一句话：提出RL增强的LLM基础模型FoundRoot，以结构化深度思考分解RCA推理，跨系统零样本RCA优于现有方法。
服务系统根因分析（RCA）对可靠性至关重要，但大量指标与复杂因果关系使其难以应用；经典统计或规则方法难以泛化到未见系统，LLM 虽能理解指标语义并推理，却常因指标繁多而产生不完整或浅层推理。为此，论文提出 FoundRoot，一个强化学习增强的 LLM 基础模型，用于零样本 RCA。其核心是结构化深度思考范式，将 RCA 推理拆解为若干目标导向子步骤，以提升因果关系推理的完整性与能力。作者收集并整理跨不同系统的开源 RCA 数据集，引入数据增强保证可扩展性，并设计 SFT 与 RL 两阶段训练流程，使 LLM 对齐该范式。在四个数据集上的实验表明，FoundRoot 在未见系统上优于经典与 LLM 方法，MRR 提升 4.5%–48.6%。
Root Cause Analysis (RCA) for service systems is critical for ensuring their reliability, while its application remains challenging because of the large number of metrics and the complex causal relationships. Classical RCA methods typically rely on statistical or rule-based approaches, making them difficult to generalize to unseen systems. The introduction of Large Language Models (LLMs) has partly addressed these challenges with their understanding of the domain-specific semantics of metrics and reasoning capabilities. However, they still struggle with incomplete or shallow reasoning when facing a large amount of metrics. To address these limitations, we present FoundRoot, a reinforcement learning (RL)-enhanced LLM foundation model for zero-shot RCA. FoundRoot features a novel structured deep thinking paradigm, which breaks down the RCA reasoning into several goal-oriented substeps, enhancing the completeness and reasoning capability of the causal relationship. We collect and curate diverse open-sourced RCA datasets across different systems and introduce a data augmentation technique to ensure data scalability. We design a two-stage training pipeline that includes supervised fine-tuning (SFT) and RL to align the LLM with the structured deep thinking paradigm, which significantly improves its reasoning quality. Extensive experiments on four datasets show that FoundRoot outperforms both classical and LLM-based methods in RCA accuracy on unseen systems, achieving 4.5%-48.6% mean reciprocal rank (MRR) improvements. The source code and data of this paper is available at: https://github.com/NetManAIOps/FoundRoot.
@inproceedings{paperbot11511,
title = {FoundRoot: Towards Foundation Model for Root Cause Analysis via Structured Deep Thinking},
author = {Zhe Xie and Zeyan Li and Xiao He and Shenglin Zhang and Longlong Xu and Yuzhuo Yang and Tieying Zhang and Jianjun Chen and Rui Shi and Dan Pei},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3787814}
}