Improving LLM-Based Fault Localization with External Memory and Project Context
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_ | 1866910986378674176 |
|---|---|
| author | Yeo, Inseok Ryu, Duksan Baik, Jongmoon |
| author_facet | Yeo, Inseok Ryu, Duksan Baik, Jongmoon |
| contents | Fault localization, the process of identifying the software components responsible for failures, is essential but often time-consuming. Recent advances in Large Language Models (LLMs) have enabled fault localization without extensive defect datasets or model fine-tuning. However, existing LLM-based methods rely only on general LLM capabilities and lack integration of project-specific knowledge, resulting in limited effectiveness, especially for complex software.
We introduce MemFL, a novel approach that enhances LLM-based fault localization by integrating project-specific knowledge via external memory. This memory includes static summaries of the project and dynamic, iterative debugging insights gathered from previous attempts. By leveraging external memory, MemFL simplifies debugging into three streamlined steps, significantly improving efficiency and accuracy. Iterative refinement through dynamic memory further enhances reasoning quality over time.
Evaluated on the Defects4J benchmark, MemFL using GPT-4o-mini localized 12.7% more bugs than current LLM-based methods, achieving this improvement with just 21% of the execution time (17.4 seconds per bug) and 33% of the API cost (0.0033 dollars per bug). On complex projects, MemFL's advantage increased to 27.6%. Additionally, MemFL with GPT-4.1-mini outperformed existing methods by 24.4%, requiring only 24.7 seconds and 0.0094 dollars per bug. MemFL thus demonstrates significant improvements by effectively incorporating project-specific knowledge into LLM-based fault localization, delivering high accuracy with reduced time and cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_03585 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving LLM-Based Fault Localization with External Memory and Project Context Yeo, Inseok Ryu, Duksan Baik, Jongmoon Software Engineering Fault localization, the process of identifying the software components responsible for failures, is essential but often time-consuming. Recent advances in Large Language Models (LLMs) have enabled fault localization without extensive defect datasets or model fine-tuning. However, existing LLM-based methods rely only on general LLM capabilities and lack integration of project-specific knowledge, resulting in limited effectiveness, especially for complex software. We introduce MemFL, a novel approach that enhances LLM-based fault localization by integrating project-specific knowledge via external memory. This memory includes static summaries of the project and dynamic, iterative debugging insights gathered from previous attempts. By leveraging external memory, MemFL simplifies debugging into three streamlined steps, significantly improving efficiency and accuracy. Iterative refinement through dynamic memory further enhances reasoning quality over time. Evaluated on the Defects4J benchmark, MemFL using GPT-4o-mini localized 12.7% more bugs than current LLM-based methods, achieving this improvement with just 21% of the execution time (17.4 seconds per bug) and 33% of the API cost (0.0033 dollars per bug). On complex projects, MemFL's advantage increased to 27.6%. Additionally, MemFL with GPT-4.1-mini outperformed existing methods by 24.4%, requiring only 24.7 seconds and 0.0094 dollars per bug. MemFL thus demonstrates significant improvements by effectively incorporating project-specific knowledge into LLM-based fault localization, delivering high accuracy with reduced time and cost. |
| title | Improving LLM-Based Fault Localization with External Memory and Project Context |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2506.03585 |