LogSage: An LLM-Based Framework for CI/CD Failure Detection and Remediation with Industrial Validation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911191569268736 |
|---|---|
| author | Xu, Weiyuan Luo, Juntao Huang, Tao Sui, Kaixin Geng, Jie Ma, Qijun Akasaka, Isami Shi, Xiaoxue Tang, Jing Cai, Peng |
| author_facet | Xu, Weiyuan Luo, Juntao Huang, Tao Sui, Kaixin Geng, Jie Ma, Qijun Akasaka, Isami Shi, Xiaoxue Tang, Jing Cai, Peng |
| contents | Continuous Integration and Deployment (CI/CD) pipelines are critical to modern software engineering, yet diagnosing and resolving their failures remains complex and labor-intensive. We present LogSage, the first end-to-end LLM-powered framework for root cause analysis (RCA) and automated remediation of CI/CD failures. LogSage employs a token-efficient log preprocessing pipeline to filter noise and extract critical errors, then performs structured diagnostic prompting for accurate RCA. For solution generation, it leverages retrieval-augmented generation (RAG) to reuse historical fixes and invokes automation fixes via LLM tool-calling. On a newly curated benchmark of 367 GitHub CI/CD failures, LogSage achieves over 98\% precision, near-perfect recall, and an F1 improvement of more than 38\% points in the RCA stage, compared with recent LLM-based baselines. In a year-long industrial deployment at ByteDance, it processed over 1.07M executions, with end-to-end precision exceeding 80\%. These results demonstrate that LogSage provides a scalable and practical solution for automating CI/CD failure management in real-world DevOps workflows. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03691 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LogSage: An LLM-Based Framework for CI/CD Failure Detection and Remediation with Industrial Validation Xu, Weiyuan Luo, Juntao Huang, Tao Sui, Kaixin Geng, Jie Ma, Qijun Akasaka, Isami Shi, Xiaoxue Tang, Jing Cai, Peng Software Engineering Continuous Integration and Deployment (CI/CD) pipelines are critical to modern software engineering, yet diagnosing and resolving their failures remains complex and labor-intensive. We present LogSage, the first end-to-end LLM-powered framework for root cause analysis (RCA) and automated remediation of CI/CD failures. LogSage employs a token-efficient log preprocessing pipeline to filter noise and extract critical errors, then performs structured diagnostic prompting for accurate RCA. For solution generation, it leverages retrieval-augmented generation (RAG) to reuse historical fixes and invokes automation fixes via LLM tool-calling. On a newly curated benchmark of 367 GitHub CI/CD failures, LogSage achieves over 98\% precision, near-perfect recall, and an F1 improvement of more than 38\% points in the RCA stage, compared with recent LLM-based baselines. In a year-long industrial deployment at ByteDance, it processed over 1.07M executions, with end-to-end precision exceeding 80\%. These results demonstrate that LogSage provides a scalable and practical solution for automating CI/CD failure management in real-world DevOps workflows. |
| title | LogSage: An LLM-Based Framework for CI/CD Failure Detection and Remediation with Industrial Validation |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2506.03691 |