arXiv cs.AI· Mohammad Baqar·· 2 天前AI 评分22
RAG4Tickets：基于 JIRA 与 GitHub 数据的 RAG 工单解决框架
RAG4Tickets: AI-Powered Ticket Resolution via Retrieval-Augmented Generation on JIRA and GitHub Data
AI 导读
RAG4Tickets 提出一套 RAG 框架，用 Sentence-Transformers 做语义嵌入、FAISS 做向量检索，将历史 JIRA 工单、用户评论与关联 PR 元数据统一索引，再由 LLM 生成有依据、可解释的解决建议。该框架打通 JIRA 与 GitHub 数据，在精确率、召回率、解决时间缩短和开发者接受度等指标上显著提升了解题准确率与知识复用。
正文 · 原文
Abstract:Modern software teams frequently encounter delays in resolving recurring or related issues due to fragmented knowledge scattered across JIRA tickets, developer discussions, and GitHub pull requests (PRs). To address this challenge, we propose a Retrieval-Augmented Generation (RAG) framework that integrates Sentence-Transformers for semantic embeddings with FAISS-based vector search to deliver context-aware ticket resolution recommendations. The approach embeds historical JIRA tickets, user comments, and linked PR metadata to retrieve semantically similar past cases, which are then synthesized by a Large Language Model (LLM) into grounded and explainable resolution suggestions. The framework contributes a unified pipeline linking JIRA and GitHub data, an embedding and FAISS indexing strategy for heterogeneous software artifacts, and a resolution generation module guided by retrieved evidence. Experimental evaluation using precision, recall, resolution time reduction, and developer acceptance metrics shows that the proposed system significantly improves resolution accuracy, fix quality, and knowledge reuse in modern DevOps environments.
| Comments: | 13 Pages |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2510.08667 [cs.SE] |
| (or arXiv:2510.08667v3 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2510.08667 arXiv-issued DOI via DataCite |
Submission history
From: Mohammad Baqar [view email]
[v1]
Thu, 9 Oct 2025 16:33:00 UTC (343 KB)
[v2]
Thu, 5 Feb 2026 17:25:30 UTC (326 KB)
[v3]
Thu, 15 Oct 2026 14:55:22 UTC (325 KB)
来源：arXiv cs.AI · arxiv.org