STAR: A Stage-attributed Triage and Repair framework for RCA Agents in Microservices
Quick Answer
The STAR framework enhances root cause analysis in microservices by localizing and repairing errors in RCA workflows.
Quick Take
It decomposes the process into four stages, improving fault localization and classification accuracy on large benchmarks and real-world datasets. STAR demonstrates significant performance gains through stage-specific evaluations and routing strategies.
Key Points
- STAR decomposes RCA into four stages: Evidence Package, Hypothesis Set, Analysis Structure, and Decision Report.
- The framework improves root cause localization and fault type classification over strong baselines.
- STAR identifies faulty stages accurately and repairs most errors within one or two replay rounds.
- Utilizes Fast/Slow Routing and counterfactual evaluation for effective stage-specific repairs.
- Evaluated on large-scale benchmarks and real-world datasets with two RCA workflows.
Paper Resources
📖 Reader Mode
~2 min readAbstract:LLM-based root cause analysis (RCA) agents have recently emerged as a promising paradigm for incident diagnosis in microservice AIOps. However, their reliability remains fragile: an error in early evidence collection, hypothesis formulation, or causal analysis can propagate through the reasoning trace and eventually corrupt the final diagnosis. In this paper, we present \textbf{STAR}, a \emph{Stage-attributed Triage and Repair} framework for repairing erroneous RCA traces. STAR explicitly decomposes an RCA workflow into four structured stages, namely \emph{Evidence Package} (EP), \emph{Hypothesis Set} (HS), \emph{Analysis Structure} (AS), and \emph{Decision Report} (DR), and treats agent failure as a stage-localizable reasoning bug rather than a monolithic end-to-end error. Built on top of LangGraph, STAR performs stage-wise auditing, budget-aware \emph{Fast/Slow Routing}, \emph{decisive stage localization via counterfactual candidate evaluation}, and stage-specific patch-and-replay repair.
We evaluate STAR on a public large-scale benchmark and a real-world production dataset, using two RCA agent workflows and three foundation models. Experimental results show that STAR consistently improves both root cause localization and fault type classification over strong baselines. Moreover, STAR identifies the decisive faulty stage with high accuracy, repairs most initially incorrect traces within one or two replay rounds, and benefits substantially from both Fast/Slow Routing and counterfactual stage evaluation. These results suggest that explicitly modeling \emph{where} an RCA agent fails is an effective path toward reliable, debuggable, and self-repairing agentic RCA systems.
| Comments: | 11 pages |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.15581 [cs.AI] |
| (or arXiv:2605.15581v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.15581 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Junle Wang [view email]
[v1]
Fri, 15 May 2026 03:44:39 UTC (4,458 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.