# STAR: A Stage-attributed Triage and Repair framework for RCA Agents in Microservices

arXiv: https://arxiv.org/abs/2605.15581 · HTML: https://mlsanity.com/paper/2605.15581/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 15 May 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 16 of 16)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems](https://mlsanity.com/paper/2505.00212/) (2025)
- [MicroHECL: High-Efficient Root Cause Localization in Large-Scale Microservice Systems](https://mlsanity.com/paper/2103.01782/) (2021)
- [Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysis](https://mlsanity.com/paper/2502.08224/) (2025)
- [mABC: multi-Agent Blockchain-Inspired Collaboration for root cause analysis in micro-services architecture](https://mlsanity.com/paper/2404.12135/) (2024)
- [Eadro: An End-to-End Troubleshooting Framework for Microservices on Multi-source Data](https://mlsanity.com/paper/2302.05092/) (2023)
- [A Scenario-Oriented Benchmark for Assessing AIOps Algorithms in Microservice Management](https://mlsanity.com/paper/2407.14532/) (2024)

## Built on by (most cited first, 1 of 1)

- [Beyond Fault Localization: A Trajectory-Level Study of LLM Agents for Microservice Root Cause Analysis](https://mlsanity.com/paper/2608.21310/) (2026)

## Abstract (arXiv)

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 STAR, a Stage-attributed Triage and Repair framework for repairing erroneous RCA traces. STAR explicitly decomposes an RCA workflow into four structured stages, namely Evidence Package (EP), Hypothesis Set (HS), Analysis Structure (AS), and 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 Fast/Slow Routing, 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 where an RCA agent fails is an effective path toward reliable, debuggable, and self-repairing agentic RCA systems.