Metraipolis › archive › dc_207d69b45272
GALA: Graph-Augmented LLM Agents for Root Cause Analysis and Incident Response in Microservices — arXiv:2608.08968
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.08968
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T09:00:57.664Z
- SHA-256 of the archived text
a5c1230f6ac42d32ed69adc4ffb5dd1bfc1d29d691a3306282a109fa1233cc0a- Stable URL of this page
https://metraipolis.com/documento/dc_207d69b45272
How to cite
GALA: Graph-Augmented LLM Agents for Root Cause Analysis and Incident Response in Microservices — arXiv:2608.08968 — arXiv (en), https://arxiv.org/abs/2608.08968 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_207d69b45272 (Metraipolis archive dc_207d69b45272, sha256 a5c1230f6ac42d32ed69adc4ffb5dd1bfc1d29d691a3306282a109fa1233cc0a)
BibTeX
@misc{dc207d69b45272,
title = {GALA: Graph-Augmented LLM Agents for Root Cause Analysis and Incident Response in Microservices — arXiv:2608.08968},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.08968},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_207d69b45272; sha256 a5c1230f6ac42d32ed69adc4ffb5dd1bfc1d29d691a3306282a109fa1233cc0a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08968. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Microservice root cause analysis (RCA) requires correlating failures across heterogeneous telemetry within complex service dependency graphs. Existing methods often rely on a single telemetry modality; recent LLM-based approaches can suffer from unconstrained exploration and hallucination; and most systems stop at fault ranking without producing actionable incident response. We present GALA+, a graph-augmented LLM agentic framework centered on graph-guided investigation, which uses service dependencies to bound exploration and refine diagnosis through localized multi-modal evidence. For initial hypothesis generation, GALA+ combines complementary telemetry signals with STRIX, a novel trace- and graph-structure-aware scoring module. GALA+ then produces ranked diagnoses, incident summaries, and stratified action recommendations. We further introduce SURE-Score, a human-guided evaluation framework co-developed with industry SRE experts for assessing RCA-specific output quality beyond conventional text similarity metrics. On two microservice benchmarks, GALA+ consistently achieves the strongest overall results, surpassing the best LLM-based baseline by more than 25 percentage points in AC@1, while also receiving the highest ratings from both SURE-Score and independent human SRE evaluation. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-11 in cs.SE). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.08968 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T09:00:31.489Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).