EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AgentReport: A Multi-Agent LLM Approach for Automated and Reproducible Bug Report Generation

Seojin Choi, Geunseok Yang

Applied Sciences · 10.11.2025 · 15 (22) · 11931

DOI: 10.3390/app152211931 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 10.11.2025. Verfasst von Seojin Choi und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bug reports in open-source projects are often incomplete or low in quality, which reduces maintenance efficiency. To address this issue, we propose AgentReport, a multi-agent pipeline based on large language models (LLMs). AgentReport integrates QLoRA-4bit lightweight fine-tuning, CTQRS (Completeness, Traceability, Quantifiability, Reproducibility, Specificity) structured prompting, Chain-of-Thought reasoning, and one-shot exemplar within seven modules: Data, Prompt, Fine-tuning, Generation, Evaluation, Reporting, and Controller. Using 3966 summary–report pairs from Bugzilla, AgentReport achieved 80.5% in CTQRS, 84.6% in ROUGE-1 Recall, 56.8% in ROUGE-1 F1, and 86.4% in Sentence-BERT (SBERT). Compared with the baseline (77.0% CTQRS, 61.0% ROUGE-1 Recall, 85.0% SBERT), AgentReport improved CTQRS by 3.5 percentage points, Recall by 23.6 points, and SBERT by 1.4 points. The inclusion of F1 complemented Recall-only evaluation, offering a balanced framework that covers structural completeness (CTQRS), lexical coverage and precision (ROUGE-1 Recall/F1), and semantic consistency (SBERT). This modular design enables consistent experimentation and flexible scaling, providing practical evidence that multi-agent LLM pipelines can generate higher-quality bug reports for software maintenance.

Zitieren

APA

Choi, S., & Yang, G. (2025). AgentReport: A Multi-Agent LLM Approach for Automated and Reproducible Bug Report Generation. Applied Sciences, 15(22), 11931. https://doi.org/10.3390/app152211931

Vancouver

Choi S, Yang G. AgentReport: A Multi-Agent LLM Approach for Automated and Reproducible Bug Report Generation. Applied Sciences. 2025;15(22):11931. doi:10.3390/app152211931

BibTeX
@article{Choi2025,
  author = {Choi, Seojin and Yang, Geunseok},
  title = {AgentReport: A Multi-Agent LLM Approach for Automated and Reproducible Bug Report Generation},
  journal = {Applied Sciences},
  year = {2025},
  volume = {15},
  number = {22},
  pages = {11931},
  doi = {10.3390/app152211931}
}
Kostenlos starten →