Crash Report Enhancement with Large Language Models: An Empirical Study
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_ | 1866914041395412992 |
|---|---|
| author | Fahim, S M Farah Al Rafi, Md Nakhla Ma, Zeyang Kim, Dong Jae Tse-Hsun Chen |
| author_facet | Fahim, S M Farah Al Rafi, Md Nakhla Ma, Zeyang Kim, Dong Jae Tse-Hsun Chen |
| contents | Crash reports are central to software maintenance, yet many lack the diagnostic detail developers need to debug efficiently. We examine whether large language models can enhance crash reports by adding fault locations, root-cause explanations, and repair suggestions. We study two enhancement strategies: Direct-LLM, a single-shot approach that uses stack-trace context, and Agentic-LLM, an iterative approach that explores the repository for additional evidence. On a dataset of 492 real-world crash reports, LLM-enhanced reports improve Top-1 problem-localization accuracy from 10.6% (original reports) to 40.2-43.1%, and produce suggested fixes that closely resemble developer patches (CodeBLEU around 56-57%). Both our manual evaluations and LLM-as-a-judge assessment show that Agentic-LLM delivers stronger root-cause explanations and more actionable repair guidance. A user study with 16 participants further confirms that enhanced reports make crashes easier to understand and resolve, with the largest improvement in repair guidance. These results indicate that supplying LLMs with stack traces and repository code yields enhanced crash reports that are substantially more useful for debugging. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13535 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Crash Report Enhancement with Large Language Models: An Empirical Study Fahim, S M Farah Al Rafi, Md Nakhla Ma, Zeyang Kim, Dong Jae Tse-Hsun Chen Software Engineering Crash reports are central to software maintenance, yet many lack the diagnostic detail developers need to debug efficiently. We examine whether large language models can enhance crash reports by adding fault locations, root-cause explanations, and repair suggestions. We study two enhancement strategies: Direct-LLM, a single-shot approach that uses stack-trace context, and Agentic-LLM, an iterative approach that explores the repository for additional evidence. On a dataset of 492 real-world crash reports, LLM-enhanced reports improve Top-1 problem-localization accuracy from 10.6% (original reports) to 40.2-43.1%, and produce suggested fixes that closely resemble developer patches (CodeBLEU around 56-57%). Both our manual evaluations and LLM-as-a-judge assessment show that Agentic-LLM delivers stronger root-cause explanations and more actionable repair guidance. A user study with 16 participants further confirms that enhanced reports make crashes easier to understand and resolve, with the largest improvement in repair guidance. These results indicate that supplying LLMs with stack traces and repository code yields enhanced crash reports that are substantially more useful for debugging. |
| title | Crash Report Enhancement with Large Language Models: An Empirical Study |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2509.13535 |