ScholarWorks@중앙대학교

초록

When debugging large-scale software systems, manually identifying relevant log portions for root-cause analysis is inefficient. Existing approaches are limited to detecting anomalies, extracting key error lines, or summarizing logs for root-cause analysis, and do not explicitly recommend which contiguous log ranges developers should review. Efficient debugging requires an approach that recommends log sections for prioritized review. This paper presents a formalization of the log-range recommendation (LRR) problem and proposes a two-stage pipeline called Log Retrieval with Intelligent Decomposition and Narrowing (LORIN). Pipeline (1) reduces the search space through anomaly detection, and pipeline (2) provides range extraction and evidence-based responses through a retrieval-augmented generation (RAG) approach that combines query decomposition with iterative refinement. To address LRR, a newly defined problem without established benchmarks, we validated the feasibility of LORIN through an exploratory multiple-case study of 30 Android Open-Source Project (AOSP) bug reports (averaging 10,445 lines). By varying the context buffer lines surrounding the recommendations across seven configurations, we observed a coverage–alignment tradeoff, where coverage improved from 66.4% to 89.9%, and intersection-over-union (IoU) score decreased from 17.8% to 4.8%. The output volume, a descriptive measure of review effort rather than an optimization objective, increased from 6.9% to 39.1%. The findings of this study provide a formalization of the LRR problem and an evaluation protocol, establishing a methodological starting point for future research across diverse domains and large-scale datasets.

키워드