EUVIMEDEUVIMED entdecken
Crossref

Process-Aware LLM-Agent Scaffolds for Metric-Based Microservice Root-Cause Analysis with Evidence-Trace Scoring

Matthew Liao

Stout in Computer Science and Technology Studies · 30.12.2025 · 1 (1) · 48-61

DOI: 10.61424/zngee941 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Stout in Computer Science and Technology Studies, online erschienen am 30.12.2025. Verfasst von Matthew Liao.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Root-cause analysis in microservice systems increasingly relies on agents that retrieve telemetry, form hypotheses, and explain a diagnosis. Final-answer accuracy alone does not reveal whether the cited evidence supports the conclusion. This study evaluated a process-aware diagnostic scaffold for large-language-model agents on the metric-only RE1-OB corpus from RCAEval. The corpus contains 125 fault-injection cases arranged as five root services, five fault types, and five repetitions. Each case was represented by equal 300-second pre-injection and post-injection windows. To prevent acquisition and schema leakage, the primary predictors were restricted to 35 CPU, memory, and workload streams present in every case; timestamps, file duration, column count, and missingness patterns were excluded. Five leave-one-repetition-out folds compared six conventional classifiers with a tri-head tree ensemble that combined joint service–fault prediction with separate localization and fault-identification heads. The process-aware model achieved 0.960 joint accuracy (95% bootstrap confidence interval [0.920, 0.992]), 0.957 macro-F1, 0.968 service accuracy, 0.992 fault accuracy, and 0.992 top-three accuracy. Injection-aligned evidence retrieval reached 0.952 root-service recall at five. Reranking evidence against the predicted service increased recall to 1.000, reason score from 0.653 to 0.719, and evidence-trace score from 0.871 to 0.893. Five errors remained, dominated by loss-fault service confusion. The findings show that strong diagnosis and auditable evidence are separable objectives: a structured retrieval and verification layer added measurable grounding without changing the underlying top-one predictions.

Zitieren

APA

Liao, M. (2025). Process-Aware LLM-Agent Scaffolds for Metric-Based Microservice Root-Cause Analysis with Evidence-Trace Scoring. Stout in Computer Science and Technology Studies, 1(1), 48-61. https://doi.org/10.61424/zngee941

Vancouver

Liao M. Process-Aware LLM-Agent Scaffolds for Metric-Based Microservice Root-Cause Analysis with Evidence-Trace Scoring. Stout in Computer Science and Technology Studies. 2025;1(1):48-61. doi:10.61424/zngee941

BibTeX
@article{Liao2025,
  author = {Liao, Matthew},
  title = {Process-Aware LLM-Agent Scaffolds for Metric-Based Microservice Root-Cause Analysis with Evidence-Trace Scoring},
  journal = {Stout in Computer Science and Technology Studies},
  year = {2025},
  volume = {1},
  number = {1},
  pages = {48--61},
  doi = {10.61424/zngee941}
}
Kostenlos starten →