQA-100基准。
执行轨迹对复杂系统理解、调试与优化至关重要，但内核及 Chrome/MySQL 等大规模轨迹庞大难析；现有工具依赖预定义分析，定制洞察常需写脚本，耗时易错。TAAF 融合时间索引、知识图谱与 LLM：从轨迹事件构建时间索引 KG，捕捉线程、CPU、系统资源等实体关系；再由 LLM 解释查询相关子图，用自然语言回答问题，减少人工检查与专家知识依赖。为评估，作者提出基于真实内核轨迹的 TraceQA-100 基准；在三个 LLM 与多种时序设置下，TAAF 答案准确率最高提升 31.2%，尤其改善多跳与因果推理，并讨论图谱推理的助益与局限。
Execution traces are a critical source of information for understanding, debugging, and optimizing complex software systems. However, traces from OS kernels or large-scale applications like Chrome or MySQL are massive and difficult to analyze. Existing tools rely on predefined analyses, and custom insights often require writing domain-specific scripts, which is an error-prone and time-consuming task. This paper introduces TAAF (Trace Abstraction and Analysis Framework), a novel approach that combines time-indexing, knowledge graphs (KGs), and large language models (LLMs) to transform raw trace data into actionable insights. TAAF constructs a time-indexed KG from trace events to capture relationships among entities such as threads, CPUs, and system resources. An LLM then interprets query-specific subgraphs to answer natural-language questions, reducing the need for manual inspection and deep system expertise. To evaluate TAAF, we introduce TraceQA-100, a benchmark of 100 questions grounded in real kernel traces. Experiments across three LLMs and multiple temporal settings show that TAAF improves answer accuracy by up to 31.2%, particularly in multi-hop and causal reasoning tasks. We further analyze where graph-grounded reasoning helps and where limitations remain, offering a foundation for next-generation trace analysis tool.
@inproceedings{abs-2601-02632,
title = {TAAF: A Trace Abstraction and Analysis Framework Synergizing Knowledge Graphs and LLMs},
author = {Alireza Ezaz and Ghazal Khodabandeh and Majid Babaei and Naser Ezzati-Jivan},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3787832}
}